首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1322566805118366675, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322566763112415546, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2024.12.596, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1735920000000, receivedDateStr=2025-01-04, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793254098443, onlineDateStr=2026-10-29, pubDate=1768406400000, pubDateStr=2026-01-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793254098443, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793254098443, creator=13701087609, updateTime=1793254098443, updator=13701087609, issue=Issue{id=1322566763112415546, tenantId=1146029695717560320, journalId=1281212831689347082, year='2026', volume='46', issue='1', pageStart='1', pageEnd='138', issueExtLink='null', onlineDate='null', pubDate='1768406400000', pubDateStr='2026-01-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793254088427, creator='13701087609', updateTime=1793254088427, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=68, endPage=77, ext={EN=ArticleExt(id=1322566805298721748, articleId=1322566805118366675, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=Landslide Susceptibility Distribution in Anhui Province Based on Machine Learning Model and Feature Selection, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

This paper uses historical landslide and hydrogeological data from Anhui province as the original dataset, employing five typical machine learning models and selects nine environmental disaster-inducing factors as initial input variables. To explore the impact of different machine learning input variable selection combinations on the performance of various models, multiple factor selection methods and several evaluation metrics are used to examine the prediction accuracy of each algorithm model under different selection combinations for landslide susceptibility. The evaluation results show that the combination of the full selection set and the lightweight gradient boosting machine (LightGBM). model yields the best performance. Therefore, this combination is chosen for the landslide susceptibility mapping in the study area. Moreover, the study suggests that factor selection for machine learning inputs does not necessarily improve model performance in landslide susceptibility studies of the research area. Additionally, ensemble models outperform individual estimator models, and LightGBM, using a leaf-node-based decision tree algorithm, shows improved performance compared to other ensemble algorithms.

, authors=Zikang LU1, Hongxin CHEN1, *, Shijin FENG1, Yong ZHAO1, Guodong SHEN2, Xiuhe CHEN2, authorsList=Zikang LU, Hongxin CHEN, Shijin FENG, Yong ZHAO, Guodong SHEN, Xiuhe CHEN, authorCompany=null, correspAuthors=Hongxin CHEN, authorNote=null, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., 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=1322566808255706088, articleId=1322566805118366675, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=基于机器学习模型与特征筛选的安徽省滑坡灾害易发性分布研究, columnId=1281933709121138897, journalTitle=大地测量与地球动力学, columnName=地球动力学, runingTitle=null, highlight=null, articleAbstract=

以安徽省历史滑坡与水文地质条件为原始数据，利用5种典型机器学习模型，选取9种环境致灾因子作为初始输入变量，针对机器学习输入变量筛选组合对不同模型的性能影响问题，采用多种因子筛选方法及数种评价指标，考察各筛选组合下每种算法模型对滑坡易发性的预测精度。评价结果显示，全选组与轻量梯度提升机(LightGBM)模型的组合具有最优的性能；在研究区的滑坡易发性研究中，对机器学习输入因子的筛选并不一定对模型的性能提升产生正面影响；集成模型比单评估器模型性能更优，且LightGBM由于采用了基于叶子节点的决策树算法，相较于其他集成算法模型性能有一定的提升。

, authors=陆子康1, 陈宏信1, *, 冯世进1, 赵勇1, 沈国栋2, 陈修和2, authorsList=陆子康, 陈宏信, 冯世进, 赵勇, 沈国栋, 陈修和, authorCompany=null, correspAuthors=陈宏信, authorNote=

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

, correspAuthorsNote=
陈宏信, 教授, 主要研究方向为工程地质与环境灾害, E-mail:
, copyrightStatement=版权所有，未经授权，不得转载。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=Phw05fq7Pn0CaNK+WUOMfQ==, magXml=iJMAfiOGF2G0A9zEtENHjw==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=XVBJF1d1oiIE3C7GBOk1bg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Jw6cWRgwiL6AnSxf7vuhHw==, mapNumber=null, fund=null)}, authors=[Author(id=1322566809073595376, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2330861@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566809354613746, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809073595376, language=EN, stringName=Zikang LU, firstName=Zikang, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566809421722611, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809073595376, language=CN, stringName=陆子康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio={"content":"

