Article(id=1297211729834955161, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, articleNumber=null, orderNo=null, doi=10.11975/j.issn.1002-6819.202601234, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1769443200000, receivedDateStr=2026-01-27, revisedDate=1779724800000, revisedDateStr=2026-05-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1787208977421, onlineDateStr=2026-08-20, pubDate=1782748800000, pubDateStr=2026-06-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1787208977421, onlineIssueDateStr=2026-08-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1787208977420, creator=13701087609, updateTime=1787208977420, updator=13701087609, issue=Issue{id=1297211624738284246, tenantId=1146029695717560320, journalId=1296125453100220459, year='2026', volume='42', issue='12', pageStart='1', pageEnd='396', issueExtLink='null', onlineDate='null', pubDate='1782748800000', pubDateStr='2026-06-30', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1787208952364, creator='13701087609', updateTime=1787212261177, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1297225503002357852, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1297225503002357853, tenantId=1146029695717560320, journalId=1296125453100220459, issueId=1297211624738284246, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=50, endPage=59, ext={EN=ArticleExt(id=1297211730044670362, articleId=1297211729834955161, tenantId=1146029695717560320, journalId=1296125453100220459, language=EN, title=Short-term prediction of environmental parameters in a multi-tier perching layer house, columnId=1297211670816907294, journalTitle=Transactions of the Chinese Society of Agricultural Engineering, columnName=Special Topics on Smart Animal-raising Technologies and Livestock Equipment(2): Smart Equipment and Environmental Engineering, runingTitle=null, highlight=null, articleAbstract=

Multi-tier perching layer houses can offer hens with perches, nests, and multi-level activity spaces. But their complex spatial structure and airflow configuration can also lead to local environmental differences and short-term fluctuations. It is often required for the accurate short-term prediction of indoor environmental parameters under proactive ventilation control and environmental risk warning in cage-free laying hen production. This study aimed to develop a short-term prediction for indoor temperature, relative humidity, and ammonia concentration in a multi-tier perching layer house, according to multi-point monitoring data. Continuous environmental data were collected from one experimental multi-tier perching layer house. The indoor monitoring points were arranged in different perching areas, while one outdoor monitoring point was used to represent boundary environmental conditions. Time alignment and resampling at a 20 min interval, point-wise mean values, and spatial ranges were calculated after data cleaning to evaluate environmental differences among monitoring points. Pearson correlation analysis was used to examine the relationship among temperature, relative humidity, and ammonia concentration. A short-term prediction framework was then developed using gradient boosting regression. Historical observations, outdoor environmental information, and indoor–outdoor difference features were used as model inputs for temperature and relative humidity. A multivariable prediction model was constructed to combine ammonia historical concentration with temperature and relative humidity. The most recent 7 d data was used as an independent validation set. In addition, recursive prediction was performed to evaluate the model performance for a future 24 h horizon. Furthermore, 0.05 and 0.95 quantile regression models were established to generate 90% prediction intervals. The results showed that the indoor environmental parameters differed among monitoring points. The average temperature, relative humidity, and ammonia concentration were 18.99-20.88 ℃, 46.52%-51.98%, and 1.32-1.86 mg/m3, respectively, at different indoor monitoring points. The mean spatial ranges were 2.31℃, 11.84%, and 1.27 mg/m3, respectively, indicating that the parameters varied among different perching areas. Correlation analysis showed that temperature and relative humidity were negatively correlated with ammonia concentration, with correlation coefficients of −0.26 and −0.16, respectively. Ammonia concentration was dominated by its historical state, thermal and humidity conditions, as well as ventilation. In the independent validation set, the temperature prediction model achieved a coefficient of determination of 0.96, a root mean square error of 0.73 ℃, and a mean absolute error of 0.50 ℃, whereas those values were 0.97, 2.94%, and 1.77%, respectively, in relative humidity. In ammonia concentration, the multivariable prediction model achieved a coefficient of determination of 0.76, a root mean square error of 0.44 mg/m3, and a mean absolute error of 0.27 mg/m3. In the multivariable model, the coefficient of determination increased from 0.64 to 0.76, whereas the mean absolute error reduced from 0.37 to 0.27 mg/m3, compared with the univariate gradient boosting regression model with only ammonia historical information. As such, temperature and relative humidity features provided useful supplementary information for ammonia prediction. The 24 h recursive prediction showed that the stable prediction performance was maintained during continuous forecasting. Smooth prediction curves were produced without outstanding abnormal jumps. The 90% prediction intervals were also provided to quantify the fluctuation range of environmental parameters. The short-term prediction can be used to adjust proactive ventilation for the less ammonia risk environment in multi-tier perching layer houses.

, authors=Yuhang LIU1, Yu LIU1, 2, *, Chaoyuan WANG1, 2, Guanghui TENG1, 2, authorsList=Yuhang LIU, Yu LIU, Chaoyuan WANG, Guanghui TENG, authorCompany=null, correspAuthors=Yu LIU, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Transactions of the Chinese Society of Agricultural Engineering., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1297211732917768613, articleId=1297211729834955161, tenantId=1146029695717560320, journalId=1296125453100220459, language=CN, title=立体栖架养殖蛋鸡舍环境参数短期预测, columnId=1297211670993068064, journalTitle=农业工程学报, columnName=智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程, runingTitle=null, highlight=null, articleAbstract=

立体栖架蛋鸡舍采用多层空间布局,舍内气流组织复杂,易产生环境参数区域分布不均与短时动态波动问题,给鸡舍环境精准调控及风险提前预警带来较大难度。为及时掌握舍内关键环境参数的短期变化情况,支撑环境调控策略快速优化与精准施策,该研究基于多点连续监测数据,使用梯度提升回归算法分别建立可反映未来24 h舍内环境温度、相对湿度和NH3浓度变化的短期预测模型,并对模型预测性能进行验证与评价。结果表明,蛋鸡舍温度、相对湿度和NH3浓度的平均值分别为18.99~20.88 ℃、46.52%~51.98%和1.32~1.86 mg/m3,其空间极差均值分别为2.31 ℃、11.84%和1.27 mg/m3,舍内环境参数存在显著的局部差异。温度预测模型的决定系数(R2)、均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)分别为0.96、0.73 ℃和0.50 ℃,相对湿度预测模型的R2、RMSE和MAE分别为0.97、2.94%和1.77%,NH3浓度预测模型的R2、RMSE和MAE分别为0.76、0.44 mg/m3和0.27 mg/m3。温度、相对湿度和NH3浓度预测值与实测值的平均回归决定系数分别为0.95、0.96和0.71,且未来24 h递推预测曲线均能较好延续各环境参数的历史变化趋势,模型预测结果与实测值具有较好一致性。研究表明,基于梯度提升回归算法的环境参数短期预测方法可为立体栖架蛋鸡舍通风量预调、高风险时段识别及热湿与氨气协同调控提供技术支撑,对提升该养殖模式下环境管理的稳定性与精细化水平具有参考意义。

, authors=刘雨航1, 刘羽1, 2, *, 王朝元1, 2, 滕光辉1, 2, authorsList=刘雨航, 刘羽, 王朝元, 滕光辉, authorCompany=null, correspAuthors=刘羽, authorNote=

中国农业工程学会高级会员:刘羽(B040114913S)

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

, correspAuthorsNote=
刘羽,副教授,硕士生导师,研究方向为设施畜禽养殖过程控制与环境。Email:
, copyrightStatement=版权所有 © 2026 农业工程学报编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FXJuc0jmOTpIj9F/3BS0RA==, magXml=uUg6TFopn8wGnRrTBSEI6g==, pdfUrl=null, pdf=cjgt7LyY04lUD7tLR3VyRg==, pdfFileSize=1825901, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=baPuxwlxW3qPa9R41dHOmg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Qnm3t6LU/NmcVM4Jy0idFA==, mapNumber=null, fund=null)}, authors=[Author(id=1300032418413568719, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuhangliu0425@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032418501649105, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418413568719, language=EN, stringName=Yuhang LIU, firstName=Yuhang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032418560369362, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418413568719, language=CN, stringName=刘雨航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国农业大学水利与智能工程学院,北京 100083, bio={"content":"