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

"}, bioImg=null, bioContent=

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566809497220085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenhongxin@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322566809778238455, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809497220085, language=EN, stringName=Hongxin CHEN, firstName=Hongxin, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566809849541624, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809497220085, language=CN, stringName=陈宏信, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566809916650491, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, 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=1322566810201863165, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809916650491, language=EN, stringName=Shijin FENG, firstName=Shijin, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810277360638, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809916650491, language=CN, stringName=冯世进, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566810344469504, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, 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=1322566810432548865, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810344469504, language=EN, stringName=Yong ZHAO, firstName=Yong, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810499657730, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810344469504, language=CN, stringName=赵勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566810558377988, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=4, 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=1322566810625486854, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810558377988, language=EN, stringName=Guodong SHEN, firstName=Guodong, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810692595719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810558377988, language=CN, stringName=沈国栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808977126380, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808985514989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China), AuthorCompanyExt(id=1322566808993903598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088)])]), Author(id=1322566810759704585, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=5, 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=1322566810835202059, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810759704585, language=EN, stringName=Xiuhe CHEN, firstName=Xiuhe, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810893922316, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810759704585, language=CN, stringName=陈修和, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808977126380, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808985514989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China), AuthorCompanyExt(id=1322566808993903598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088)])])], keywords=[Keyword(id=1322566810977808397, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, orderNo=1, keyword=landslide), Keyword(id=1322566811049111566, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1322566811116220431, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, orderNo=3, keyword=feature selection), Keyword(id=1322566811179134992, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, orderNo=4, keyword=susceptibility), Keyword(id=1322566811246243857, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, orderNo=5, keyword=ensemble models), Keyword(id=1322566811325935634, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, orderNo=1, keyword=滑坡), Keyword(id=1322566811388850195, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1322566811443376148, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, orderNo=3, keyword=特征筛选), Keyword(id=1322566811514679317, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, orderNo=4, keyword=易发性), Keyword(id=1322566811581788182, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, orderNo=5, keyword=集成模型)], refs=[Reference(id=1322566814014484530, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=191, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=Huang F M, Cao Z S, Guo J F, journalName=Catena, refType=null, unstructuredReference= Huang F M , Cao Z S , Guo J F , et al. Comparisons of Heuristic, General Statistical and Machine Learning Models for Landslide Susceptibility Prediction and Mapping[J]. Catena, 2020, 191, articleTitle=Comparisons of Heuristic, General Statistical and Machine Learning Models for Landslide Susceptibility Prediction and Mapping, refAbstract=null), Reference(id=1322566814085787699, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=133, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=Niu H T, Shao S J, Gao J Q, journalName=Physics and Chemistry of the Earth, Parts A/B/C, refType=null, unstructuredReference= Niu H T , Shao S J , Gao J Q , et al. Research on GIS-Based Information Value Model for Landslide Geological Hazards Prediction in Soil-Rock Contact Zone in Southern Shaanxi[J]. Physics and Chemistry of the Earth, Parts A/B/C, 2024, 133, articleTitle=Research on GIS-Based Information Value Model for Landslide Geological Hazards Prediction in Soil-Rock Contact Zone in Southern Shaanxi, refAbstract=null), Reference(id=1322566814173868084, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=6, pageStart=1365, pageEnd=1370, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=邵健, 王霄, 昌文峰, journalName=计算机与数字工程, refType=null, unstructuredReference=邵健, 王霄, 昌文峰, 等. 基于CatBoost算法的滑坡敏感性模型: 以毕节市大方县为例[J]. 计算机与数字工程, 2022, 50 (6): 1365- 1370, articleTitle=基于CatBoost算法的滑坡敏感性模型: 以毕节市大方县为例, refAbstract=null), Reference(id=1322566814236782645, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=6, pageStart=1365, pageEnd=1370, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=Shao Jian, Wang Xiao, Chang Wenfeng, journalName=null, refType=null, unstructuredReference= Shao Jian , Wang Xiao , Chang Wenfeng , et al. Landslide Sensitivity Model Based on CatBoost Algorithm: Taking Dafang County of Bijie City as an Example[J]. Computerand Digital Engineering, 2022, 50 (6): 1365- 1370, articleTitle=null, refAbstract=null), Reference(id=1322566814316474422, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=679, pageEnd=684, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=王志彪, 赵丽华, journalName=大地测量与地球动力学, refType=null, unstructuredReference=王志彪, 赵丽华. 遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形[J]. 大地测量与地球动力学, 2023, 43 (7): 679- 684, articleTitle=遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形, refAbstract=null), Reference(id=1322566814379388983, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=679, pageEnd=684, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=Wang Zhibiao, Zhao Lihua, journalName=null, refType=null, unstructuredReference= Wang Zhibiao , Zhao Lihua . Prediction of Loess Landslides Deformation Using Elman Neural Network Model Based on Genetic Algorithm and Particle Swarm Optimization[J]. Journal of Geodesy and Geodynamics, 2023, 43 (7): 679- 684, articleTitle=null, refAbstract=null), Reference(id=1322566814446497848, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2023, volume=413, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=Zou F, Che E Z, Long M Q, journalName=Journal of Cleaner Production, refType=null, unstructuredReference= Zou F , Che E Z , Long M Q . Quantitative Assessment of Geological Hazard Risk with Different Hazard Indexes in Mountainous Areas[J]. Journal of Cleaner Production, 2023, 413, articleTitle=Quantitative Assessment of Geological Hazard Risk with Different Hazard Indexes in Mountainous Areas, refAbstract=null), Reference(id=1322566814521995321, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2021, volume=204, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=Zou Q, Jiang H, Cui P, journalName=Catena, refType=null, unstructuredReference= Zou Q , Jiang H , Cui P , et al. A New Approach to Assess Landslide Susceptibility Based on Slope Failure Mechanisms[J]. Catena, 2021, 204, articleTitle=A New Approach to Assess Landslide Susceptibility Based on Slope Failure Mechanisms, refAbstract=null), Reference(id=1322566814597492794, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2021, volume=379, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=Sun D L, Shi S X, Wen H J, journalName=Geomorphology, refType=null, unstructuredReference= Sun D L , Shi S X , Wen H J , et al. A Hybrid Optimization Method of Factor Screening Predicated on GeoDetector and Random Forest for Landslide Susceptibility Mapping[J]. Geomorphology, 2021, 379, articleTitle=A Hybrid Optimization Method of Factor Screening Predicated on GeoDetector and Random Forest for Landslide Susceptibility Mapping, refAbstract=null), Reference(id=1322566814677184571, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=1, pageStart=93, pageEnd=104, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=邓佳良, 黄黄, 王耀, journalName=中国地质调查, refType=null, unstructuredReference=邓佳良, 黄黄, 王耀, 等. 安徽省宁国市山核桃种植区典型滑坡机制与稳定性分析: 以石岭村滑坡为例[J]. 中国地质调查, 2024, 11 (1): 93- 104, articleTitle=安徽省宁国市山核桃种植区典型滑坡机制与稳定性分析: 以石岭村滑坡为例, refAbstract=null), Reference(id=1322566814786236476, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=1, pageStart=93, pageEnd=104, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=Deng Jialiang, Huang Huang, Wang Yao, journalName=null, refType=null, unstructuredReference= Deng Jialiang , Huang Huang , Wang Yao , et al. Mechanism and Stability Analysis of Typical Landslide in Pecan Planting Area of Ningguo City in Anhui Province: A Case Study of Shilingcun Landslide[J]. Geological Survey of China, 2024, 11 (1): 93- 104, articleTitle=null, refAbstract=null), Reference(id=1322566814874316861, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=1, pageStart=156, pageEnd=167, url=null, language=null, rfNumber=9, rfOrder=11, authorNames=黄发明, 殷坤龙, 蒋水华, journalName=岩石力学与工程学报, refType=null, unstructuredReference=黄发明, 殷坤龙, 蒋水华, 等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报, 2018, 37 (1): 156- 167, articleTitle=基于聚类分析和支持向量机的滑坡易发性评价, refAbstract=null), Reference(id=1322566814949814334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=1, pageStart=156, pageEnd=167, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=Huang Faming, Yin Kunlong, Jiang Shuihua, journalName=null, refType=null, unstructuredReference= Huang Faming , Yin Kunlong , Jiang Shuihua , et al. Landslide Susceptibility Assessment Based on Clustering Analysis and Support Vector Machine[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37 (1): 156- 167, articleTitle=null, refAbstract=null), Reference(id=1322566815025311807, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2012, volume=179, issue=null, pageStart=116, pageEnd=125, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=Das I, Stein A, Kerle N, journalName=Geomorphology, refType=null, unstructuredReference= Das I , Stein A , Kerle N , et al. Landslide Susceptibility Mapping along Road Corridors in the Indian Himalayas Using Bayesian Logistic Regression Models[J]. Geomorphology, 2012, 179, 116- 125, articleTitle=Landslide Susceptibility Mapping along Road Corridors in the Indian Himalayas Using Bayesian Logistic Regression Models, refAbstract=null), Reference(id=1322566815109197888, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=17, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=Rabby Y W, Ishtiaque A, Rahman M S, journalName=Remote Sensing, refType=null, unstructuredReference= Rabby Y W , Ishtiaque A , Rahman M S . Evaluating the Effects of Digital Elevation Models in Landslide Susceptibility Mapping in Rangamati District, Bangladesh[J]. Remote Sensing, 2020, 12 (17), articleTitle=Evaluating the Effects of Digital Elevation Models in Landslide Susceptibility Mapping in Rangamati District, Bangladesh, refAbstract=null), Reference(id=1322566815180501057, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2017, volume=14, issue=2, pageStart=249, pageEnd=268, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=Du G L, Zhang Y S, Iqbal J, journalName=Journal of Mountain Science, refType=null, unstructuredReference= Du G L , Zhang Y S , Iqbal J , et al. Landslide Susceptibility Mapping Using an Integrated Model of Information Value Method and Logistic Regression in the Bailongjiang Watershed, Gansu Province, China[J]. Journal of Mountain Science, 2017, 14 (2): 249- 268, articleTitle=Landslide Susceptibility Mapping Using an Integrated Model of Information Value Method and Logistic Regression in the Bailongjiang Watershed, Gansu Province, China, refAbstract=null), Reference(id=1322566815243415618, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=2, pageStart=187, pageEnd=192, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=于宪煜, 熊十力, journalName=大地测量与地球动力学, refType=null, unstructuredReference=于宪煜, 熊十力. 