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

"}, bioImg=null, bioContent=

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)])]), Author(id=1300032418644255444, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuyu2024@cau.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1300032418719752919, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418644255444, language=EN, stringName=Yu LIU, firstName=Yu, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032418782667480, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418644255444, language=CN, stringName=刘羽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])]), Author(id=1300032418866553562, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032418954633949, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418866553562, language=EN, stringName=Chaoyuan WANG, firstName=Chaoyuan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032419021742814, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418866553562, language=CN, stringName=王朝元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])]), Author(id=1300032419088851680, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032419181126371, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032419088851680, language=EN, stringName=Guanghui TENG, firstName=Guanghui, middleName=null, lastName=TENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032419239846628, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032419088851680, language=CN, stringName=滕光辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])])], keywords=[Keyword(id=1300032419357287141, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, orderNo=1, keyword=layer house), Keyword(id=1300032419420201702, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, orderNo=2, keyword=multi-tier perching), Keyword(id=1300032419491504871, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, orderNo=3, keyword=environmental parameters), Keyword(id=1300032419541836520, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, orderNo=4, keyword=gradient boosting regression algorithm), Keyword(id=1300032419604751081, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, orderNo=5, keyword=multivariable short-term prediction), Keyword(id=1300032419663471338, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, orderNo=1, keyword=蛋鸡舍), Keyword(id=1300032419738968811, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, orderNo=2, keyword=立体栖架), Keyword(id=1300032419797689068, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, orderNo=3, keyword=环境参数), Keyword(id=1300032419898352365, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, orderNo=4, keyword=梯度提升回归算法), Keyword(id=1300032419961266926, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, orderNo=5, keyword=多变量短期预测)], refs=[Reference(id=1300032423257989891, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=孙从佼, 于爱芝, 杨敏, 等. 2024年蛋鸡产业发展情况、未来发展趋势及建议[J]. 中国畜牧杂志, 2025, 61(3): 365-370., articleTitle=null, refAbstract=null), Reference(id=1300032423325098756, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=JEON H, SHIN H, LEE J, et al. Welfare characteristics of laying hens in aviary and cage systems[J]. Poultry Science, 2025, 104(5): 104987., articleTitle=null, refAbstract=null), Reference(id=1300032423396401925, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=席磊, 王永芬, 常杰, 等. 散养模式对蛋鸡健康与肉品质的影响[J]. 家畜生态学报, 2015, 36(2): 36-42., articleTitle=null, refAbstract=null), Reference(id=1300032423455122182, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=XI Lei, WANG Yongfen, CHANG Jie, et al. Effect of free roost feeding on health and meat quality of laying hens[J]. Journal of Domestic Animal Ecology, 2015, 36(2): 36-42. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032423559979783, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=HARTCHER K M, JONES B. The welfare of layer hens in cage and cage-free housing systems[J]. World’s Poultry Science Journal, 2017, 73(4): 767-782., articleTitle=null, refAbstract=null), Reference(id=1300032423635477256, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=谢苗苗, 李华龙, 詹凯. 基于多元数据的夏季鸡舍环境质量评价及其对产蛋性能的影响[J]. 农业工程学报, 2024, 40(8): 188-197., articleTitle=null, refAbstract=null), Reference(id=1300032423710974729, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=XIE Miaomiao, LI Hualong, ZHAN Kai. Evaluating the environmental quality of layer house in summer based on multivariate data and its impact on production performance[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(8): 188-197. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032423786472202, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=KIM D H, LEE Y K, LEE S D, et al. Impact of relative humidity on the laying performance, egg quality, and physiological stress responses of laying hens exposed to high ambient temperature[J]. Journal of Thermal Biology, 2022, 103: 103167., articleTitle=null, refAbstract=null), Reference(id=1300032423849386763, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=KIM H R, RYU C, LEE S D, et al. Effects of heat stress on the laying performance, egg quality, and physiological response of laying hens[J]. Animals, 2024, 14(7): 1076., articleTitle=null, refAbstract=null), Reference(id=1300032423912301324, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU Y, ZHANG M, LIU Q, et al. The alterations of tracheal microbiota and inflammation caused by different levels of ammonia exposure in broiler chickens[J]. Poultry Science, 2021, 100(2): 685-696., articleTitle=null, refAbstract=null), Reference(id=1300032423979410189, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=LI D P, TONG Q, SHI Z X, et al. Effects of chronic heat stress and ammonia concentration on blood parameters of laying hens[J]. Poultry Science, 2020, 99(8): 3784-3792., articleTitle=null, refAbstract=null), Reference(id=1300032424172348174, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=梁超, 尹欢欢, 李保明, 等. 蛋鸡舍热湿环境参数全年逐时动态预测模型[J]. 农业工程学报, 2021, 37(8): 229-235., articleTitle=null, refAbstract=null), Reference(id=1300032424516281104, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=LIANG Chao, YIN Huanhuan, LI Baoming, et al. Hourly model for predicting year-round temperature and relative humidity of the environment in laying hen houses[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(8): 229-235. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032424595972881, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=JI H Y, TENG G H. Multistep prediction of temperature and humidity in poultry houses based on the GFF-transformer model[J]. Frontiers of Agricultural Science and Engineering, 2025, 12(4): 803-817., articleTitle=null, refAbstract=null), Reference(id=1300032424667276050, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=XU Y D, TENG G H, ZHOU Z Y. Short-term prediction method for gas concentration in poultry houses under different feeding patterns[J]. Agriculture, 2024, 14(11): 1891., articleTitle=null, refAbstract=null), Reference(id=1300032424751162131, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=AHMADI BABADI K, KHORASANIZADEH H, AGHAEI A. CFD modeling of air flow, humidity, CO2 and NH3 distributions in a caged laying hen house with tunnel ventilation system[J]. Computers and Electronics in Agriculture, 2022, 193: 106677., articleTitle=null, refAbstract=null), Reference(id=1300032424822465300, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=BORDIGNON F, PRAVATO M, TROCINO A, et al. Environmental gradients and hen spatial distribution in a cage-free aviary system: Internet of things-based real-time monitoring for proactive management[J]. Animals, 2025, 15(9): 1225., articleTitle=null, refAbstract=null), Reference(id=1300032424939905813, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=李大鹏, 严格齐, 刘玮, 等. 基于EMD-LSTM-Attention的蛋鸡舍环境温度预测[J]. 农业工程学报, 2026, 42(5): 350-357., articleTitle=null, refAbstract=null), Reference(id=1300032425019597590, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=LI Dapeng, YAN Geqi, LIU Wei, et al. Prediction of environmental temperature in laying hen houses using EMD-LSTM-Attention model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(5): 350-357. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032425078317847, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=RATHER I H, KUMAR S, GANDOMI A H. Breaking the data barrier: A review of deep learning techniques for democratizing AI with small datasets[J]. Artificial Intelligence Review, 2024, 57: 226., articleTitle=null, refAbstract=null), Reference(id=1300032425137038104, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=XIE Y F, TUMMALA S P. Machine learning for sensor analytics: A comprehensive review and benchmark of boosting algorithms in healthcare, environmental, and energy applications[J]. Sensors, 2025, 25(23): 7294., articleTitle=null, refAbstract=null), Reference(id=1300032425195758361, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Y, ZHUANG Y R, JI B Y, et al. Prediction of laying hen house odor concentrations using machine learning models based on small sample data[J]. Computers and Electronics in Agriculture, 2022, 195: 106849., articleTitle=null, refAbstract=null), Reference(id=1300032425258672922, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=PENG C, WANG Z, LI J, et al. Prediction of ammonia concentration in a pig house based on machine learning models and environmental parameters[J]. Animals, 2022, 13(1): 165., articleTitle=null, refAbstract=null), Reference(id=1300032425334170395, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=WIENS M, VERONE-BOYLE A, HENSCHEID N, et al. A tutorial and use case example of the eXtreme Gradient Boosting (XGBoost) artificial intelligence algorithm for drug development applications[J]. Clinical and Translational Science, 2025, 18(3): e70172., articleTitle=null, refAbstract=null), Reference(id=1300032425397084956, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=SIERRA-PORTA D. Assessing the impact of missing data on water quality index estimation: a machine learning approach[J]. Discover Water, 2024, 4: 11., articleTitle=null, refAbstract=null), Reference(id=1300032425459999517, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Y, NI J Q, WANG G, et al. Concentrations and emissions of ammonia from different laying hen production systems of conventional cage, aviary and natural mating colony cage in North China Plain[J]. Applied Sciences, 2020, 10(19): 6820., articleTitle=null, refAbstract=null), Reference(id=1300032425535496990, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=MOSER J, KOHLER S, HENTGEN J, et al. Assessment of ammonia concentrations and climatic conditions in calf housing using stationary and mobile sensors[J]. Animals, 2024, 14(13): 2001., articleTitle=null, refAbstract=null), Reference(id=1300032425594217247, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG K, GUO R, ZHOU Y H, et al. Detection of NH3 in poultry housing based on tunable diode laser absorption spectroscopy combined with a micro circular absorption cell[J]. Frontiers in Physics, 2022, 10: 1051719., articleTitle=null, refAbstract=null), Reference(id=1300032425657131808, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=NATEKIN A, KNOLL A. Gradient boosting machines, a tutorial[J]. Frontiers in Neurorobotics, 2013, 7: 21., articleTitle=null, refAbstract=null), Reference(id=1300032425720046369, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=FRIEDMAN J H. Greedy function approximation: A gradient boosting machine[J]. Annals of Statistics, 2001, 29(5): 1189-1232., articleTitle=null, refAbstract=null), Reference(id=1300032425770378018, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=LALAPURA V S, AMUDHA J, SATHEESH H S. Recurrent neural networks for edge intelligence: A survey[J]. ACM Computing Surveys, 2021, 54(4): 1-38., articleTitle=null, refAbstract=null), Reference(id=1300032425837486883, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: Association for Computational Linguistics, 2014: 1724-1734., articleTitle=null, refAbstract=null), Reference(id=1300032425929761572, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=TAIEB S B, BONTEMPI G, ATIYA A F, et al. A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition[J]. Expert Systems with Applications, 2012, 39(8): 7067-7083., articleTitle=null, refAbstract=null), Reference(id=1300032426005259045, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=LI L H, LI M, YU Y, et al. Modeling and regulation of dynamic temperature for layer houses under combined positive- and negative-pressure ventilation[J]. Animals, 2024, 14(21): 3055., articleTitle=null, refAbstract=null), Reference(id=1300032427636843302, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN Y J, DENG S Z, WANG Y, et al. Thermal stability of multi-tier layer hen housing with all-year sidewall inlet ventilation system[J]. Poultry Science, 2025, 104(11): 105887., articleTitle=null, refAbstract=null), Reference(id=1300032427729117991, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=BEGGS C B, AVITAL E J. A psychrometric model to assess the biological decay of the SARS-CoV-2 virus in aerosols[J]. PeerJ, 2021, 9: e11024., articleTitle=null, refAbstract=null), Reference(id=1300032427800421160, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=SWELUM A A, EL-SAADONY M T, ABD EL-HACK M E, et al. Ammonia emissions in poultry houses and microbial nitrification as a promising reduction strategy[J]. Science of the Total Environment, 2021, 781: 146978., articleTitle=null, refAbstract=null), Reference(id=1300032427863335721, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=BIST R B, BIST D B, REGMI D, et al. Ammonia emissions, impacts, and mitigation strategies for poultry production: A critical review[J]. Journal of Environmental Management, 2023, 328: 116919., articleTitle=null, refAbstract=null), Reference(id=1300032427922055978, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=沈丰菊, 刘雪兰, 张克强. 密闭蛋鸡舍内NH3浓度变化规律及其影响因子分析[J]. 农业资源与环境学报, 2019, 36(2): 221-226., articleTitle=null, refAbstract=null), Reference(id=1300032427984970539, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=SHEN Fengju, LIU Xuelan, ZHANG Keqiang. Variation of ammonia concentration and influence factors analysis in layer house[J]. Journal of Agricultural Resources and Environment, 2019, 36(2): 221-226. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032428039496492, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=杨亮, 刘春红, 郭昱辰, 等. 基于EMD-LSTM的猪舍氨气浓度预测研究[J]. 农业机械学报, 2019, 50(增刊1): 353-360., articleTitle=null, refAbstract=null), Reference(id=1300032428127576877, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG Liang, LIU Chunhong, GUO Yuchen, et al. Prediction of ammonia concentration in fattening piggery based on EMD-LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(Supp.1): 353-360. (in Chinese with English abstract), articleTitle=null, refAbstract=null), Reference(id=1300032428190491438, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=张蕾, 冯婧, 韩静, 等. 冬季地面平养蛋鸡舍温湿度对氨气浓度的影响[J]. 畜禽业, 2019, 30(11): 1-5., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])], figs=[ArticleFig(id=1300032420129039087, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Fig.1, caption=Layout diagram of environmental monitoring equipment in a multi-tier perching layer house, figureFileSmall=EKc0kdkJ6vyuk0YS3LRWdA==, figureFileBig=SBLMWVQpx0BS7Q88XzkmQA==, tableContent=null), ArticleFig(id=1300032420196147952, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=图1, caption=立体栖架鸡舍环境监测设备布点图, figureFileSmall=EKc0kdkJ6vyuk0YS3LRWdA==, figureFileBig=SBLMWVQpx0BS7Q88XzkmQA==, tableContent=null), ArticleFig(id=1300032420284228337, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Fig.2, caption=Overall framework of collaborative prediction for environmental parameters in a multi-tier perching layer house, figureFileSmall=XBmn0j+LbZ3vcy+pHdefDw==, figureFileBig=YlZwfyMz2Znk2m6J2SZ7vw==, tableContent=null), ArticleFig(id=1300032420338754290, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=图2, caption=立体栖架蛋鸡舍环境参数协同预测总体流程

注:TinRHin和NH3in分别表示舍内温度、相对湿度和NH3浓度。Tout和RHout分别表示舍外温度和相对湿度。

, figureFileSmall=XBmn0j+LbZ3vcy+pHdefDw==, figureFileBig=YlZwfyMz2Znk2m6J2SZ7vw==, tableContent=null), ArticleFig(id=1300032420439417587, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Fig.3, caption=Correlation matrix heatmap, figureFileSmall=ddqFUZCelsD73KpbgaLb0g==, figureFileBig=EqMxEV84Tc/2eNobkZXQRw==, tableContent=null), ArticleFig(id=1300032420510720756, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=图3, caption=相关矩阵热图, figureFileSmall=ddqFUZCelsD73KpbgaLb0g==, figureFileBig=EqMxEV84Tc/2eNobkZXQRw==, tableContent=null), ArticleFig(id=1300032420577829621, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Fig.4, caption=Feature importance of prediction models for temperature, relative humidity, and NH3 concentration, figureFileSmall=F+W1Zhugf5iTUqbAfXMhoQ==, figureFileBig=JUnPYw1sK2Pd9BkmfB7Q9Q==, tableContent=null), ArticleFig(id=1300032420657521398, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=图4, caption=温度、相对湿度和NH3浓度预测模型的特征重要性, figureFileSmall=F+W1Zhugf5iTUqbAfXMhoQ==, figureFileBig=JUnPYw1sK2Pd9BkmfB7Q9Q==, tableContent=null), ArticleFig(id=1300032420720435959, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Fig.5, caption=24 h recursive predictions of indoor temperature, relative humidity and NH3 concentration in the multi-tier perching layer house, figureFileSmall=GfjOG9KMs7iM9ce3gxqQUA==, figureFileBig=8ovyxm0NANAToRB1f0ny5A==, tableContent=null), ArticleFig(id=1300032420783350520, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=图5, caption=立体栖架蛋鸡舍温度、相对湿度和NH3浓度未来24 h递推预测结果

注:黑色竖直圆点虚线为预测起点,左侧为历史真实值,右侧为未来24 h递推预测值,阴影区域为90%预测区间。

, figureFileSmall=GfjOG9KMs7iM9ce3gxqQUA==, figureFileBig=8ovyxm0NANAToRB1f0ny5A==, tableContent=null), ArticleFig(id=1300032420842070777, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Tab.1, caption=

Search space and optimal hyperparameters of GBR models

, figureFileSmall=null, figureFileBig=null, tableContent=
参数
Parameter
搜索范围
Search space
温度模型
Temperature
model
相对湿度
模型
Relative
humidity
model
NH3浓度
模型
NH3
concentration
model
损失函数
Loss function
squared error, HuberHuberHuberHuber
Huber损失函数
分位数参数
Quantile parameter
of Huber loss
0.80~0.950.850.850.90
学习率
Learning rate
0.01~0.080.0350.0350.04
最大树深度
Maximum tree depth
2~5333
子采样比例
Subsampling ratio
0.70~1.000.850.850.85
叶节点最小样本数
Minimum samples per leaf
5~20101010
回归树数量
Number of regression trees
200~600420420420
), ArticleFig(id=1300032420930151162, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=表1, caption=

GBR模型超参数搜索范围及最优值

, figureFileSmall=null, figureFileBig=null, tableContent=
参数
Parameter
搜索范围
Search space
温度模型
Temperature
model
相对湿度
模型
Relative
humidity
model
NH3浓度
模型
NH3
concentration
model
损失函数
Loss function
squared error, HuberHuberHuberHuber
Huber损失函数
分位数参数
Quantile parameter
of Huber loss
0.80~0.950.850.850.90
学习率
Learning rate
0.01~0.080.0350.0350.04
最大树深度
Maximum tree depth
2~5333
子采样比例
Subsampling ratio
0.70~1.000.850.850.85
叶节点最小样本数
Minimum samples per leaf
5~20101010
回归树数量
Number of regression trees
200~600420420420
), ArticleFig(id=1300032421001454331, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Tab.2, caption=

Environmental data in the multi-tier perching layer house

, figureFileSmall=null, figureFileBig=null, tableContent=
变量
Variable
统一窗口起止时间
Time period
理论样本数
Theoretical
sample size
有效样本数
Valid
sample size
覆盖率
Coverage
rate/%
温度
Temperature/ ℃
2019-12-12—
2020-05-02
10296981695.30
相对湿度
Relative humidity/%
2019-12-12—
2020-05-02
10296985795.74
NH3浓度
NH3 concentration/
(mg·m−3
2020-01-24—
2020-05-02
7200667892.75
), ArticleFig(id=1300032421102117628, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=表2, caption=

立体栖架蛋鸡舍环境参数

, figureFileSmall=null, figureFileBig=null, tableContent=
变量
Variable
统一窗口起止时间
Time period
理论样本数
Theoretical
sample size
有效样本数
Valid
sample size
覆盖率
Coverage
rate/%
温度
Temperature/ ℃
2019-12-12—
2020-05-02
10296981695.30
相对湿度
Relative humidity/%
2019-12-12—
2020-05-02
10296985795.74
NH3浓度
NH3 concentration/
(mg·m−3
2020-01-24—
2020-05-02
7200667892.75
), ArticleFig(id=1300032421169226493, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Tab.3, caption=

Mean values of environmental parameters at different monitoring points in the multi-tier perching layer house

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点
Monitoring point
温度
Temperature/ ℃
相对湿度
Relative humidity/%
NH3浓度
NH3 concentration/
(mg·m-3)
注:同列不同小写字母表示不同监测单元之间差异显著(P<0.05)。
Note: Different lowercase letters within the same column indicate significant differences among monitoring points (P<0.05).
PMU220.88±3.45a46.52±15.13d1.32±0.99c
PMU318.99±3.51d51.98±19.43a1.86±1.52a
PMU420.00±4.08b49.21±14.62c1.76±1.23a
PMU519.78±3.80c50.39±15.52b1.65±1.27b
), ArticleFig(id=1300032421240529662, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=表3, caption=

立体栖架蛋鸡舍不同监测单元环境参数平均值

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点
Monitoring point
温度
Temperature/ ℃
相对湿度
Relative humidity/%
NH3浓度
NH3 concentration/
(mg·m-3)
注:同列不同小写字母表示不同监测单元之间差异显著(P<0.05)。
Note: Different lowercase letters within the same column indicate significant differences among monitoring points (P<0.05).
PMU220.88±3.45a46.52±15.13d1.32±0.99c
PMU318.99±3.51d51.98±19.43a1.86±1.52a
PMU420.00±4.08b49.21±14.62c1.76±1.23a
PMU519.78±3.80c50.39±15.52b1.65±1.27b
), ArticleFig(id=1300032421316027135, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Tab.4, caption=

Performances of environment factors predicting models

, figureFileSmall=null, figureFileBig=null, tableContent=
变量
Variable
R2均方根误差
Root mean square error
(RMSE)
平均绝对误差
Mean absolute error
(MAE)
温度
Temperature/ ℃
0.960.730.50
相对湿度
Relative humidity/%
0.972.941.77
NH3浓度
NH3 concentration/(mg·m-3)
0.760.440.27
), ArticleFig(id=1300032421378941696, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=表4, caption=

环境参数预测模型性能

, figureFileSmall=null, figureFileBig=null, tableContent=
变量
Variable
R2均方根误差
Root mean square error
(RMSE)
平均绝对误差
Mean absolute error
(MAE)
温度
Temperature/ ℃
0.960.730.50
相对湿度
Relative humidity/%
0.972.941.77
NH3浓度
NH3 concentration/(mg·m-3)
0.760.440.27
), ArticleFig(id=1300032421454439169, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=EN, label=Tab.5, caption=

Overall performance comparison of mainstream models for short-term NH3 concentration prediction

, figureFileSmall=null, figureFileBig=null, tableContent=
模型ModelR2RMSE/(mg·m-3MAE/(mg·m-3
本文模型Proposed model0.760.440.27
单变量GBR
Univariate GBR
0.640.520.37
LSTM0.720.470.28
GRU0.730.460.29
), ArticleFig(id=1300032421529936642, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, language=CN, label=表5, caption=