基于空间多尺度分析的滑坡易发性评价: 以三峡库区秭归、巴东段为例[J]. 大地测量与地球动力学, 2020, 40 (2): 187- 192, articleTitle=基于空间多尺度分析的滑坡易发性评价: 以三峡库区秭归、巴东段为例, refAbstract=null), Reference(id=1322566815310524483, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=2, pageStart=187, pageEnd=192, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=Yu Xianyu, Xiong Shili, journalName=null, refType=null, unstructuredReference= Yu Xianyu , Xiong Shili . Landslide Susceptibility Assessment Based on Spatial Multi-Scale Analysis: A Case Study of Zigui to Badong in the Three Gorges Reservoir Area[J]. Journal of Geodesy and Geodynamics, 2020, 40 (2): 187- 192, articleTitle=null, refAbstract=null), Reference(id=1322566815394410564, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=17, issue=18, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=Djukem W D L, Braun A, Wouatong A S L, journalName=International Journal of Environmental Research and Public Health, refType=null, unstructuredReference= Djukem W D L , Braun A , Wouatong A S L , et al. Effect of Soil Geomechanical Properties and Geo-Environmental Factors on Landslide Predisposition at Mount Oku, Cameroon[J]. International Journal of Environmental Research and Public Health, 2020, 17 (18), articleTitle=Effect of Soil Geomechanical Properties and Geo-Environmental Factors on Landslide Predisposition at Mount Oku, Cameroon, refAbstract=null), Reference(id=1322566815461519429, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2014, volume=204, issue=null, pageStart=287, pageEnd=301, url=null, language=null, rfNumber=15, rfOrder=19, authorNames=Peng L, Niu R Q, Huang B, journalName=Geomorphology, refType=null, unstructuredReference= Peng L , Niu R Q , Huang B , et al. Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines: A Case of the Three Gorges Area, China[J]. Geomorphology, 2014, 204, 287- 301, articleTitle=Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines: A Case of the Three Gorges Area, China, refAbstract=null), Reference(id=1322566815532822598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=12, pageStart=1211, pageEnd=1219, url=null, language=null, rfNumber=16, rfOrder=20, authorNames=瞿伟, 李昕, 李久元, journalName=大地测量与地球动力学, refType=null, unstructuredReference=瞿伟, 李昕, 李久元, 等. 一种改进自适应步长人工蜂群优化随机森林的滑坡风险性评价方法[J]. 大地测量与地球动力学, 2024, 44 (12): 1211- 1219, articleTitle=一种改进自适应步长人工蜂群优化随机森林的滑坡风险性评价方法, refAbstract=null), Reference(id=1322566815608320071, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=12, pageStart=1211, pageEnd=1219, url=null, language=null, rfNumber=16, rfOrder=21, authorNames=Qu Wei, Li Xin, Li Jiuyuan, journalName=null, refType=null, unstructuredReference= Qu Wei , Li Xin , Li Jiuyuan , et al. A Landslide Risk Assessment Method with Improved Adaptive Step Size Artificial Bee Colony Optimization Random Forest[J]. Journal of Geodesy and Geodynamics, 2024, 44 (12): 1211- 1219, articleTitle=null, refAbstract=null), Reference(id=1322566815667040328, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=22, authorNames=Andrews-Todd J, Steinberg J, Flor M, journalName=Journal of Intelligence, refType=null, unstructuredReference= Andrews-Todd J , Steinberg J , Flor M , et al. Exploring Automated Classification Approaches to Advance the Assessment of Collaborative Problem Solving Skills[J]. Journal of Intelligence, 2022, 10 (3), articleTitle=Exploring Automated Classification Approaches to Advance the Assessment of Collaborative Problem Solving Skills, refAbstract=null), Reference(id=1322566815738343497, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2024, volume=2, issue=2, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=18, rfOrder=23, authorNames=Bai Z Q, Jiang Y S, Jing C Z, journalName=Journal of Intelligent Construction, refType=null, unstructuredReference= Bai Z Q , Jiang Y S , Jing C Z , et al. Clayshock Mechanism and Application to Shield Tunneling through Existing Tunnels: Settlement Prediction Using Artificial Intelligence[J]. Journal of Intelligent Construction, 2024, 2 (2): 1- 22, articleTitle=Clayshock Mechanism and Application to Shield Tunneling through Existing Tunnels: Settlement Prediction Using Artificial Intelligence, refAbstract=null), Reference(id=1322566815797063754, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=6, pageStart=131, pageEnd=144, url=null, language=null, rfNumber=19, rfOrder=24, authorNames=郑迎凯, 陈建国, 王成彬, journalName=地质科技通报, refType=null, unstructuredReference=郑迎凯, 陈建国, 王成彬, 等. 确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用[J]. 地质科技通报, 2020, 39 (6): 131- 144, articleTitle=确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用, refAbstract=null), Reference(id=1322566815855784011, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=6, pageStart=131, pageEnd=144, url=null, language=null, rfNumber=19, rfOrder=25, authorNames=Zheng Yingkai, Chen Jianguo, Wang Chengbin, journalName=null, refType=null, unstructuredReference= Zheng Yingkai , Chen Jianguo , Wang Chengbin , et al. Application of Certainty Factor and Random Forests Model in Landslide Susceptibility Evaluation in Mangshi City, Yunnan Province[J]. Bulletin of Geological Science and Technology, 2020, 39 (6): 131- 144, articleTitle=null, refAbstract=null), Reference(id=1322566815918698572, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=3, pageStart=1937, pageEnd=1967, url=null, language=null, rfNumber=20, rfOrder=26, authorNames=Bentéjac C, Csörgö A, Martínez-Muñoz G, journalName=Artificial Intelligence Review, refType=null, unstructuredReference= Bentéjac C , Csörgö A , Martínez-Muñoz G . A Comparative Analysis of Gradient Boosting Algorithms[J]. Artificial Intelligence Review, 2021, 54 (3): 1937- 1967, articleTitle=A Comparative Analysis of Gradient Boosting Algorithms, refAbstract=null), Reference(id=1322566816006778957, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2023, volume=1, issue=1, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=21, rfOrder=27, authorNames=Feng Y, Zhang X L, Feng S J, journalName=Journal of Intelligent Construction, refType=null, unstructuredReference= Feng Y , Zhang X L , Feng S J , et al. Improved SOLOv2 Detection Method for Shield Tunnel Lining Water Leakages[J]. Journal of Intelligent Construction, 2023, 1 (1): 1- 15, articleTitle=Improved SOLOv2 Detection Method for Shield Tunnel Lining Water Leakages, refAbstract=null), Reference(id=1322566816082276430, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, doi=null, pmid=null, pmcid=null, year=2017, volume=8, issue=3, pageStart=1, pageEnd=19, url=null, language=null, rfNumber=22, rfOrder=28, authorNames=Zhang S C, Li X L, Zong M, journalName=ACM Transactions on Intelligent Systems and Technology, refType=null, unstructuredReference= Zhang S C , Li X L , Zong M , et al. Learning k for KNN Classification[J]. ACM Transactions on Intelligent Systems and Technology, 2017, 8 (3): 1- 19, articleTitle=Learning k for KNN Classification, refAbstract=null)], funds=[Fund(id=1322566813926404145, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, awardId=2022CSJGG1202, language=CN, fundingSource=长三角科技创新共同体联合攻关项目(2022CSJGG1202), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)]), AuthorCompany(id=1322566808977126380, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808985514989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China), AuthorCompanyExt(id=1322566808993903598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088)])], figs=[ArticleFig(id=1322566811703422999, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 1, caption=Distribution of historical and non-historical landslide points, figureFileSmall=Ve5823Kf6vmL8/t+EMTb/A==, figureFileBig=XVBJF1d1oiIE3C7GBOk1bg==, tableContent=null), ArticleFig(id=1322566811766337560, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图1, caption=历史滑坡点位和非历史滑坡点位分布, figureFileSmall=Ve5823Kf6vmL8/t+EMTb/A==, figureFileBig=XVBJF1d1oiIE3C7GBOk1bg==, tableContent=null), ArticleFig(id=1322566811950886937, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 2, caption=Spatial distribution of the nine environmental disaster triggering factors in the study area, figureFileSmall=BzmJ5NhASWayPstijxS4/Q==, figureFileBig=Cs4d38W+szCuirxVuJG8tA==, tableContent=null), ArticleFig(id=1322566812030578714, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图2, caption=研究区域9种环境致灾因子空间分布, figureFileSmall=BzmJ5NhASWayPstijxS4/Q==, figureFileBig=Cs4d38W+szCuirxVuJG8tA==, tableContent=null), ArticleFig(id=1322566812097687579, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 3, caption=Density distribution of the nine environmental disaster triggering factors for historical and non-historical landslide points in the study area, figureFileSmall=6daPQutM/nFl5jlhapHmlA==, figureFileBig=Pq+xLcdMriRX2pYlx/6kzw==, tableContent=null), ArticleFig(id=1322566812194156572, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图3, caption=研究区历史滑坡点与非历史滑坡点9种环境致灾因子数据密度分布, figureFileSmall=6daPQutM/nFl5jlhapHmlA==, figureFileBig=Pq+xLcdMriRX2pYlx/6kzw==, tableContent=null), ArticleFig(id=1322566812278042653, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 4, caption=Heatmap of the Spearman correlation coefficients of original input variables, figureFileSmall=mlI9pfonLcK9vpDS3RfaNw==, figureFileBig=fpZexvcwQRaBt+qtXlLQRA==, tableContent=null), ArticleFig(id=1322566812370317342, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图4, caption=原始输入变量斯皮尔曼相关系数热力图, figureFileSmall=mlI9pfonLcK9vpDS3RfaNw==, figureFileBig=fpZexvcwQRaBt+qtXlLQRA==, tableContent=null), ArticleFig(id=1322566812458397727, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 5, caption=Schematic view of each machine learning model, figureFileSmall=1ILRuvZXSaEBoRyoxpFmsw==, figureFileBig=cmuGMc/2xvVcrQd5Y0Vt8w==, tableContent=null), ArticleFig(id=1322566812546478112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图5, caption=各机器学习模型算法示意图, figureFileSmall=1ILRuvZXSaEBoRyoxpFmsw==, figureFileBig=cmuGMc/2xvVcrQd5Y0Vt8w==, tableContent=null), ArticleFig(id=1322566812617781281, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 6, caption=Training time of models under different conditions, figureFileSmall=JJ15bMsWa+LoD+FvB33dlQ==, figureFileBig=IU+3qXGlzVQKYFb+QndPjA==, tableContent=null), ArticleFig(id=1322566812697473058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图6, caption=各工况下模型的训练时长, figureFileSmall=JJ15bMsWa+LoD+FvB33dlQ==, figureFileBig=IU+3qXGlzVQKYFb+QndPjA==, tableContent=null), ArticleFig(id=1322566812764581923, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 7, caption=Receiver operating characteristic (ROC) curves of models under different conditions, figureFileSmall=eeeEPJ+KRTWgRAlmB5zjhw==, figureFileBig=itkJEeiamfrg62nNfl6BIA==, tableContent=null), ArticleFig(id=1322566812827496484, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图7, caption=各工况的受试者工作特征曲线, figureFileSmall=eeeEPJ+KRTWgRAlmB5zjhw==, figureFileBig=itkJEeiamfrg62nNfl6BIA==, tableContent=null), ArticleFig(id=1322566812907188261, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 8, caption=Results of the three evaluation indexes under different conditions, figureFileSmall=d1WGGtrNDvWqn5Fv0EISdg==, figureFileBig=u1FrICvctSefLv+Ogh+IkA==, tableContent=null), ArticleFig(id=1322566812982685734, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图8, caption=各工况的3种评价指标结果, figureFileSmall=d1WGGtrNDvWqn5Fv0EISdg==, figureFileBig=u1FrICvctSefLv+Ogh+IkA==, tableContent=null), ArticleFig(id=1322566813074960423, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Fig. 9, caption=Susceptibility distribution of landslide disasters in Anhui province, figureFileSmall=652ZyheE4D+yZFew4pJ7iQ==, figureFileBig=Z1zK6dpXSgzFA6WaUXYu0A==, tableContent=null), ArticleFig(id=1322566813146263592, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=图9, caption=安徽省滑坡灾害易发性分布, figureFileSmall=652ZyheE4D+yZFew4pJ7iQ==, figureFileBig=Z1zK6dpXSgzFA6WaUXYu0A==, tableContent=null), ArticleFig(id=1322566813217566761, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Tab. 1, caption=