NH3浓度短期预测主流模型总体性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型ModelR2RMSE/(mg·m-3MAE/(mg·m-3
本文模型Proposed model0.760.440.27
单变量GBR
Univariate GBR
0.640.520.37
LSTM0.720.470.28
GRU0.730.460.29
)], attaches=null, journal=Journal(id=1296123985890738214, delFlag=0, nameCn=农业工程学报, nameEn=Transactions of the Chinese Society of Agricultural Engineering, nameHistory1=null, nameHistory2=null, issn=1002-6819, eissn=null, cn=11-2047/S, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=+90GfMrDOo0sGnhM27IfIQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Transactions of the Chinese Society of Agricultural Engineering, journalRemark=null, publicationField=null, createdTime=1786949639057, updatedTime=1788949514636, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=N, firstLetterEn=N, subjectCode=Agriculture, subjectName=null, subjectCodeEn=Agriculture, subjectNameEn=null, picCn=+90GfMrDOo0sGnhM27IfIQ==, picEn=+UrL7Qgb+cjoX8OpJtziCA==, jcr=null, cjcr=null, exts=[JournalExt(id=1304512072117678568, language=CN, name=农业工程学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949514655, updatedTime=1788949514655, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304512072168010217, language=EN, name=Transactions of the Chinese Society of Agricultural Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949514667, updatedTime=1788949514667, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://tsg.tcsae.org/nygcxb/author/login, submissionEditorUrl=https://nygcxb.ijournals.cn/nygcxb/editor/login, submissionReviewUrl=http://tsg.tcsae.org/nygcxb/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1296125453100220459, websiteList=[Website(id=1296128922534564555, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/nygcxb/CN, language=CN, createTime=1786950816043, createBy=18614031015, updateTime=1786950989293, updateBy=18614031015, name=农业工程学报-中文, tplId=1146099689490845704, title=农业工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129761215009609, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=articleTextType, value=kx, createTime=1786951016000, updateTime=1786951016000, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761194038086, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=banner, value=null, createTime=1786951015995, updateTime=1786951015995, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761231786828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=grayFlag, value=0, createTime=1786951016004, updateTime=1786951016004, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761185649477, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951015993, updateTime=1786951015993, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761244369742, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=minRunFlag, value=0, createTime=1786951016007, updateTime=1786951016007, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761206621000, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/CN/file/pic, createTime=1786951015998, updateTime=1786951015998, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761240175437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=silenceFlag, value=0, createTime=1786951016006, updateTime=1786951016006, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761202426695, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1786951015997, updateTime=1786951015997, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761219203914, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeColor, value=null, createTime=1786951016001, updateTime=1786951016001, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129761227592523, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922534564555, code=themeStyle, value=null, createTime=1786951016003, updateTime=1786951016003, creator=18614031015, updator=18614031015)]), Website(id=1296128922677170905, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1296125453100220459, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/nygcxb/EN, language=EN, createTime=1786950816077, createBy=18614031015, updateTime=1786950985772, updateBy=18614031015, name=农业工程学报-英文, tplId=1146101810881728533, title=Transactions of the Chinese Society of Agricultural Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1296129731049575225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=articleTextType, value=kx, createTime=1786951008808, updateTime=1786951008808, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731028603702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=banner, value=null, createTime=1786951008803, updateTime=1786951008803, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731070546748, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=grayFlag, value=0, createTime=1786951008813, updateTime=1786951008813, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731016020789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=logo, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic?fileId=6wW+hIE4oBGmmFvGgEb5JQ==, createTime=1786951008800, updateTime=1786951008800, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731087323966, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=minRunFlag, value=0, createTime=1786951008817, updateTime=1786951008817, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731041186616, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/nygcxb/EN/file/pic, createTime=1786951008806, updateTime=1786951008806, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731078935357, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=silenceFlag, value=0, createTime=1786951008815, updateTime=1786951008815, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731032798007, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1786951008804, updateTime=1786951008804, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731053769530, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeColor, value=null, createTime=1786951008809, updateTime=1786951008809, creator=18614031015, updator=18614031015), WebsiteProps(id=1296129731062158139, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1296128922677170905, code=themeStyle, value=null, createTime=1786951008811, updateTime=1786951008811, creator=18614031015, updator=18614031015)])], journalTitle=农业工程学报, weixinUrl=null, journalUrl=http://www.tcsae.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Transactions of the Chinese Society of Agricultural Engineering, journalPhotoCn=+90GfMrDOo0sGnhM27IfIQ==, journalPhotoEn=+UrL7Qgb+cjoX8OpJtziCA==, journalFirstLetter=N, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202601234, detailUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/10.11975/j.issn.1002-6819.202601234, pdfUrlCn=https://castjournals.cast.org.cn/joweb/nygcxb/CN/PDF/10.11975/j.issn.1002-6819.202601234, pdfUrlEn=https://castjournals.cast.org.cn/joweb/nygcxb/EN/PDF/10.11975/j.issn.1002-6819.202601234, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1782748800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
立体栖架养殖蛋鸡舍环境参数短期预测
收藏切换
PDF下载
刘雨航 1 , 刘羽 1, 2, * , 王朝元 1, 2 , 滕光辉 1, 2
农业工程学报 | 智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程 2026,42(12): 50-59
收起
收藏切换
农业工程学报 |智慧养殖技术与智能畜牧装备专题(2):智能装备与环境工程 2026 , 42 (12) : 50 -59
立体栖架养殖蛋鸡舍环境参数短期预测
全屏
[Author(id=1300032418413568719, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuhangliu0425@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032418501649105, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418413568719, language=EN, stringName=Yuhang LIU, firstName=Yuhang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032418560369362, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418413568719, language=CN, stringName=刘雨航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国农业大学水利与智能工程学院,北京 100083, bio={"content":"

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

"}, bioImg=null, bioContent=

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)])]), Author(id=1300032418644255444, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuyu2024@cau.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1300032418719752919, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418644255444, language=EN, stringName=Yu LIU, firstName=Yu, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032418782667480, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418644255444, language=CN, stringName=刘羽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])]), Author(id=1300032418866553562, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032418954633949, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418866553562, language=EN, stringName=Chaoyuan WANG, firstName=Chaoyuan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032419021742814, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032418866553562, language=CN, stringName=王朝元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])]), Author(id=1300032419088851680, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1300032419181126371, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032419088851680, language=EN, stringName=Guanghui TENG, firstName=Guanghui, middleName=null, lastName=TENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1300032419239846628, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, authorId=1300032419088851680, language=CN, stringName=滕光辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1中国农业大学水利与智能工程学院,北京 100083
2农业农村部设施农业工程重点实验室,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1300032418249990856, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=1, ext=[AuthorCompanyExt(id=1300032418258379465, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China), AuthorCompanyExt(id=1300032418266768074, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418249990856, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国农业大学水利与智能工程学院,北京 100083)]), AuthorCompany(id=1300032418338071243, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, xref=2, ext=[AuthorCompanyExt(id=1300032418342265548, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China), AuthorCompanyExt(id=1300032418350654157, tenantId=1146029695717560320, journalId=1296125453100220459, articleId=1297211729834955161, companyId=1300032418338071243, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2农业农村部设施农业工程重点实验室,北京 100083)])])]
刘雨航1 , 刘羽1, 2, * , 王朝元1, 2, 滕光辉1, 2
作者信息
  • 1中国农业大学水利与智能工程学院,北京 100083
  • 2农业农村部设施农业工程重点实验室,北京 100083
通讯作者:
刘羽,副教授,硕士生导师,研究方向为设施畜禽养殖过程控制与环境。Email:
作者简介:

中国农业工程学会高级会员:刘羽(B040114913S)

刘雨航,研究方向为设施畜禽养殖环境与控制。Email:

Short-term prediction of environmental parameters in a multi-tier perching layer house
Yuhang LIU1 , Yu LIU1, 2, * , Chaoyuan WANG1, 2, Guanghui TENG1, 2
Affiliations
  • 1College of Water Resources and Intelligence Engineering, China Agricultural University, Beijing 100083, China
  • 2Key Laboratory of Protected Agricultural Engineering, Ministry of Agriculture and Rural Affairs, Beijing 100083, China
出版时间: 2026-06-30 doi: 10.11975/j.issn.1002-6819.202601234
文章导航
收藏切换

立体栖架蛋鸡舍采用多层空间布局,舍内气流组织复杂,易产生环境参数区域分布不均与短时动态波动问题,给鸡舍环境精准调控及风险提前预警带来较大难度。为及时掌握舍内关键环境参数的短期变化情况,支撑环境调控策略快速优化与精准施策,该研究基于多点连续监测数据,使用梯度提升回归算法分别建立可反映未来24 h舍内环境温度、相对湿度和NH3浓度变化的短期预测模型,并对模型预测性能进行验证与评价。结果表明,蛋鸡舍温度、相对湿度和NH3浓度的平均值分别为18.99~20.88 ℃、46.52%~51.98%和1.32~1.86 mg/m3,其空间极差均值分别为2.31 ℃、11.84%和1.27 mg/m3,舍内环境参数存在显著的局部差异。温度预测模型的决定系数(R2)、均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)分别为0.96、0.73 ℃和0.50 ℃,相对湿度预测模型的R2、RMSE和MAE分别为0.97、2.94%和1.77%,NH3浓度预测模型的R2、RMSE和MAE分别为0.76、0.44 mg/m3和0.27 mg/m3。温度、相对湿度和NH3浓度预测值与实测值的平均回归决定系数分别为0.95、0.96和0.71,且未来24 h递推预测曲线均能较好延续各环境参数的历史变化趋势,模型预测结果与实测值具有较好一致性。研究表明,基于梯度提升回归算法的环境参数短期预测方法可为立体栖架蛋鸡舍通风量预调、高风险时段识别及热湿与氨气协同调控提供技术支撑,对提升该养殖模式下环境管理的稳定性与精细化水平具有参考意义。

蛋鸡舍  /  立体栖架  /  环境参数  /  梯度提升回归算法  /  多变量短期预测

Multi-tier perching layer houses can offer hens with perches, nests, and multi-level activity spaces. But their complex spatial structure and airflow configuration can also lead to local environmental differences and short-term fluctuations. It is often required for the accurate short-term prediction of indoor environmental parameters under proactive ventilation control and environmental risk warning in cage-free laying hen production. This study aimed to develop a short-term prediction for indoor temperature, relative humidity, and ammonia concentration in a multi-tier perching layer house, according to multi-point monitoring data. Continuous environmental data were collected from one experimental multi-tier perching layer house. The indoor monitoring points were arranged in different perching areas, while one outdoor monitoring point was used to represent boundary environmental conditions. Time alignment and resampling at a 20 min interval, point-wise mean values, and spatial ranges were calculated after data cleaning to evaluate environmental differences among monitoring points. Pearson correlation analysis was used to examine the relationship among temperature, relative humidity, and ammonia concentration. A short-term prediction framework was then developed using gradient boosting regression. Historical observations, outdoor environmental information, and indoor–outdoor difference features were used as model inputs for temperature and relative humidity. A multivariable prediction model was constructed to combine ammonia historical concentration with temperature and relative humidity. The most recent 7 d data was used as an independent validation set. In addition, recursive prediction was performed to evaluate the model performance for a future 24 h horizon. Furthermore, 0.05 and 0.95 quantile regression models were established to generate 90% prediction intervals. The results showed that the indoor environmental parameters differed among monitoring points. The average temperature, relative humidity, and ammonia concentration were 18.99-20.88 ℃, 46.52%-51.98%, and 1.32-1.86 mg/m3, respectively, at different indoor monitoring points. The mean spatial ranges were 2.31℃, 11.84%, and 1.27 mg/m3, respectively, indicating that the parameters varied among different perching areas. Correlation analysis showed that temperature and relative humidity were negatively correlated with ammonia concentration, with correlation coefficients of −0.26 and −0.16, respectively. Ammonia concentration was dominated by its historical state, thermal and humidity conditions, as well as ventilation. In the independent validation set, the temperature prediction model achieved a coefficient of determination of 0.96, a root mean square error of 0.73 ℃, and a mean absolute error of 0.50 ℃, whereas those values were 0.97, 2.94%, and 1.77%, respectively, in relative humidity. In ammonia concentration, the multivariable prediction model achieved a coefficient of determination of 0.76, a root mean square error of 0.44 mg/m3, and a mean absolute error of 0.27 mg/m3. In the multivariable model, the coefficient of determination increased from 0.64 to 0.76, whereas the mean absolute error reduced from 0.37 to 0.27 mg/m3, compared with the univariate gradient boosting regression model with only ammonia historical information. As such, temperature and relative humidity features provided useful supplementary information for ammonia prediction. The 24 h recursive prediction showed that the stable prediction performance was maintained during continuous forecasting. Smooth prediction curves were produced without outstanding abnormal jumps. The 90% prediction intervals were also provided to quantify the fluctuation range of environmental parameters. The short-term prediction can be used to adjust proactive ventilation for the less ammonia risk environment in multi-tier perching layer houses.

layer house  /  multi-tier perching  /  environmental parameters  /  gradient boosting regression algorithm  /  multivariable short-term prediction
刘雨航, 刘羽, 王朝元, 滕光辉. 立体栖架养殖蛋鸡舍环境参数短期预测. 农业工程学报, 2026 , 42 (12) : 50 -59 . DOI: 10.11975/j.issn.1002-6819.202601234
Yuhang LIU, Yu LIU, Chaoyuan WANG, Guanghui TENG. Short-term prediction of environmental parameters in a multi-tier perching layer house[J]. Transactions of the Chinese Society of Agricultural Engineering, 2026 , 42 (12) : 50 -59 . DOI: 10.11975/j.issn.1002-6819.202601234
蛋鸡产业是中国畜牧业的重要组成部分,对国家粮食安全和乡村振兴具有重要意义,2024年中国鸡蛋产量约为2941万t[1]。随着蛋鸡养殖由高密度笼养向健康化、福利化和精细化管理方向发展,立体栖架养殖模式逐渐受到关注[2]。与叠层笼养系统相比,立体栖架鸡舍可为蛋鸡提供栖架、巢箱和活动空间等资源,有利于蛋鸡自然行为表达和生产性能提升,其产蛋率可达93.73%,且更早达到产蛋高峰并维持更长时间[3],为中国蛋鸡养殖向高效、绿色、健康方向转型提供了设施支撑[4]。舍内温度、相对湿度、气体环境等环境因子的异常变化会显著影响蛋鸡生长和生产性能[5]。当环境处于较高的热湿状态时,蛋鸡会出现热应激反应[6],导致采食量下降和产蛋率降低[7]。而氨气(NH3)作为首要有害气体,即使在低浓度下长期作用,也会严重损害蛋鸡呼吸道黏膜屏障,使病原体更易侵入机体,影响蛋鸡健康状况和生产性能[8]。热湿环境与NH3的协同作用会进一步放大这些负面影响,对动物福利与养殖效益构成严重威胁[9]。预测舍内环境因子是开展精细化通风调控的前提,能为调控决策提供科学依据,从而有效规避不良环境的影响。
温度[10]和相对湿度[11]是影响蛋鸡舍热湿环境的重要参数,其短期变化直接关系到舍内热负荷水平、通风调控需求和热应激风险。NH3浓度与粪污分解、通风稀释和舍内空气质量变化密切相关,是影响蛋鸡健康和生产性能的重要有害气体指标[12]。已有蛋鸡舍环境预测研究为鸡舍环境主动调控提供了方法基础,但相关模型通常基于特定鸡舍结构、通风方式和测点布设条件建立,其输入特征与目标变量之间的关系会因应用场景不同而发生变化[13]。与传统笼养鸡舍相比,立体栖架蛋鸡舍内部设有多层平台、栖架、巢箱和清粪带,鸡群可在不同层级和功能区域内自由活动。鸡只产热散湿、粪污排放和通风稀释过程在空间上相互叠加,使温度、相对湿度和NH3浓度更易受到位置、鸡群分布和局部气流条件的共同影响[14]。因此有必要构建可稳定反映鸡舍不同位置环境温度、相对湿度和NH3浓度短期预测模型,为该养殖模式下通风预调、局部风险识别和环境精准管理提供依据。
机器学习算法的应用为提升预测精度提供了有效支撑。在深度学习模型方面,JI和TENG[11]构建了基于门控特征融合的Transformer模型(gated feature fusion-transformer,GFF-Transformer),用于家禽舍温度和相对湿度多步预测,并与长短期记忆网络(long short-term memory,LSTM)、门控循环单元(gated recurrent unit,GRU)和Transformer等时序模型进行对比。结果表明,深度学习模型能够较好捕捉禽舍温湿度序列的长期依赖关系和多步变化特征。李大鹏等[15]将经验模态分解(empirical mode decomposition,EMD)、LSTM与注意力机制(attention mechanism,Attention)相结合,构建EMD-LSTM-Attention模型用于传统笼养蛋鸡舍环境温度预测,在全年数据集上取得了较好的预测效果。上述研究为立体栖架蛋鸡舍环境预测提供了参考,但深度模型在现场监测场景下需要更大的训练数据规模与更高的算力投入,成本相对更高[16]。相比之下,梯度提升算法更适用于结构化传感器数据,能够捕捉非线性关系和特征间的相互作用,借助滞后项、滚动统计等特征支持,稳健性较强适合工程部署[17]。已有研究表明,梯度提升类模型在畜禽舍环境参数预测中具有较好的适用性。LIU等[18]采用极端梯度提升模型(extreme gradient boosting, XGBoost)基于小样本监测数据预测蛋鸡舍气味浓度,并与支持向量回归和反向传播神经网络进行对比,结果表明XGBoost在非线性和小样本条件下仍能获得更高预测精度,但模型效果对输入变量质量与工况覆盖范围具有依赖性。PENG等[19]面向猪舍NH3浓度预测,对比决策树、支持向量回归与XGBoost等模型,结果显示XGBoost在多种输入方案下拟合度较高,R2可达0.91,整体优于单棵决策树与支持向量回归,说明梯度提升方法在结构化环境数据中具有较强的非线性表达能力,适合用于畜禽舍环境参数预测。
梯度提升回归(gradient boosting regressor, GBR)方法,可在保证精度的同时降低训练与部署成本,便于在工况变化后快速更新模型,更适合用于预警与风险识别。GBR不仅具有强大的非线性拟合能力与较高的计算效率[20],且具有处理缺失值的能力[21],适用于构建多源环境数据的快速迭代预测模型。相较于参数量大且训练成本高的深度学习模型,GBR模型更便于现场部署与在线更新,综合成本更低[17]
针对立体栖架蛋鸡舍环境参数短期变化预测需求,本研究以立体栖架养殖蛋鸡舍为研究对象,基于舍内不同监测单元的数据构建温度、相对湿度和NH3浓度预测数据集,采用梯度提升回归算法对环境参数未来24 h的变化进行短期预测。研究旨在实现立体栖架蛋鸡舍未来24 h内温度、湿度及NH3浓度的稳定预测,为鸡舍通风系统的前瞻性控制与环境精准管理提供可靠依据。
试验在中国农业大学上庄实验基地进行,地点位于北京市海淀区(116.11°E,40.08°N),属暖温带半湿润季风气候区。试验对象为一栋立体栖架蛋鸡舍,钢结构框架、夹芯彩钢板围护,内部布置两列立体笼架。鸡舍平面尺寸为90.0 m×12.0 m×3.5 m。饲养品种为京粉6号,存栏规模2952只;笼架单元尺寸4.8 m×2.8 m×3.3 m,平均饲养密度14.06只/m2。通风方式为机械通风,在端墙配置3台风机。鸡舍采用清粪带清粪,16:00—17:00开启一次。
为全面反映鸡舍内外环境变化规律,在试验鸡舍内外布设了5个环境监测单元(portable monitoring unit, PMU),具体位置如图1所示。
各监测单元用于同步采集温度、相对湿度和NH3浓度数据。PMU1布设于鸡舍进风端附近,用于反映进入鸡舍气流的环境状态。PMU2和PMU3布设于东侧栖架区域,PMU4和PMU5布设于西侧栖架区域,用于采集两列栖架饲养区域内的环境参数。各监测单元参照蛋鸡舍温度、相对湿度及气体浓度监测中常用的舍内布点高度[22],安装高度均距地面1.5 m。监测系统采样间隔为10 min,所有传感器数据经无线网络实时传输至上位机存储。监测期间鸡舍运行状态保持稳定,采样时间为2019年12月至2020年5月。
温度和相对湿度由HOBO U23-001温湿度记录仪(Onset Computer Corp.,美国)测定,温度和相对湿度量程分别为–40~70 ℃、0~100%,精度分别为±0.18 ℃和±2.5%。NH3浓度采用ME3-NH3型电化学传感器(Winsen Electronics,中国),量程0~35 mg/m3,精度为±5%满量程。所有传感器在试验前均通过标准气体校准。采集到的原始数据经时间统一、缺失插补与异常值剔除后,用于后续的时间序列分析和预测模型构建。
各监测单元原始数据的时间戳格式与记录间隔存在差异。为保证数据一致性,首先对原始文件进行字段识别,将各类型时间字段统一成标准日期时间格式;之后剔除无效数据和缺省值,对重复时间戳仅保留首次记录;最后按时间升序排列构建原始时序索引。
数据清洗与时间统一详细步骤为:首先去除数值列中的非数字字符并转换为标准数值型,然后依据传感器量程对温度、相对湿度和NH3浓度设定物理边界,剔除超出合理范围的异常观测值[23]。温度、相对湿度和NH3浓度的物理边界分别为−20~50 ℃、0~100%和0~35 mg/m3。对于温度和相对湿度数据,剔除异常值后采用时间插值法修复短时间缺失值。由于NH3浓度数据更易受到传感器波动和局部扰动影响[24],在物理边界筛选后,先将数据重采样至20 min时间间隔,再采用滚动中位数绝对偏差(median absolute deviation, MAD)法识别异常值。考虑到重采样后72个时间步恰好对应24 h,能覆盖鸡舍环境参数的昼夜变化周期,本研究以72个时间步作为滚动窗口,计算各时刻的局部中位数与MAD。当某一时刻的NH3浓度值相对于局部中位数的偏离超过设定阈值时,将其判定为异常值,并采用时间插值法进行修复。以PMU1作为舍外环境变化的参考点,将所有监测点数据按统一时间轴对齐。
为明晰立体栖架蛋鸡舍内不同区域环境参数的分布情况,并为后续数据处理和环境参数预测特征选择提供依据,本研究采用点位平均值和多点极差分析了温度、相对湿度和NH3浓度在不同监测区域间的差异。在每一时刻计算不同监测单元间测量值的最大值与最小值之差,用于反映舍内不同区域间环境参数的最大差异。设第t个时刻PMU2~PMU5对某一环境参数的观测值分别为$ {q}_{2,t},{q}_{3,t},{q}_{4,t},{q}_{5,t} $,则该时刻该环境参数的空间极差$ \text{Δ}{q}_{t} $
$ \text{Δ}{q}_{t}=\underset{j\in\text{{2,3,4,5}}}{\max } \left({q}_{j,t}\right)-\underset{j\in\text{{2,3,4,5}}}{\min } \left({q}_{j,t}\right) $
式中$ \text{Δ}{q}_{t} $为第t个时刻某一环境参数在PMU2-PMU5任意两个监测单元之间的空间极差。$ {q}_{j,t} $为第$ t $个时刻第$ j $个监测单元的环境参数观测值。$ j $为监测单元编号,$ t $为时间步。
为反映温度、相对湿度与NH3浓度在时间上的协同变化特征,需将各环境参数进行标准化处理,标准化方程为
$ {z}_{c,t}=\frac{{x}_{c,t}-{\overline{x}}_{c}}{{s}_{c}} $
式中$ {z}_{c,t} $$ {x}_{c,t} $分别为第c类环境参数在第$ t $个时刻标准化后的无量纲值和原始观测值。$ {\overline{x}}_{c} $为第$ c $类环境参数原始序列的平均值。$ {s}_{c} $为第$ c $类环境参数原始序列的标准差。
采用皮尔逊相关系数计算温度、相对湿度与NH3浓度之间的相关性,并将相关系数矩阵以热力图形式进行可视化,直观展示各变量之间的协同强度与关系,为后续多变量预测模型的特征选取和结果解释提供依据。