Data sources and spatial distribution map generation methods for the nine environmental disaster triggering factors

, figureFileSmall=null, figureFileBig=null, tableContent=
选取类型环境致灾因子数据来源年份空间分布图生成方法
地形地貌 高程/m国家地理空间数据云数字高程模型2023基于数字高程模型（DEM），利用ArcGIS软件生成
坡度/(°)国家地理空间数据云数字高程模型2023基于DEM，利用ArcGIS软件中Slope工具生成
地面粗糙度国家地理空间数据云数字高程模型2023基于DEM，利用栅格计算器，计算公式为：SDS=1/cosɑ ，式中，ɑ为栅格单元坡度值
地质条件 地层岩性全国地理信息资源目录 服务系统2022基于tiff栅格数据坐标变换生成
土壤重度/kN·m-3中国科学院资源环境 科学与数据中心2022基于tiff栅格数据坐标变换生成
水文 环境月均降雨量/mm中国气象局 国家气象信息中心1991— 2021基于安徽省内78个气象站所处坐标和每年月降雨数据，利用克里金法生成
归一化植被指数国家地理空间数据云Landsat8 OLI卫星数据2023基于卫星数据，利用栅格计算器计算，计算公式为NDVI=PN-PRPN+PR（PN代表Landsat8卫星近红波段数据，PR代表红波段数据）
距水系距离/m国家地理遥感生态网2022结合湖泊江河shp数据，利用欧氏距离计算
人类活动距路网距离/m国家地理遥感生态网2022结合铁路公路shp数据，利用欧氏距离计算
), ArticleFig(id=1322566813318230058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=表1, caption=

9种环境致灾因子数据来源和空间分布图生成方法

, figureFileSmall=null, figureFileBig=null, tableContent=
选取类型环境致灾因子数据来源年份空间分布图生成方法
地形地貌 高程/m国家地理空间数据云数字高程模型2023基于数字高程模型（DEM），利用ArcGIS软件生成
坡度/(°)国家地理空间数据云数字高程模型2023基于DEM，利用ArcGIS软件中Slope工具生成
地面粗糙度国家地理空间数据云数字高程模型2023基于DEM，利用栅格计算器，计算公式为：SDS=1/cosɑ ，式中，ɑ为栅格单元坡度值
地质条件 地层岩性全国地理信息资源目录 服务系统2022基于tiff栅格数据坐标变换生成
土壤重度/kN·m-3中国科学院资源环境 科学与数据中心2022基于tiff栅格数据坐标变换生成
水文 环境月均降雨量/mm中国气象局 国家气象信息中心1991— 2021基于安徽省内78个气象站所处坐标和每年月降雨数据，利用克里金法生成
归一化植被指数国家地理空间数据云Landsat8 OLI卫星数据2023基于卫星数据，利用栅格计算器计算，计算公式为NDVI=PN-PRPN+PR（PN代表Landsat8卫星近红波段数据，PR代表红波段数据）
距水系距离/m国家地理遥感生态网2022结合湖泊江河shp数据，利用欧氏距离计算
人类活动距路网距离/m国家地理遥感生态网2022结合铁路公路shp数据，利用欧氏距离计算
), ArticleFig(id=1322566813423087659, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Tab. 2, caption=

Multicollinearity analysis data for each environmental disaster triggering factor

, figureFileSmall=null, figureFileBig=null, tableContent=
类型因子VIFTOL
地形地貌 高程0.5201.922
坡度0.5711.751
地面粗糙度0.4642.154
地质条件地层岩性0.8351.198
土壤重度0.7721.295
水文环境 月均降雨量0.6611.513
归一化 植被指数0.6151.625
距水系距离0.6731.486
人类活动距路网距离0.5471.829
), ArticleFig(id=1322566813502779436, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=表2, caption=

各环境致灾因子的共线性分析数据

, figureFileSmall=null, figureFileBig=null, tableContent=
类型因子VIFTOL
地形地貌 高程0.5201.922
坡度0.5711.751
地面粗糙度0.4642.154
地质条件地层岩性0.8351.198
土壤重度0.7721.295
水文环境 月均降雨量0.6611.513
归一化 植被指数0.6151.625
距水系距离0.6731.486
人类活动距路网距离0.5471.829
), ArticleFig(id=1322566813586665517, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Tab. 3, caption=

Detailed setting of hyperparameters and optimal results of each machine learning model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数设置最优结果
SVM C [0.1, 1, 10]0.1
kernel type[′linear′, ′rbf′, ′poly′]rbf
epsilon[0.1, 0.2, 0.3]0.1
KNN n_neighbors[1, 3, 5, 7, 9]7
p [1, 2]2
weights[′uniform′, ′distance′]distance
RFmax_depth[4, 5, 6]6
min_samples_leaf[1, 2, 3]2
n_estimators[50, 100, 150]150
XG-Boost gamma[0, 0.1, 0.2]0
learning rate[0.05, 0.1, 0.3]0.1
max_depth[3, 5, 7]3
Light-GBMmin_data_in_leaf[10, 30, 50, 70, 90]30
num_leaves[32, 64, 128]32
learning rate[0.05, 0.1]0.1
), ArticleFig(id=1322566813657968686, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=表3, caption=

各机器学习模型的超参数详细设置与最优结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数设置最优结果
SVM C [0.1, 1, 10]0.1
kernel type[′linear′, ′rbf′, ′poly′]rbf
epsilon[0.1, 0.2, 0.3]0.1
KNN n_neighbors[1, 3, 5, 7, 9]7
p [1, 2]2
weights[′uniform′, ′distance′]distance
RFmax_depth[4, 5, 6]6
min_samples_leaf[1, 2, 3]2
n_estimators[50, 100, 150]150
XG-Boost gamma[0, 0.1, 0.2]0
learning rate[0.05, 0.1, 0.3]0.1
max_depth[3, 5, 7]3
Light-GBMmin_data_in_leaf[10, 30, 50, 70, 90]30
num_leaves[32, 64, 128]32
learning rate[0.05, 0.1]0.1
), ArticleFig(id=1322566813741854767, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=EN, label=Tab. 4, caption=

Statistical analysis of historical landslides at different susceptibility levels

, figureFileSmall=null, figureFileBig=null, tableContent=
风险性等级面积比/%历史滑坡点个数点数占比/%
低易发区20725.95
较低易发区201018.35
中易发区2013210.91
较高易发区2031726.20
高易发区2058848.59
总计1001 210100
), ArticleFig(id=1322566813829935152, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, language=CN, label=表4, caption=

不同风险易发等级的历史滑坡统计

, figureFileSmall=null, figureFileBig=null, tableContent=
风险性等级面积比/%历史滑坡点个数点数占比/%
低易发区20725.95
较低易发区201018.35
中易发区2013210.91
较高易发区2031726.20
高易发区2058848.59
总计1001 210100
)], attaches=null, journal=Journal(id=1281211523964080133, delFlag=0, nameCn=大地测量与地球动力学, nameEn=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, issn=1671-5942, eissn=null, cn=42-1655/P, coden=null, periodic=0, 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=BeWo6OWOseISH6uPOmc2hA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geodesy and Geodynamics, journalRemark=null, publicationField=null, createdTime=1783394231074, updatedTime=1788951966472, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=BeWo6OWOseISH6uPOmc2hA==, picEn=YHLfVa8gITbOo0FeIjbLDg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522356412666698, language=CN, name=大地测量与地球动力学, 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=1788951966622, updatedTime=1788951966622, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522356576244555, language=EN, name=Journal of Geodesy and Geodynamics, 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=1788951966661, updatedTime=1788951966661, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1281212831689347082, websiteList=[Website(id=1281216327125799907, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/CN, language=CN, createTime=1783395376235, createBy=18614031015, updateTime=1783395439358, updateBy=18614031015, name=大地测量与地球动力学-中文, tplId=1146099689490845704, title=大地测量与地球动力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216715371548758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=articleTextType, value=kx, createTime=1783395468800, updateTime=1783395468800, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715346382931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=banner, value=null, createTime=1783395468794, updateTime=1783395468794, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715400908889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=grayFlag, value=0, createTime=1783395468807, updateTime=1783395468807, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715333800018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395468791, updateTime=1783395468791, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715421880411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=minRunFlag, value=0, createTime=1783395468812, updateTime=1783395468812, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715363160149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic, createTime=1783395468798, updateTime=1783395468798, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715409297498, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=silenceFlag, value=0, createTime=1783395468809, updateTime=1783395468809, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715358965844, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1783395468797, updateTime=1783395468797, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715384131671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeColor, value=null, createTime=1783395468803, updateTime=1783395468803, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715392520280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeStyle, value=null, createTime=1783395468805, updateTime=1783395468805, creator=18614031015, updator=18614031015)]), Website(id=1281216327713002474, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/EN, language=EN, createTime=1783395376375, createBy=18614031015, updateTime=1783395435863, updateBy=18614031015, name=大地测量与地球动力学-英文, tplId=1146101810881728533, title=Journal of Geodesy and Geodynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216680483328066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=articleTextType, value=kx, createTime=1783395460482, updateTime=1783395460483, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680453967935, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=banner, value=null, createTime=1783395460475, updateTime=1783395460475, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680521076805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=grayFlag, value=0, createTime=1783395460491, updateTime=1783395460491, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680437190718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395460471, updateTime=1783395460471, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680542048327, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=minRunFlag, value=0, createTime=1783395460496, updateTime=1783395460496, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680474939457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic, createTime=1783395460480, updateTime=1783395460480, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680533659718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=silenceFlag, value=0, createTime=1783395460494, updateTime=1783395460494, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680462356544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1783395460477, updateTime=1783395460477, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680495910979, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeColor, value=null, createTime=1783395460485, updateTime=1783395460485, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680508493892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeStyle, value=null, createTime=1783395460488, updateTime=1783395460488, creator=18614031015, updator=18614031015)])], journalTitle=大地测量与地球动力学, weixinUrl=null, journalUrl=http://www.jgg09.com/CN/home, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geodesy and Geodynamics, journalPhotoCn=BeWo6OWOseISH6uPOmc2hA==, journalPhotoEn=YHLfVa8gITbOo0FeIjbLDg==, journalFirstLetter=D, 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/ddcl/CN/10.14075/j.jgg.2024.12.596, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.12.596, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2024.12.596, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2024.12.596, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1768406400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于机器学习模型与特征筛选的安徽省滑坡灾害易发性分布研究
收藏切换
陆子康 1 , 陈宏信 1, * , 冯世进 1 , 赵勇 1 , 沈国栋 2 , 陈修和 2
大地测量与地球动力学 | 地球动力学 2026,46(1): 68-77
收起
收藏切换
大地测量与地球动力学 |地球动力学 2026 , 46 (1) : 68 -77
基于机器学习模型与特征筛选的安徽省滑坡灾害易发性分布研究
全屏
[Author(id=1322566809073595376, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2330861@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566809354613746, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809073595376, language=EN, stringName=Zikang LU, firstName=Zikang, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566809421722611, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809073595376, language=CN, stringName=陆子康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio={"content":"

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

"}, bioImg=null, bioContent=

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566809497220085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenhongxin@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322566809778238455, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809497220085, language=EN, stringName=Hongxin CHEN, firstName=Hongxin, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566809849541624, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809497220085, language=CN, stringName=陈宏信, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566809916650491, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, 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=1322566810201863165, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809916650491, language=EN, stringName=Shijin FENG, firstName=Shijin, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810277360638, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566809916650491, language=CN, stringName=冯世进, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566810344469504, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, 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=1322566810432548865, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810344469504, language=EN, stringName=Yong ZHAO, firstName=Yong, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Civil Engineering, Tongji University, Shanghai 200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810499657730, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810344469504, language=CN, stringName=赵勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 同济大学土木工程学院, 上海, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808633193449, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808641582058, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Tongji University, Shanghai 200092, China), AuthorCompanyExt(id=1322566808649970667, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808633193449, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 同济大学土木工程学院, 上海, 200092)])]), Author(id=1322566810558377988, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=4, 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=1322566810625486854, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810558377988, language=EN, stringName=Guodong SHEN, firstName=Guodong, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810692595719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810558377988, language=CN, stringName=沈国栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808977126380, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808985514989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China), AuthorCompanyExt(id=1322566808993903598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088)])]), Author(id=1322566810759704585, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, orderNo=5, 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=1322566810835202059, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810759704585, language=EN, stringName=Xiuhe CHEN, firstName=Xiuhe, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566810893922316, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, authorId=1322566810759704585, language=CN, stringName=陈修和, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566808977126380, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, xref=null, ext=[AuthorCompanyExt(id=1322566808985514989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China), AuthorCompanyExt(id=1322566808993903598, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566805118366675, companyId=1322566808977126380, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088)])])]
陆子康1 , 陈宏信1, * , 冯世进1, 赵勇1, 沈国栋2, 陈修和2
作者信息
  • 1 同济大学土木工程学院, 上海, 200092
  • 2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088
通讯作者:
陈宏信, 教授, 主要研究方向为工程地质与环境灾害, E-mail:
作者简介:

陆子康, 硕士生, 主要研究方向为边坡失稳流滑预测, E-mail:

Landslide Susceptibility Distribution in Anhui Province Based on Machine Learning Model and Feature Selection
Zikang LU1 , Hongxin CHEN1, * , Shijin FENG1, Yong ZHAO1, Guodong SHEN2, Xiuhe CHEN2
Affiliations
  • 1 College of Civil Engineering, Tongji University, Shanghai 200092, China
  • 2 Anhui Transport Consulting and Design Institute Co Ltd, Hefei 230088, China
出版时间: 2026-01-15 doi: 10.14075/j.jgg.2024.12.596
文章导航
收藏切换
摘要
收起

以安徽省历史滑坡与水文地质条件为原始数据，利用5种典型机器学习模型，选取9种环境致灾因子作为初始输入变量，针对机器学习输入变量筛选组合对不同模型的性能影响问题，采用多种因子筛选方法及数种评价指标，考察各筛选组合下每种算法模型对滑坡易发性的预测精度。评价结果显示，全选组与轻量梯度提升机(LightGBM)模型的组合具有最优的性能；在研究区的滑坡易发性研究中，对机器学习输入因子的筛选并不一定对模型的性能提升产生正面影响；集成模型比单评估器模型性能更优，且LightGBM由于采用了基于叶子节点的决策树算法，相较于其他集成算法模型性能有一定的提升。

滑坡  /  机器学习  /  特征筛选  /  易发性  /  集成模型

This paper uses historical landslide and hydrogeological data from Anhui province as the original dataset, employing five typical machine learning models and selects nine environmental disaster-inducing factors as initial input variables. To explore the impact of different machine learning input variable selection combinations on the performance of various models, multiple factor selection methods and several evaluation metrics are used to examine the prediction accuracy of each algorithm model under different selection combinations for landslide susceptibility. The evaluation results show that the combination of the full selection set and the lightweight gradient boosting machine (LightGBM). model yields the best performance. Therefore, this combination is chosen for the landslide susceptibility mapping in the study area. Moreover, the study suggests that factor selection for machine learning inputs does not necessarily improve model performance in landslide susceptibility studies of the research area. Additionally, ensemble models outperform individual estimator models, and LightGBM, using a leaf-node-based decision tree algorithm, shows improved performance compared to other ensemble algorithms.