本研究采用GBR构建鸡舍环境参数的短期预测模型。该方法在加性框架下通过逐步拟合残差逼近目标函数[25],能够较好反映多类因素与环境参数变化之间的复杂关系[26]。GBR将多个弱回归树按加法形式进行集成,模型可表示为
$ F_G\left({\boldsymbol{u}}\right)=F_0\left({{\boldsymbol{u}}}\right)+\sum\limits_{{g}=1}^G{\eta_g}{{{h}_g}}\left({\boldsymbol{u}}\right) $
式中$ {\boldsymbol{u}} $为模型输入特征向量,$ F_G\left({\boldsymbol{u}}\right) $为最终集成模型的预测函数,$ {F}_{0}({\boldsymbol{u}}) $为初始模型,$ h_g\left({\boldsymbol{u}}\right) $为第$ g $棵回归树,$ {\eta }_{g} $为第$ g $棵回归树对应的步长系数,$ G $为回归树总数。
在训练过程中,GBR以给定损失函数为目标,在函数空间中采用逐步逼近的方式进行优化。每一轮迭代以当前模型预测值$ {F}_{r-1}(u) $为基础,则第$ i $个样本在该轮迭代中的残差计算式为
$ {e}_{i,r}={y}_{i}-{F}_{r-1}({{u}}_{i}) $
式中$ {e}_{i,r} $为第$ r $轮迭代时第$ i $个样本的残差。$ {y}_{i} $为第$ i $个样本的观测值。$ {u}_{i} $为第$ i $个样本的输入特征向量。$ {F}_{r-1}\left({u}_{i}\right) $为第$ \mathit{ }r-1 $轮模型对第$ i $个样本的预测值。$ i $为样本编号,$ r $为迭代轮数。
之后训练新的回归树$ \mathit{_{ }^{ }h}_{ }^{\left(r\right)}\left(u\right) $拟合残差$ {e}_{i,r} $,并确定步长系数$ {\eta }^{(r)} $,模型更新为
$ {F}_{r}({u})={F}_{r-1}({u})+{\eta }^{(r)}{{h}}^{(r)}({u}) $
式中$ {F}_{r}(u) $为第$ r\mathit{ } $轮迭代后的模型预测函数,$ {F}_{r-1}(u) $为第$ \mathit{r}-1 $轮迭代后的模型预测函数,$ {h}^{(r)}(u) $为第$ r $轮迭代中训练得到的回归树,$ {\eta }^{(r)} $为第$ r $轮迭代对应的步长系数。通过多轮迭代,模型逐步逼近目标函数。
温度、相对湿度和NH3浓度预测模型均采用GBR框架,根据不同环境参数变化特点,设计不同的建模方式。温度、相对湿度与NH3浓度协同预测流程如图2所示。
温度和相对湿度采用基线预测与GBR残差修正相结合的方法。基线预测综合上一时刻观测值、前一日同一时刻观测值以及室内外差值的近期变化信息,用于获得目标变量下一时刻的初始预测值。以实际观测值与基线预测值之间的差值作为GBR的学习目标。在预测阶段,先计算基线预测值,再由GBR输出残差修正量,二者相加得到最终预测值。NH3浓度预测同样采用基线预测与GBR残差修正相结合的方法。基线预测主要依据NH3浓度上一时刻状态和前一日同一时刻状态建立。在此基础上将温度、相对湿度及其室内外差值等特征作为GBR输入变量,用于预测NH3浓度的残差修正量,使模型能够同时利用NH3浓度自身历史变化信息和热湿环境信息。
考虑到现场监测数据中可能仍存在少量未完全剔除的异常扰动,3类环境参数的模型均采用Huber损失函数,以提高模型对离群值和局部突变的适应能力。同时为了量化未来24 h预测的不确定性,本研究采用GBR分位数回归方法,分别建立0.05和0.95分位数预测模型,获得90%预测区间,以为鸡舍通风系统的提前调控和高风险时段预警提供量化依据。
预测对象为立体栖架蛋鸡舍内温度、相对湿度和NH3浓度。针对每一类环境参数,先分别利用PMU2~PMU5各点位的时间序列数据构建样本,再按照时间顺序将不同点位样本合并形成统一样本集。
为使模型有效捕捉时序动态特征,本研究构建了历史滞后值、差分项、滚动均值以及滚动标准差4个输入特征。历史滞后值指前几个时刻的真实观测值,用于反映环境参数的短时延续性。差分项为相邻时刻观测值之间的变化量,可用于描述参数变化的方向和快慢。滚动均值为某一时间窗口内观测值的平均水平,用于反映参数的总体变化水平。滚动标准差为某一时间窗口内观测值的离散程度,用于反映局部时段内环境参数的波动强弱。
温度和相对湿度预测模型采用融合历史序列与舍外环境信息的建模框架。模型数据统一重采样为20 min间隔,其中前1、2、3步分别对应20、40、60 min,可反映环境参数的短时连续变化;前6步和12步分别对应2 h和4 h,可反映环境参数的中短期变化;前72步对应24 h,可引入前一日同一时刻信息,用于表征环境参数的昼夜周期特征。因此,模型输入特征包括目标点当前值及前1、2、3、6、12、72步滞后值。在变化趋势特征构建方面,选取前1步和前3步差分,分别描述相邻时刻变化和近1 h变化趋势。选取前3、6、12步窗口计算滚动均值,分别反映近1、2、4 h内的局部平均水平。选取前3步和前6步窗口计算滚动标准差,用于表征短时间内环境参数的局部波动强度。为反映舍外边界条件对舍内环境的影响,模型进一步引入舍外PMU1对应环境参数的当前值、滞后项、滚动均值和差分项,并构造室内外差值特征,以表征舍外环境变化与舍内环境状态之间的差异。
NH3浓度预测采用温湿协同的建模框架。模型首先构造NH3当前值、滞后项、差分项、滚动均值和滚动标准差。为反映热湿环境对NH3累积和稀释过程的影响,模型引入目标点当前时刻的温度、相对湿度、舍外温度、舍外相对湿度及其室内外差值,同时加入目标点温度和相对湿度的滞后项、滚动均值和差分项。为满足多步递推预测的需要,模型还引入下一时刻舍内外温湿度预测值及其差值,并构造温度与相对湿度的交互项,以提高模型对温湿协同作用的反映能力。
为评估模型在当前工况下的短期预测性能,本研究采用前期样本训练模型,并使用紧邻训练集之后的连续7 d数据进行验证。温度、相对湿度和NH3浓度预测模型均以2020年4月25日之前的数据作为训练集,以2020年4月26日至2020年5月2日的连续7 d数据作为独立验证集。模型训练和验证均在Python环境下完成,模型采用scikit-learn中的Gradient Boosting Regressor。
为确定GBR模型超参数,本研究模型构建过程中的超参数优化以决定系数(R2)最大为主要依据、同时结合均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)评价模型稳定性。模型训练中比较平方误差损失和Huber损失两种损失函数,并根据验证集结果确定最终设置。其中,Huber损失函数分位数参数用于调节模型对较大残差的敏感程度,参数值越大,模型对较大残差的容忍范围越宽。温度和相对湿度采用相同的参数搜索范围和最终参数设置。NH3浓度采用单独设置参数搜索范围并确定最优参数。各模型参数搜索范围及最终参数见表1
为提高模型对环境参数局部波动的识别能力,训练过程中对样本设置了非均匀权重。温度和相对湿度预测模型的样本权重由时间权重、局部波动权重和基线偏离权重共同确定。经预试验分析,温度和相对湿度预测模型的时间权重沿训练集时间顺序由0.88逐渐增加至1.18,即越接近验证期的样本权重越高,越早期的样本权重越低。局部波动权重根据前1步差分构造,基线偏离权重根据基线预测值与前一时刻观测值之差的绝对值构造,用于增强模型对短时变化和基线偏离较大样本的修正能力。NH3浓度预测模型的样本权重由时间权重和波动权重共同确定。经预试验分析,NH3浓度预测模型的时间权重沿训练集时间顺序由1.00线性增加至1.80。NH3浓度波动性更强,单步差分易受瞬时噪声影响[24],因此采用6步滚动标准差表征其局部波动程度。6个时间步对应2 h,既能反映短时间尺度内NH3浓度变化,又可减弱单点异常值对权重计算的影响。通过上述权重设置,模型在保持整体训练样本信息利用的基础上,可进一步提高对近期变化和局部波动过程的响应能力。模型训练完成后,在验证集上计算模型的整体性能指标,并分别统计PMU2~PMU5的验证结果,以检验模型在不同监测点上的泛化能力。模型性能采用决定系数R2、RMSE和MAE进行评价。对验证集样本$ \left\{{y}_{i},{\hat{y}}_{i}\right\}_{i=1}^{N} $,评价指标计算式如下:
$ {R}^{2}=1-\frac{\displaystyle\sum\nolimits_{i=1}^{{n}_{v}}{\left({y}_{i}-{\hat{y}}_{i}\right)}^{2}}{\displaystyle\sum\nolimits_{i=1}^{{n}_{v}}{\left({y}_{i}-\overline{y}\right)}^{2}} $
$ \mathrm{RMSE}=\sqrt{\frac{1}{{n}_{v}}\sum\nolimits_{i=1}^{{n}_{v}}{\left({y}_{i}-{\hat{y}}_{i}\right)}^{2}} $
$ \mathrm{MAE}=\frac{1}{{n}_{v}}\sum\nolimits_{i=1}^{{n}_{v}}\left| {y}_{i}-{\hat{y}}_{i}\right| $
式中$ {\hat{y}}_{i} $为第$ i $个验证样本的模型预测值;$ \overline{y} $为验证集中观测值的平均值;$ {n}_{v} $为验证样本数。
为解释模型预测性能的来源并识别关键影响因素,本研究采用置换重要性方法(permutation importance)在独立验证集上开展特征重要性分析。特征是指输入到模型中的各类具体预测因子。首先利用训练完成的模型在原始验证集上进行预测,并计算基准均方根误差,记为$ \text{RMS}{\text{E}}_{0} $。针对第$ \mathit{ }p $个输入特征,随机打乱该特征在验证集中的取值顺序,以破坏其与目标变量之间的统计关联,再将扰动后的验证集输入模型进行预测,得到第$ b $次置换后的均方根误差,记为$ \text{RMSE}_{p,b}^{\text{perm}} $。第$ p $个特征的置换重要性分数$ \text{P}{\text{I}}_{p} $定义为
$ \mathrm{P}{\text{I}}_{p}=\frac{1}{B}\sum\nolimits_{{b=1}}^{{B}}\left(\text{RMSE}_{p,b}^{\text{perm}}\text{-RMS}{\text{E}}_{0}\right) $
式中$ \text{P}{\text{I}}_{p} $为第$ p $个输入特征的置换重要性分数,$ \text{RMS}{\text{E}}_{0} $为未置换任何特征时模型在验证集上的基准均方根误差,$ \text{RMSE}_{p,b}^{\text{perm}} $为第$ b $次随机置换第$ p $个特征后得到的均方根误差,$ B $为重复置换次数,$ \mathit{p} $为特征编号,$ b\mathit{ } $为重复置换编号。
为反映重复置换结果的离散程度,进一步计算第$ p $个特征置换重要性结果的标准差$ s_{PI,p}\mathit{ } $,定义为
$ {s}_{PI{,p}}=\sqrt{\frac{1}{B-1}\sum\nolimits_{{b=1}}^{{B}}{\left[\left(\text{RMSE}_{p,b}^{\text{perm}}\text{-RMS}{\text{E}}_{0}\right)\text{-P}{\text{I}}_{p}\right]}^{2}} $
式中$ \mathit{s_{PI,p}\mathit{ }} $为第$ p $个输入特征置换重要性结果的标准差。
温度和相对湿度预测模型重复置换10次,NH3浓度预测模型重复置换20次,统计各输入特征$ \text{P}{\text{I}}_{p} $的均值和标准差。
为评估模型在立体栖架蛋鸡舍环境参数短期预测任务中的性能,本研究选取单变量GBR、长短期记忆网络(LSTM)和门控循环单元网络(GRU)作为对比模型。LSTM是一种通过引入输入门、遗忘门和输出门控制信息存储与传递的循环神经网络,能够较好地缓解长序列建模中的梯度消失问题[27]。GRU是在循环神经网络基础上提出的一种门控结构,通过更新门和重置门实现对时序信息的选择性保留与更新,在保持较强时序建模能力的同时具有更简洁的结构[28]。模型性能采用R2、RMSE与MAE进行评价。
模型训练完成后,采用时间序列递推方式生成未来24 h、共72个时间步的预测序列。以当前时刻为起点,先利用已有观测值预测下一时刻的环境参数,再将该预测值回填到历史序列中,作为下一步预测的输入,依次向前递推。对于温度和相对湿度预测模型,根据更新后的时序特征分别预测各监测单元的数值。得到未来24 h的温度和相对湿度序列后,将其作为协同输入变量引入NH3浓度预测模型,预测各点位NH3浓度变化。
在多步递推预测过程中,模型误差会随着预测步长增加而逐渐累积,进而导致个别时刻出现不合理变化[29]。为减轻误差累积和数据异常跳变的影响,本研究根据历史观测数据统计各环境参数的最大单步变化幅度,对相邻时刻的预测增量进行约束,避免预测值出现明显偏离实际变化规律的突变。在得到完整递推预测序列后,采用指数平滑方法对局部异常波动进行处理,以提高预测曲线的连续性和稳定性。为进一步评价预测值与实测值的一致性,本研究基于验证集结果,以实测值为自变量、预测值为因变量进行一元线性回归分析,并计算回归决定系数。各环境参数分别计算PMU2~PMU5各监测单元的回归决定系数,再取平均值作为预测一致性的量化评价指标。
表2列出了各环境参数原始监测数据的有效时间范围与覆盖情况。各环境参数的有效记录覆盖率均在90%以上,数据连续性较好,为后续建模提供了可靠基础。
表3反映了不同监测单元温度、相对湿度和NH3浓度的差异。不同监测单元之间温度的差异显著(P<0.05),最大平均差值为1.89 ℃,空间极差为2.31 ℃,中位数为2.00 ℃,表明舍内温度在不同区域间存在空间分布差异。这一结果与机械通风蛋鸡舍热环境分布的一般规律基本一致[30],立体栖架结构会改变舍内气流组织和热量分配,进而影响局部温度分布及其波动幅度[31]。同时,不同监测单元之间相对湿度的差异显著(P<0.05),最大平均差值为5.46个百分点,空间极差为11.84%,中位数为11.00%,说明相对湿度的空间差异较为明显。相对湿度同时受水汽产生和通风排湿等过程影响,在舍内温度较高且通风排湿效果较好的条件下,不同位置的相对湿度水平往往表现出明显的空间不均匀性[32]
NH3浓度的舍内分布情况与温度和相对湿度相同,不同监测单元之间NH3浓度差异显著(P<0.05),最大平均差值为0.54 mg/m3,空间极差为1.27 mg/m3,中位数为0.73 mg/m3,说明舍内NH3浓度也存在局部差异。由于NH3主要来源于粪污中含氮物质在微生物作用下的分解与挥发,其空间分布通常受粪污暴露强度、清粪方式和通风稀释等因素共同控制[33]。尽管各监测点的平均浓度整体处于较低水平,但局部点位之间仍存在一定差异,说明鸡舍内部NH3分布并不均匀。因此,开展鸡舍内部NH3浓度预测对于识别局部高风险时段和及时优化通风调控具有实际意义[34]
由上述分析可知,立体栖架蛋鸡舍内温度、相对湿度和NH3浓度均具有一定空间不均匀性。后续预测模型构建中保留PMU2~PMU5各监测点独立样本,以反映不同区域环境参数变化特征。
图3为温度、相对湿度与NH3浓度之间的皮尔逊相关系数矩阵。结果显示温度和相对湿度与NH3浓度均呈负相关关系,主要原因是鸡舍在温度和相对湿度过高时会提高通风量来改善舍内环境,同时导致NH3浓度降低[35]。因此在后续NH3浓度预测中同时引入温度和相对湿度信息,可以提高对NH3浓度变化过程的表征能力。
各环境参数预测模型在验证集上的主要性能指标如表4所示。
温度和相对湿度预测模型的R2分别为0.96和0.97,说明模型能够较好地反映鸡舍温湿度的短期变化,并在不同监测区域都保持较好的预测能力。NH3浓度预测模型整体的R2、RMSE和MAE分别为0.76、0.44 mg/m3和0.27 mg/m3,整体预测精度低于温度和相对湿度预测模型,NH3浓度的影响因素较多,短期变化更复杂,不确定性也更强[36]。NH3浓度除受自身历史变化影响外,还与局部温湿状态和环境扰动密切相关,其短期波动和区域差异均较温度、相对湿度更复杂[37]
为进一步解释模型预测性能的来源,本研究在独立验证集上采用置换重要性方法分析各特征的贡献。温度、相对湿度和NH3浓度统一预测模型中主要特征的置换重要性结果如图4所示。图中“初步预测”为根据历史状态和经验规律得到的基础预测结果,“预测误差”为初步预测值与实际观测值之间的差值,“一天中的时间特征”用于反映不同时刻对相对湿度变化的影响。
温度预测模型的重要特征主要为在前一天同一时刻温差和近20 min变化值,说明温度变化同时受昼夜周期和外部边界条件的影响。相对湿度预测模型中,相对湿度初步预测值贡献最高,其余重要特征主要包括近20 min湿度变化值和部分环境变化项,表明相对湿度预测不仅与历史状态有关,也受到外界条件变化的影响。NH3浓度预测模型中,NH3浓度的初步预测值仍占主导,但下一时刻湿度预测、20 min前相对湿度以及下一时刻温湿交互项等特征也具有一定贡献,说明NH3浓度不仅由自身历史序列决定,而是多种因素综合作用的结果[33]。温湿度信息能够补充反映NH3累积、挥发和通风稀释过程,可以提高NH3浓度预测适用性。
由于温湿度序列的周期性和平稳性更强,在前述GBR模型验证中已经获得了较高的预测精度,而NH3浓度受通风稀释、排放累积以及管理事件的影响更显著[33],是本研究中更具挑战性和应用价值的预测对象,因此对比试验重点探究了NH3浓度短期预测模型的总体性能。本研究以NH3浓度预测为例,选取单变量GBR、LSTM和GRU作为对比模型,对比结果如表5所示。结果表明,本研究模型相较于GRU和LSTM表现出更好的整体预测效果。本研究模型的R2为0.76,高于GRU和LSTM;本研究模型的RMSE和MAE分别为0.44、0.27 mg/m3,均低于GRU和LSTM。与两种循环神经网络模型相比,本研究模型在NH3浓度短期预测中具有更好的拟合能力和误差控制。与仅使用NH3历史信息的单变量GBR模型相比,本研究模型的R²由0.64提高至0.76,RMSE由0.52 mg/m3降低至0.44 mg/m3,MAE由0.37 mg/m3降低至0.27 mg/m3,整体预测性能更优。这表明仅依赖NH3历史单变量信息难以准确反映鸡舍中NH3浓度的变化规律,而引入多源环境信息后,模型预测性能能够得到明显改善。
为了验证环境参数预测模型在长时序预测任务中的误差累积效应与稳定性,本研究对温度、相对湿度和NH3浓度进行未来24 h递推预测。图5为不同监测点温度、相对湿度和NH3浓度未来24 h的递推预测轨迹及90%预测区间。
从温度预测结果看,4个监测单元的预测曲线都较好延续了历史序列的变化趋势,温度预测值与实测值的R2为0.95。预测起始段与历史末端衔接自然,没有出现明显跳变,说明模型能够较稳定地反映不同位置温度变化的短时延续性和昼夜周期特征。
相对湿度预测值与实测值的R2为0.96,预测结果整体上也较好延续了历史序列的变化趋势,能够较准确地反映次日湿度水平及日变化过程。与温度相比,相对湿度在部分时段波动更明显,说明湿度变化对边界条件和局部扰动更敏感。已有研究表明,相对湿度通常比温度波动更剧烈,预测难度也更高[11],但本研究模型仍能较稳定地反映不同监测单元相对湿度的短期变化。
NH3浓度的预测结果较温度和相对湿度表现出更明显的点位差异。NH3浓度预测值与实测值的R2为0.71,且各监测单元的预测曲线都保持了与近期历史观测相近的变化特征,但不同位置在波动幅度存在明显差别。PMU2和PMU4的预测曲线整体较为平缓,说明这两个点位的NH3浓度短期变化相对稳定,预测不确定性较低。而PMU3和PMU5的预测曲线变化幅度较大,说明这两个位置的NH3浓度变化更复杂,预测不确定性也更高。结合图4的结果可知,NH3浓度的短期变化不仅受自身变化影响,还与温度、相对湿度的变化密切相关[33],不同点位之间的可预测性存在明显差异。
总体来说,递推预测模型能够同时给出不同监测单元温度、相对湿度和NH3浓度未来24 h的变化轨迹及90%预测区间,为判断未来一段时间内环境参数的波动范围提供了量化依据。对于温度和相对湿度,这些结果可为通风调控和阈值调整提供参考。对于NH3浓度,由于其短期波动更复杂、空间差异更明显,预测结果更适合用于有害气体预警和局部风险识别,为鸡舍环境精细化调控提供依据。
针对立体栖架蛋鸡舍环境参数短期变化预测需求,本研究基于舍内多点环境监测数据,构建了温度、相对湿度与NH3浓度的短期预测模型。主要结论如下:
1)基于梯度提升回归(gradient boosting regressor, GBR)模型的温度和相对湿度短期预测模型具有较好的预测精度。温度预测模型的R2、均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)分别为0.96、0.73 ℃和0.50 ℃,相对湿度预测模型的R2、RMSE和MAE分别为0.97、2.94%和1.77%。模型可较好预测立体栖架蛋鸡舍温度和相对湿度未来24 h的变化。
2)温度和相对湿度与NH3浓度的变化均呈负相关性,相关系数分别为−0.26和−0.16。NH3浓度预测模型的R2、RMSE和MAE分别为0.76、0.44 mg/m3和0.27 mg/m3,温湿度信息可为NH3浓度短期预测提供有效补充。
3)3类预测模型对立体栖架蛋鸡舍温度、相对湿度与NH3浓度未来24 h的递推预测,可较好延续历史变化趋势,温度、相对湿度与NH3浓度预测值与真实值的R2分别为0.95、0.96和0.71,为鸡舍环境调控措施及时调整和NH3风险识别提供方法支持。
需要指出的是,本研究数据来源于单栋试验鸡舍,尚不能全面反映不同气候区及不同管理模式下的环境特征。模型在极端天气或通风策略突变情形下的鲁棒性有待进一步验证。未来可在多地区、多类型鸡舍开展对比研究,并将短期预测结果嵌入实际通风控制,实现闭环验证与优化。
总体而言,本研究构建的立体栖架养殖蛋鸡舍环境参数预测模型,为福利化养殖蛋鸡舍环境的精细化评估和预测性通风控制提供了可复现的技术路径,对推动立体栖架模式下鸡舍环境调控向智能化、低碳化方向发展具有重要意义。