landslide  /  machine learning  /  feature selection  /  susceptibility  /  ensemble models
陆子康, 陈宏信, 冯世进, 赵勇, 沈国栋, 陈修和. 基于机器学习模型与特征筛选的安徽省滑坡灾害易发性分布研究. 大地测量与地球动力学, 2026 , 46 (1) : 68 -77 . DOI: 10.14075/j.jgg.2024.12.596
Zikang LU, Hongxin CHEN, Shijin FENG, Yong ZHAO, Guodong SHEN, Xiuhe CHEN. Landslide Susceptibility Distribution in Anhui Province Based on Machine Learning Model and Feature Selection[J]. Journal of Geodesy and Geodynamics, 2026 , 46 (1) : 68 -77 . DOI: 10.14075/j.jgg.2024.12.596
正文
收起
随着计算机技术的不断发展，结合机器学习的统计预测模型已成为应用最为广泛的滑坡易发性分析方法之一[1-3]。不少学者在构建预测模型前对原始环境因子进行相关性筛选，以此剔除冗余或不相关的因子，并认为该步骤能有效提高预测模型的准确性[4-5]。机器学习模型的训练过程中，去除冗余输入特征往往能够降低过拟合的风险，既能减少由于噪声特征而引入误导信息的可能性，又能选择最相关的特征, 使模型更专注于重要信息, 从而提升预测的准确性[6]。然而，统计筛选的结果虽然能在一定程度上反映潜在的冗余或不相关信息，也可以提升数据处理阶段的效率，但实际上并没有充分的理由证明其筛选剔除的一定为冗余特征或噪声特征。
研究表明，对输入特征的“优选”并不一定会提高模型的性能，也可能导致有效信息的丢失，造成模型拟合效果变差[7]。然而，目前在区域滑坡易发性分析中鲜有学者针对这一问题进行深入研究，尚未充分探讨环境致灾因子的筛选与机器学习模型的组合对预测精度的影响。因此，本文选取安徽省作为研究区域，结合历史滑坡点位的分布，利用多卫星遥感数据得到多种环境致灾因子在研究区的空间分布; 选取典型机器学习模型，同时采用多种因子筛选方法得到不同的输入变量组合，一方面研究不同机器学习预测模型的滑坡易发性评价精度，另一方面研究不同环境致灾因子组合对模型预测精度的影响; 最后选取最佳输入变量与算法模型的组合，得到研究区滑坡灾害易发性分布。本文研究有助于科学防灾减灾和工程安全建设。
1 研究区概况与基础数据
收起
1.1 研究区概况
安徽省位于我国华东长江中下游地区，处于暖温带与亚热带的过渡地带，夏季雨水集中；全省地形地貌复杂多样，既有江淮丘陵和皖南山地，也有沿江平原和淮北平原，总体呈山区多、平原丘陵少的特点。
在地形、气候及人类活动等多种因素的综合影响下，安徽省部分地区滑坡地质灾害频发。尤其是在皖西大别山区和皖南山区等区域，由于地形起伏较大，且近年来人类活动加剧、工程建设频繁，滑坡风险逐渐增高。特别是梅雨季降雨量充沛，这些山区滑坡灾害频率高、影响大。目前针对安徽地区的滑坡灾害研究多集中在具体案例的分析，缺乏全区域内的滑坡易发性预测与风险分析[8]。而对区域性滑坡灾害易发性的精确分析预测有助于减轻地质灾害对当地居民的影响，还可以为防灾减灾工作提供科学依据，确保该地区经济社会的可持续发展。
1.2 研究区历史滑坡点分布与非历史滑坡点提取
本文汇总安徽省交通规划设计研究院提供的2000—2020年省内滑坡案例数据，整理灾害发生的地理位置信息，形成历史滑坡编录数据库。
对原始数据去除异常值并随机筛选后，利用ArcGIS软件使点位分布可视化。通过坐标变换投影，采用WGS-1984地理坐标系(根据安徽省所处经纬度统一选用50N分度带)。最终得到研究区1 210个历史滑坡点位的空间分布，如图 1(a)所示。初步发现，历年来滑坡灾害多分布在安徽省境内皖西大别山区和皖南山区。两大山区地势崎岖，地形起伏较大，且降雨充沛，因此成为滑坡灾害的高发区。
黄发明等[9]认为，远离历史滑坡样本所在区域选择非滑坡样本对机器学习易发性预测结果的准确性有正面影响。本研究将所有历史滑坡点方圆500 m内作为缓冲区，将缓冲区和江河水系等所在区域之外的范围作为非滑坡区域，从非滑坡区域中利用随机抽样选取非历史滑坡样本数据。根据相关研究[10]，用于机器学习训练历史灾害点与非灾害点比例最优为1∶10~1∶5，最终获得9 000个非历史滑坡点位数据，空间分布如图 1(b)所示。
1.3 滑坡环境致灾因子选取
滑坡灾害的孕育与所处地理环境的水文地貌等多种条件息息相关，国内外相关研究中用过的环境致灾因子多达百余种，总体上可以分为4种类型：地形地貌、地质条件、水文环境与人类活动[11]。为全面深入地评价研究区的滑坡灾害风险，参考已有研究，从上述4个角度出发，并结合研究区域环境特点，共选取9个环境致灾因子。
1) 基于地形地貌，选取高程、坡度、地面粗糙度3个环境致灾因子。海拔高程的差异，一方面导致附近的水文地理环境差异，间接影响了植被生长类型、岩石风化程度等；另一方面，地形崎岖起伏构造出的倾坡为滑坡启动提供势能基础，是滑坡灾害发生的先决条件之一。这3种地形地貌因子数据均以研究区的数字高程模型(DEM)为基础数据源计算得出。
2) 基于地质条件，选取地层岩性、土壤重度2个环境致灾因子。岩土性质与节理和裂隙的发育直接相关，也会影响降雨渗入能力；土壤重度直接影响着坡体的应力分布以及土壤的结构和稳定性。
3) 基于水文环境，选取月均降雨量、归一化植被指数(normalized difference vegetation index, NDVI)、距水系距离3个环境致灾因子。降雨是滑坡灾害的重要诱发因素之一，降雨渗入直接影响坡体孔隙水压力与土壤含水量，从而影响岩土体抗剪能力；归一化植被指数反映了区域植被覆盖的疏密，植物根系往往能够起到稳定土壤保持水土的作用，间接影响滑坡发生的概率；河流湖泊会影响周围地下水的流动及分布，尤其是安徽地区水网密布，坡体距水系的远近与滑坡灾害的易发与否关系密切。
4) 基于人类活动，选取距路网距离因子作为环境致灾因子。安徽地区铁路公路网密度很高，而道路的修建总是伴随着开挖、削坡等改造自然地貌的人类活动，此外交通运输带来的振动荷载可能会导致邻近土体内部颗粒与水分的重分布，也可能引起岩土体中裂缝和节理扩展，增大滑坡灾害发生的可能性[12]。
结合相关原始数据，利用ArcGIS软件，制作研究区9种环境致灾因子的空间分布图，如图 2所示。每幅图均采用WGS-1984地理坐标系，根据安徽省所处经纬度统一选用50N分度带，且栅格单元精度均为30 m。选取的9种环境致灾因子的数据源、年份和空间分布图生成方法如表 1所示。
2 滑坡环境致灾因子可视化与归一化
收起
2.1 环境致灾因子可视化
将安徽省1 210个历史滑坡点位与9 000个非历史滑坡点位合并，得到10 210个研究区空间点，并提取每个点位处9种环境致灾因子数据和分类标签数据(将历史滑坡点标记为“1”，非历史滑坡点标记为“0”)作为样本空间全集，接着通过密度分布将样本空间历史滑坡点与非历史滑坡点的环境致灾因子数据可视化。其中，岩性因子数据为离散型而非连续型，故以频率分布将其可视化，如图 3所示。
从可视化数据可以初步看出，在高程分布上，相较于非历史滑坡点，历史滑坡点处海拔偏高。此外，根据坡度与地面粗糙度分布情况可知，安徽省历史滑坡点位所处位置坡度更陡，主要集中在10°~30°区间内，且地形起伏更大。在岩性的分布上，研究区内非滑坡点多以松散沉积物为主，而历史滑坡点岩性多为酸性深成岩和硅质碎屑沉积岩，这可能是由于这2种岩石风化特点和其节理、层理的存在，导致在降雨等因素影响下，内部结构更容易失稳，滑坡发生的概率较高。此外，安徽省历史滑坡点月均降雨量相较于非滑坡点较大，空间分布上距离也更接近于公路和水系，这是由于靠近水系的区域一般地下水位较高，会导致坡体的抗剪强度降低。另外，在道路建设、隧道开挖等工程中，削坡挖掘等人类活动会破坏原有的地质结构和地貌特征，使边坡稳定性下降。
通常来说，更大的土壤重度或更低的植被指数更容易诱发滑坡灾害。因为斜坡体自重是滑坡发生的主要驱动力，且重度较大的土壤有着较小孔隙与较低渗透性，遭遇降雨时内部水分累积，土壤有效应力降低，进一步增加滑坡发生的可能性[13]; 低NDVI值表明植被覆盖度不高，而植被的根系可以增强土壤的结构稳定性，减少土壤侵蚀，较低的植被覆盖度往往会增加滑坡风险。然而，研究区历史滑坡点的空间分布却更偏向于土壤重度更低、归一化植被指数更高的地域，推测可能的原因如下：由于安徽省植被覆盖更茂密的区域和地表土壤重度低的区域多处于地形起伏更大的两大山区，但是滑坡灾害受多种因素共同影响，很可能对于本研究区的滑坡灾害而言，地形地貌比地质条件、水文环境影响权重更大。
综上所述，历史滑坡的空间分布与单个环境致灾因子间有一定的关系，但规律性较模糊，所以在研究区滑坡灾害风险的研究中，不能仅关注单一因子与滑坡灾害的关联，考虑多种因子耦合作用对滑坡灾害孕育的影响很有必要，因此在本文的后续研究中将采用更合理的复杂非线性研究方法。
2.2 环境致灾因子无量纲归一化
为了后续进行多方法环境致灾因子筛选，将不同因子组合作为机器学习模型的输入变量，将样本空间全集10 210个点位对应的9种环境致灾因子数值分别进行归一化处理，以降低数据离散性，同时减少量纲不同带来的影响。计算方法如下：
$X_{i j}^*=\frac{X_{i j}-\left(X_j\right)_{\max }}{\left(X_j\right)_{\min }-\left(X_j\right)_{\max }}$
式中，Xij和Xij*分别代表第i个点位的第j种因子无量纲归一化前和后的值；(Xj)min和(Xj)max分别代表样本空间全集中第j种因子数值的最小值与最大值。对于离散型类别数据岩性因子，先将每种标签按种类编号赋值进行数字化，再进行归一化处理。处理后的每种环境致灾因子与分类标签数据(历史滑坡点标签为“1”，非历史滑坡点标签为“0”)均作为预选的模型输入特征参数。
3 滑坡环境致灾因子的筛选组合
收起
以无量纲归一化处理后的环境致灾因子数据和分类标签数据作为机器学习模型的原始输入变量。首先，将没经过筛选的全部原始输入变量记作组合A，然后采用方差膨胀因子与容忍度分析、粗糙集法分析和斯皮尔曼相关性分析3种不同的方法对原始输入变量进行筛选。
3.1 方差膨胀因子与容忍度分析
方差膨胀因子(VIF)和容忍度(TOL)是回归分析中多重共线性程度的衡量指标，VIF表示由于多重共线性导致该自变量回归系数方差膨胀的倍数，用于确定一个变量与同组其他变量之间的相关性；TOL是VIF的倒数，表示某个自变量不受其他变量影响的程度。
依次选取9种环境致灾因子中的一个为因变量，其他变量作为自变量回归模型的决定系数，利用VIF和TOL进行多重共线性分析，结果如表 2所示。剔除存在较强多重共线性的因子(VIF＞2，TOL＜0.5)[14]，选取高程、坡度、地层岩性、土壤重度、月均降雨量、归一化植被指数、距水系距离和距路网距离共8种环境致灾因子和分类标签数据作为机器学习模型输入变量，筛选后的因子组合记作组合B。
3.2 粗糙集法分析
粗糙集法(RST)是一种以集合论为基础的方法，它将对象划分为不同的等价类，即具有相同属性的对象可以被视为同一类，同时衡量某些属性对决策属性的依赖程度。通过粗糙集法，可以去除冗余属性，从而缩小属性空间[15]。
利用RSE2软件，将经过离散化处理的所有环境致灾因子作为输入，删除其中干扰或冗余的属性，得到输出中的7个核心因子：高程、坡度、地面粗糙度、地层岩性、土壤重度、月均降雨量和归一化植被指数。选取这7种环境致灾因子和分类标签数据作为机器学习模型输入变量，筛选后的因子组合记作组合C。
3.3 斯皮尔曼相关性分析
斯皮尔曼相关性(Spearman correlation)分析通过对数据进行秩转换，测量变量之间的单调关系，相较于以往研究中常用的皮尔逊相关性分析，该方法不受数据分布的影响，对异常值不敏感，且在衡量非线性单调关系时效果更好。
本文对各环境致灾因子数据间和因子与分类标签数据间的相关性进行分析，生成原始输入变量的斯皮尔曼相关系数热力图，如图 4所示。根据分析结果，对各因子间相关系数较高的因子(大于0.75)进行筛选，剔除因子与分类标签间相关系数较低(小于0.25)的组合[16]。最终选取高程、坡度、地面粗糙度、地层岩性、月均降雨量、归一化植被指数共6种环境致灾因子和分类标签数据作为机器学习模型输入变量，筛选后的因子组合记作组合D。
4 机器学习模型和超参数调优
收起
以上述组合A、B、C、D分别作为机器学习模型的输入变量，均随机选取数据集中70%为训练集、30%为测试集(随机种子random_state = 40)，分别采用支持向量机(SVM)、K近邻算法(KNN)、随机森林(RF)、极端梯度提升(XGBoost)和轻量梯度提升机(LightGBM)5种机器学习模型进行训练。
4.1 各机器学习模型简介
5种机器学习模型中，SVM与KNN为单评估器机器学习模型，RF、XGBoost和LightGBM为集成式机器学习模型。SVM利用监督学习方式对数据进行分类和回归分析[17]，它能够通过不同的核函数有效地处理线性可分和线性不可分的数据；KNN通过测量训练数据不同特征值之间的距离划分特征向量空间，并将划分结果作为最终算法模型[18]；RF通过构建多个决策树并将结果进行投票或平均，得到最终的预测[19]；XGBoost的算法思想是将许多弱分类器集成形成一个强分类器，与RF不同，组成XGBoost的弱分类器之间存在先后顺序，后一棵决策树的生成会考虑前一棵决策树的预测结果；LightGBM与XGBoost类似，主要利用弱分类器迭代训练得到最优模型，且其采用基于叶子节点的决策树算法，在很多模型中训练速度更快、内存占用更少[20]。各模型结构示意图如图 5所示。
4.2 各模型的超参数调优
根据以往的研究[21]，超参数的选择在控制机器学习模型的行为中起着至关重要的作用。为探索各机器学习模型的最优性能，获得最合适的模型，本文采用网格搜索方法，利用Python计算每个模型多参数的正交组合在验证集上的表现，来获取5种模型的最优超参数集，不同机器学习模型的超参数设置与选取结果如表 3所示。
5 各环境致灾因子选取组下不同机器学习模型评价结果
收起
5.1 不同机器学习模型训练效率对比
5种机器学习模型分别以A、B、C、D因子组为输入参数，形成20种不同的滑坡易发性分析工况，各工况下模型的训练环境均为Windows 10操作系统，CPU为13th Intel Core i7-13700KF，训练时采用单核运算，并记录各工况下模型的训练时长，如图 6所示。
可以看出，对于每种机器学习模型，选用更少的环境致灾因子种类作为输入参数均可以缩短模型训练时间。可以认为，机器学习输入变量筛选后的组合对模型的效率提升能够起到正面作用。此外，从5种机器学习模型之间的比较来看，训练效率最高的是KNN模型，XGBoost和LightGBM模型的训练效率表现也很优秀，而RF模型所需训练时间最长。可能的原因是：一方面，作为集成式算法的RF模型多决策树会使总时间成本呈线性增长，而同为集成式算法的XGBoost和LightGBM模型相较于RF在算法层面进行了优化并改善了内存访问模式[20]，显著提升了训练效率；另一方面，SVM和KNN虽同为单评估器模型，但后者简化了预测模型的建立过程，这可能会牺牲一定的精度[22]。然而，针对每种工况下模型性能的评价，不仅需要考虑其训练效率，更需要考察各模型的预测精度。
5.2 模型评价指标选择
为了综合评价不同机器学习模型预测区域空间中每个栅格单元滑坡灾害易发性的准确程度，本文采用受试者工作特征(ROC)曲线下面积(AUC值)、平均绝对误差(MAE)与均方根误差(RMSE)作为模型的评价指标。其中，ROC曲线用于判断评价结果与真值的一致程度。横坐标为假阳性率，也称为误报率，是指在所有实际阴性样本中，被错误地识别为阳性的比例；纵坐标为真阳性率，也称为灵敏度，是指在所有实际阳性样本中，被正确地识别为阳性的比例。该曲线下面积即AUC值区间为0~1，AUC值越大则模型的预测性能越好，值越接近1越能体现出模型具有高灵敏度与高特异性。
5.3 不同机器学习模型评价结果
各种工况下模型的ROC曲线如图 7所示，3种评价指标结果如图 8所示。
从各工况的评价指标结果可以看出，4种因子组合对5种机器学习模型的AUC值和RMSE值影响幅度不大，而不同的输入因子组合方式对除了SVM模型以外的其他4种机器学习模型的MAE值影响较为显著，这说明将不同因子组合作为输入参数时，各模型的灵敏度和特异性并未发生显著变化，但SVM之外4种模型的平均预测精度受影响较大。总体上，对于5种机器学习模型，环境致灾因子组合A、B、C、D分别为输入参数时，其AUC值基本呈递减趋势，而MAE与RMSE值均呈递增趋势，因此对于这5种机器学习模型，都是因子组合A工况下的模型精度最优、性能最佳。这意味着在本研究中，对输入特征因子的多种筛选方法均没有起到优化模型预测精度的作用。
有理由认为，在环境致灾因子的筛选过程中往往会存在不可避免的误判，错误地剔除了能一定程度反映滑坡发育特征的有效信息。理想情况下，筛选出与目标变量相关性较高的特征，可以使模型更加专注于学习那些真正对预测结果有影响的因素，且剔除与目标变量相关性较低的噪声以及自身之间相关性较高的冗余特征，可以降低过拟合的风险。但是统计相关性的判别方式揭示出的冗余特征或噪声特征只能认为在一定程度上有参考价值，却并不是确切的定论[22]。尤其是在实际工程问题背景下，选择的特征是否是冗余特征或噪声特征，是否会对模型性能产生负面影响，还需对各工况进行对比与评价。
另一方面，观察同一输入因子组合下各机器学习模型的评价指标，LightGBM拥有最高的AUC值和最低的MAE和RMSE，反映出其具有最优异的性能；XGBoost和RF预测精度略低于LightGBM，也取得了不错的成绩；而SVM和KNN模型的AUC值显著低于其他3种机器学习模型。这是由于RF、XGBoost和LightGBM均为集成式机器学习模型，相比于SVM和KNN等单评估器模型有多预测结果的组合，减少了模型的偏差，从而提高了预测精度。例如，RF通过平均多个模型的结果来降低方差，而XGBoost和LightGBM通过依次训练模型来提高预测精度；此外，相比于XGBoost和RF，LightGBM的表现更好，这是因为其使用了基于叶子节点的决策树算法，而不是传统的分支节点，从而可以更好地拟合数据，提高预测准确性，其对于异常值和缺失值也具有更好的鲁棒性，不容易受到异常数据的影响。
在全部20种工况中，选用因子组合A作为输入参数的LightGBM模型的AUC值达到0.927 8，其MAE和RMSE的值为0.096 0和0.309 8，均反映出上述组合能够在本研究区的滑坡易发性评价中发挥出最优秀的性能，此外，该工况的训练时间(0.88 s)较短。综上所述，本文选择环境致灾因子组A作为模型的输入特征参数，选择LightGBM作为研究区滑坡灾害易发性预测模型。
6 研究区滑坡灾害易发性分布
收起
结合上述选择的输入特征和预测模型的最优组合(组A和LightGBM模型)，对研究区每个栅格单元进行滑坡易发性预测。本文所选研究区范围内栅格单元总计16 011列、20 278行，提取每个栅格单元处9种滑坡环境致灾因子数据作为模型的输入参数，并由所选预测模型输出该栅格被判别为“1”的概率，将该输出作为滑坡易发性高低的判别标准。
综合研究区各栅格单元的易发性评价值，将评价值前20%(从高到低排列)的区域划分为高易发区，将接下来的20%区域划分为较高易发区，据此依次划分出中易发区、较低易发区和低易发区，得到的研究区滑坡灾害易发性分布如图 9所示。进一步利用ArcGIS计算落入每个易发性等级的历史滑坡点数，结果如表 4所示。
由表 4可见，1 210个历史滑坡点中，共有905个点处于较高易发区与高易发区，占总点数比例达到74.79%。整体而言，随着易发性等级的提高，历史滑坡数占比逐渐增大，历史滑坡密度与易发性等级呈显著的正相关关系。
7 结语
收起
本文选取安徽省为研究区域，以滑坡灾害为研究对象，选择9种初始环境致灾因子，结合研究区内历史滑坡灾害点位，利用SVM、RF、KNN、XGBoost和LightGBM等5种机器学习模型和3种原始输入变量筛选方法，进行研究区域内滑坡灾害易发性分析。一方面考察了在选择输入特征时，对影响因子进行相关性分析, 筛选能否优化模型预测结果，另一方面考察了不同种类的机器学习模型预测性能的差异。得到的主要结论如下：
1) 由安徽历史滑坡数据和9种环境致灾因子分布可以初步看出，历史滑坡的空间分布与每个影响因子间有一定的关系，但规律性较模糊。从斯皮尔曼相关性系数热力图可以看出，多种因子与历史滑坡分类存在较复杂的非线性关系。在未来研究中，需要采用更合理的复杂非线性研究方法，考虑多种因子对滑坡灾害的耦合影响。
2) 对比各机器学习模型的训练时间发现，输入变量筛选组合对模型的效率提升能够起到正面作用，但对于本文研究区数据的效率提升量较小。选取AUC、MAE与RMSE作为各机器学习模型的评价指标，在研究区的滑坡灾害易发性预测中，利用因子全选组A作为训练样本的LightGBM模型的AUC为0.927 8、MAE为0.096 0、RMSE为0.309 8，相较于性能紧跟其后且同为集成算法的XGBoost模型分别提升0.68%、5.42%、2.68%。且3种集成式机器学习模型比2种单评估器模型优势显著，因为集成式模型通过多预测结果的组合，减少了模型的偏差。此外，3种集成式机器学习模型中，LightGBM使用了基于叶子节点的决策树算法代替传统的分支节点，对于异常或缺失值也具有更好的鲁棒性。
3) 对于本文所选的研究区及环境致灾因子，在考虑所选预测模型的输入变量时，各输入特征筛选方法均没有对模型的预测精度起到正面影响，因为结果虽然在一定程度上反映了潜在的冗余信息，但实际上并没有充分的理由证明其剔除的一定为冗余特征或噪声特征。如果将统计性分析结果作为输入变量筛选的唯一标准，往往会错误地剔除能一定程度反映滑坡发育特征的有效信息。当然，输入因子选择时仍需要避免重复采用相关性太高且对滑坡有相似影响机制的环境致灾因子。
4) 本文选取环境致灾因子组A和LightGBM模型，得到安徽省滑坡易发性分布图。将全研究区划分为低、较低、中、较高和高5个易发等级区域，统计落入各等级区的历史滑坡点数，结果表明，随着易发性等级的提高，历史滑坡密度显著增大，二者呈显著的正相关，进一步验证了本文方法的可靠性。
基金
收起
  • 长三角科技创新共同体联合攻关项目(2022CSJGG1202)
文献
收起
参考文献 引证文献
排序方式：
1
Huang F M , Cao Z S , Guo J F , et al. Comparisons of Heuristic, General Statistical and Machine Learning Models for Landslide Susceptibility Prediction and Mapping[J]. Catena, 2020, 191
2
Niu H T , Shao S J , Gao J Q , et al. Research on GIS-Based Information Value Model for Landslide Geological Hazards Prediction in Soil-Rock Contact Zone in Southern Shaanxi[J]. Physics and Chemistry of the Earth, Parts A/B/C, 2024, 133
3
邵健, 王霄, 昌文峰, 等. 基于CatBoost算法的滑坡敏感性模型: 以毕节市大方县为例[J]. 计算机与数字工程, 2022, 50 (6): 1365- 1370
Shao Jian , Wang Xiao , Chang Wenfeng , et al. Landslide Sensitivity Model Based on CatBoost Algorithm: Taking Dafang County of Bijie City as an Example[J]. Computerand Digital Engineering, 2022, 50 (6): 1365- 1370