参考文献 引证文献
排序方式:
1
孙从佼, 于爱芝, 杨敏, 等. 2024年蛋鸡产业发展情况、未来发展趋势及建议[J]. 中国畜牧杂志, 2025, 61(3): 365-370.
2
JEON H, SHIN H, LEE J, et al. Welfare characteristics of laying hens in aviary and cage systems[J]. Poultry Science, 2025, 104(5): 104987.
3
席磊, 王永芬, 常杰, 等. 散养模式对蛋鸡健康与肉品质的影响[J]. 家畜生态学报, 2015, 36(2): 36-42.
XI Lei, WANG Yongfen, CHANG Jie, et al. Effect of free roost feeding on health and meat quality of laying hens[J]. Journal of Domestic Animal Ecology, 2015, 36(2): 36-42. (in Chinese with English abstract)
4
HARTCHER K M, JONES B. The welfare of layer hens in cage and cage-free housing systems[J]. World’s Poultry Science Journal, 2017, 73(4): 767-782.
5
谢苗苗, 李华龙, 詹凯. 基于多元数据的夏季鸡舍环境质量评价及其对产蛋性能的影响[J]. 农业工程学报, 2024, 40(8): 188-197.
XIE Miaomiao, LI Hualong, ZHAN Kai. Evaluating the environmental quality of layer house in summer based on multivariate data and its impact on production performance[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2024, 40(8): 188-197. (in Chinese with English abstract)
6
KIM D H, LEE Y K, LEE S D, et al. Impact of relative humidity on the laying performance, egg quality, and physiological stress responses of laying hens exposed to high ambient temperature[J]. Journal of Thermal Biology, 2022, 103: 103167.
7
KIM H R, RYU C, LEE S D, et al. Effects of heat stress on the laying performance, egg quality, and physiological response of laying hens[J]. Animals, 2024, 14(7): 1076.
8
ZHOU Y, ZHANG M, LIU Q, et al. The alterations of tracheal microbiota and inflammation caused by different levels of ammonia exposure in broiler chickens[J]. Poultry Science, 2021, 100(2): 685-696.
9
LI D P, TONG Q, SHI Z X, et al. Effects of chronic heat stress and ammonia concentration on blood parameters of laying hens[J]. Poultry Science, 2020, 99(8): 3784-3792.
10
梁超, 尹欢欢, 李保明, 等. 蛋鸡舍热湿环境参数全年逐时动态预测模型[J]. 农业工程学报, 2021, 37(8): 229-235.
LIANG Chao, YIN Huanhuan, LI Baoming, et al. Hourly model for predicting year-round temperature and relative humidity of the environment in laying hen houses[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2021, 37(8): 229-235. (in Chinese with English abstract)
11
JI H Y, TENG G H. Multistep prediction of temperature and humidity in poultry houses based on the GFF-transformer model[J]. Frontiers of Agricultural Science and Engineering, 2025, 12(4): 803-817.
12
XU Y D, TENG G H, ZHOU Z Y. Short-term prediction method for gas concentration in poultry houses under different feeding patterns[J]. Agriculture, 2024, 14(11): 1891.
13
AHMADI BABADI K, KHORASANIZADEH H, AGHAEI A. CFD modeling of air flow, humidity, CO2 and NH3 distributions in a caged laying hen house with tunnel ventilation system[J]. Computers and Electronics in Agriculture, 2022, 193: 106677.
14
BORDIGNON F, PRAVATO M, TROCINO A, et al. Environmental gradients and hen spatial distribution in a cage-free aviary system: Internet of things-based real-time monitoring for proactive management[J]. Animals, 2025, 15(9): 1225.
15
李大鹏, 严格齐, 刘玮, 等. 基于EMD-LSTM-Attention的蛋鸡舍环境温度预测[J]. 农业工程学报, 2026, 42(5): 350-357.
LI Dapeng, YAN Geqi, LIU Wei, et al. Prediction of environmental temperature in laying hen houses using EMD-LSTM-Attention model[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2026, 42(5): 350-357. (in Chinese with English abstract)
16
RATHER I H, KUMAR S, GANDOMI A H. Breaking the data barrier: A review of deep learning techniques for democratizing AI with small datasets[J]. Artificial Intelligence Review, 2024, 57: 226.
17
XIE Y F, TUMMALA S P. Machine learning for sensor analytics: A comprehensive review and benchmark of boosting algorithms in healthcare, environmental, and energy applications[J]. Sensors, 2025, 25(23): 7294.
18
LIU Y, ZHUANG Y R, JI B Y, et al. Prediction of laying hen house odor concentrations using machine learning models based on small sample data[J]. Computers and Electronics in Agriculture, 2022, 195: 106849.
19
PENG C, WANG Z, LI J, et al. Prediction of ammonia concentration in a pig house based on machine learning models and environmental parameters[J]. Animals, 2022, 13(1): 165.
20
WIENS M, VERONE-BOYLE A, HENSCHEID N, et al. A tutorial and use case example of the eXtreme Gradient Boosting (XGBoost) artificial intelligence algorithm for drug development applications[J]. Clinical and Translational Science, 2025, 18(3): e70172.
21
SIERRA-PORTA D. Assessing the impact of missing data on water quality index estimation: a machine learning approach[J]. Discover Water, 2024, 4: 11.
22
LIU Y, NI J Q, WANG G, et al. Concentrations and emissions of ammonia from different laying hen production systems of conventional cage, aviary and natural mating colony cage in North China Plain[J]. Applied Sciences, 2020, 10(19): 6820.
23
MOSER J, KOHLER S, HENTGEN J, et al. Assessment of ammonia concentrations and climatic conditions in calf housing using stationary and mobile sensors[J]. Animals, 2024, 14(13): 2001.
24
WANG K, GUO R, ZHOU Y H, et al. Detection of NH3 in poultry housing based on tunable diode laser absorption spectroscopy combined with a micro circular absorption cell[J]. Frontiers in Physics, 2022, 10: 1051719.
25
NATEKIN A, KNOLL A. Gradient boosting machines, a tutorial[J]. Frontiers in Neurorobotics, 2013, 7: 21.
26
FRIEDMAN J H. Greedy function approximation: A gradient boosting machine[J]. Annals of Statistics, 2001, 29(5): 1189-1232.
27
LALAPURA V S, AMUDHA J, SATHEESH H S. Recurrent neural networks for edge intelligence: A survey[J]. ACM Computing Surveys, 2021, 54(4): 1-38.
28
CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: Association for Computational Linguistics, 2014: 1724-1734.
29
TAIEB S B, BONTEMPI G, ATIYA A F, et al. A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition[J]. Expert Systems with Applications, 2012, 39(8): 7067-7083.
30
LI L H, LI M, YU Y, et al. Modeling and regulation of dynamic temperature for layer houses under combined positive- and negative-pressure ventilation[J]. Animals, 2024, 14(21): 3055.
31
CHEN Y J, DENG S Z, WANG Y, et al. Thermal stability of multi-tier layer hen housing with all-year sidewall inlet ventilation system[J]. Poultry Science, 2025, 104(11): 105887.
32
BEGGS C B, AVITAL E J. A psychrometric model to assess the biological decay of the SARS-CoV-2 virus in aerosols[J]. PeerJ, 2021, 9: e11024.
33
SWELUM A A, EL-SAADONY M T, ABD EL-HACK M E, et al. Ammonia emissions in poultry houses and microbial nitrification as a promising reduction strategy[J]. Science of the Total Environment, 2021, 781: 146978.
34
BIST R B, BIST D B, REGMI D, et al. Ammonia emissions, impacts, and mitigation strategies for poultry production: A critical review[J]. Journal of Environmental Management, 2023, 328: 116919.
35
沈丰菊, 刘雪兰, 张克强. 密闭蛋鸡舍内NH3浓度变化规律及其影响因子分析[J]. 农业资源与环境学报, 2019, 36(2): 221-226.
SHEN Fengju, LIU Xuelan, ZHANG Keqiang. Variation of ammonia concentration and influence factors analysis in layer house[J]. Journal of Agricultural Resources and Environment, 2019, 36(2): 221-226. (in Chinese with English abstract)
36
杨亮, 刘春红, 郭昱辰, 等. 基于EMD-LSTM的猪舍氨气浓度预测研究[J]. 农业机械学报, 2019, 50(增刊1): 353-360.
YANG Liang, LIU Chunhong, GUO Yuchen, et al. Prediction of ammonia concentration in fattening piggery based on EMD-LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(Supp.1): 353-360. (in Chinese with English abstract)
37
张蕾, 冯婧, 韩静, 等. 冬季地面平养蛋鸡舍温湿度对氨气浓度的影响[J]. 畜禽业, 2019, 30(11): 1-5.
2026年第42卷第12期
PDF下载
204
86
引用本文
BibTeX
文章信息
doi: 10.11975/j.issn.1002-6819.202601234
  • 接收时间:2026-01-27
  • 首发时间:2026-08-20
  • 出版时间:2026-06-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-01-27
  • 修回日期:2026-05-26
基金
作者信息
    1中国农业大学水利与智能工程学院,北京 100083
    2农业农村部设施农业工程重点实验室,北京 100083

通讯作者:

刘羽,副教授,硕士生导师,研究方向为设施畜禽养殖过程控制与环境。Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/nygcxb/CN/10.11975/j.issn.1002-6819.202601234
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