4
王志彪, 赵丽华. 遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形[J]. 大地测量与地球动力学, 2023, 43 (7): 679- 684
Wang Zhibiao , Zhao Lihua . Prediction of Loess Landslides Deformation Using Elman Neural Network Model Based on Genetic Algorithm and Particle Swarm Optimization[J]. Journal of Geodesy and Geodynamics, 2023, 43 (7): 679- 684
5
Zou F , Che E Z , Long M Q . Quantitative Assessment of Geological Hazard Risk with Different Hazard Indexes in Mountainous Areas[J]. Journal of Cleaner Production, 2023, 413
6
Zou Q , Jiang H , Cui P , et al. A New Approach to Assess Landslide Susceptibility Based on Slope Failure Mechanisms[J]. Catena, 2021, 204
7
Sun D L , Shi S X , Wen H J , et al. A Hybrid Optimization Method of Factor Screening Predicated on GeoDetector and Random Forest for Landslide Susceptibility Mapping[J]. Geomorphology, 2021, 379
8
邓佳良, 黄黄, 王耀, 等. 安徽省宁国市山核桃种植区典型滑坡机制与稳定性分析: 以石岭村滑坡为例[J]. 中国地质调查, 2024, 11 (1): 93- 104
Deng Jialiang , Huang Huang , Wang Yao , et al. Mechanism and Stability Analysis of Typical Landslide in Pecan Planting Area of Ningguo City in Anhui Province: A Case Study of Shilingcun Landslide[J]. Geological Survey of China, 2024, 11 (1): 93- 104
9
黄发明, 殷坤龙, 蒋水华, 等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报, 2018, 37 (1): 156- 167
Huang Faming , Yin Kunlong , Jiang Shuihua , et al. Landslide Susceptibility Assessment Based on Clustering Analysis and Support Vector Machine[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37 (1): 156- 167
10
Das I , Stein A , Kerle N , et al. Landslide Susceptibility Mapping along Road Corridors in the Indian Himalayas Using Bayesian Logistic Regression Models[J]. Geomorphology, 2012, 179, 116- 125
11
Rabby Y W , Ishtiaque A , Rahman M S . Evaluating the Effects of Digital Elevation Models in Landslide Susceptibility Mapping in Rangamati District, Bangladesh[J]. Remote Sensing, 2020, 12 (17)
12
Du G L , Zhang Y S , Iqbal J , et al. Landslide Susceptibility Mapping Using an Integrated Model of Information Value Method and Logistic Regression in the Bailongjiang Watershed, Gansu Province, China[J]. Journal of Mountain Science, 2017, 14 (2): 249- 268
13
于宪煜, 熊十力. 基于空间多尺度分析的滑坡易发性评价: 以三峡库区秭归、巴东段为例[J]. 大地测量与地球动力学, 2020, 40 (2): 187- 192
Yu Xianyu , Xiong Shili . Landslide Susceptibility Assessment Based on Spatial Multi-Scale Analysis: A Case Study of Zigui to Badong in the Three Gorges Reservoir Area[J]. Journal of Geodesy and Geodynamics, 2020, 40 (2): 187- 192
14
Djukem W D L , Braun A , Wouatong A S L , et al. Effect of Soil Geomechanical Properties and Geo-Environmental Factors on Landslide Predisposition at Mount Oku, Cameroon[J]. International Journal of Environmental Research and Public Health, 2020, 17 (18)
15
Peng L , Niu R Q , Huang B , et al. Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines: A Case of the Three Gorges Area, China[J]. Geomorphology, 2014, 204, 287- 301
16
瞿伟, 李昕, 李久元, 等. 一种改进自适应步长人工蜂群优化随机森林的滑坡风险性评价方法[J]. 大地测量与地球动力学, 2024, 44 (12): 1211- 1219
Qu Wei , Li Xin , Li Jiuyuan , et al. A Landslide Risk Assessment Method with Improved Adaptive Step Size Artificial Bee Colony Optimization Random Forest[J]. Journal of Geodesy and Geodynamics, 2024, 44 (12): 1211- 1219
17
Andrews-Todd J , Steinberg J , Flor M , et al. Exploring Automated Classification Approaches to Advance the Assessment of Collaborative Problem Solving Skills[J]. Journal of Intelligence, 2022, 10 (3)
18
Bai Z Q , Jiang Y S , Jing C Z , et al. Clayshock Mechanism and Application to Shield Tunneling through Existing Tunnels: Settlement Prediction Using Artificial Intelligence[J]. Journal of Intelligent Construction, 2024, 2 (2): 1- 22
19
郑迎凯, 陈建国, 王成彬, 等. 确定性系数与随机森林模型在云南芒市滑坡易发性评价中的应用[J]. 地质科技通报, 2020, 39 (6): 131- 144
Zheng Yingkai , Chen Jianguo , Wang Chengbin , et al. Application of Certainty Factor and Random Forests Model in Landslide Susceptibility Evaluation in Mangshi City, Yunnan Province[J]. Bulletin of Geological Science and Technology, 2020, 39 (6): 131- 144
20
Bentéjac C , Csörgö A , Martínez-Muñoz G . A Comparative Analysis of Gradient Boosting Algorithms[J]. Artificial Intelligence Review, 2021, 54 (3): 1937- 1967
21
Feng Y , Zhang X L , Feng S J , et al. Improved SOLOv2 Detection Method for Shield Tunnel Lining Water Leakages[J]. Journal of Intelligent Construction, 2023, 1 (1): 1- 15
22
Zhang S C , Li X L , Zong M , et al. Learning k for KNN Classification[J]. ACM Transactions on Intelligent Systems and Technology, 2017, 8 (3): 1- 19
2026年第46卷第1期
40
16
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2024.12.596
  • 接收时间：2025-01-04
  • 首发时间：2026-10-29
  • 出版时间：2026-01-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2025-01-04
基金
长三角科技创新共同体联合攻关项目(2022CSJGG1202)
作者信息
    1 同济大学土木工程学院, 上海, 200092
    2 安徽省交通规划设计研究总院股份有限公司, 合肥, 230088

通讯作者:

陈宏信, 教授, 主要研究方向为工程地质与环境灾害, E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.12.596
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
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
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
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62662699（运营及技术支持）
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持