智能化农业装备学报（中英文）

基于DMFM-Net的冬小麦氮营养指数反演研究

预览PDF | 下载PDF

张云皓 ¹^,² , 孙浩天 ¹^,² , 聂灵芝 ¹^,² , 云白钰 ¹^,² , 徐法虎 ¹^,² , 苏宝峰 ¹^,²^,^*^,^*

智能化农业装备学报（中英文） | 2026,7(2): 112-123

收起

智能化农业装备学报（中英文） | 2026 , 7 (2) : 112 -123

基于DMFM-Net的冬小麦氮营养指数反演研究

全屏

张云皓¹^,², 孙浩天¹^,², 聂灵芝¹^,², 云白钰¹^,², 徐法虎¹^,², 苏宝峰¹^,²^,^*^,^*

作者信息

^1.西北农林科技大学机械与电子工程学院，陕西杨凌，712100

^2.农业农村部农业物联网重点实验室，陕西杨凌，712100

通讯作者:

^* 苏宝峰，男，1981年生，山东济南人，博士，教授；研究方向为田间植物表型获取及应用。E-mail：bfs@nwsuaf.edu.cn

作者简介:

张云皓，男，2001年生，吉林四平人，硕士研究生；研究方向为农业遥感。E-mail：zhangy.h@nwafu.edu.cn

Inversion of winter wheat nitrogen nutrition index based on DMFM-Net

Yunhao Zhang¹^,², Haotian Sun¹^,², Lingzhi Nie¹^,², Baiyu Yun¹^,², Fahu Xu¹^,², Baofeng Su¹^,²

Affiliations

^1.College of Mechanical and Electronic Engineering, Northwest A & F University, Yangling 712100, China

^2.Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Yangling 712100, China

Corresponding Author:

^* Su Baofeng, E-mail: bfs@nwsuaf.edu.cn

Zhang Yunhao, E-mail: zhangy.h@nwafu.edu.cn

出版时间: 2026-05-15 doi: 10.12398/j.issn.2096-7217.2026.02.010

文章导航

摘要

收起

实时且精准地监测冬小麦氮营养指数（nitrogen nutrition index，NNI）对优化大田水肥管理与降低农业面源污染具有重要意义。针对现有深度网络在处理多源无人机遥感数据时易引发模态干扰，以及在时序建模中易丢失二维空间拓扑信息的问题，研究提出一种双分支多源特征融合记忆网络（DMFM-Net）。该方法利用无人机获取冬小麦分蘖期、拔节期和孕穗期的多光谱影像与冠层结构数据，首先通过改进的CBAM-ResNet50双分支骨干网络独立提取光谱特征与冠层结构特征，随后将保留了空间维度的特征张量直接输入卷积长短期记忆网络（ConvLSTM）进行时序建模。结果表明：（1）相比于传统的串行网络（CBAM-ResNet-LSTM）与单分支网络（CBAM-ResNet-ConvLSTM），DMFM-Net有效克服多模态异构数据的噪声干扰，在各关键生育期均展现出最优的反演性能，模型在分蘖期、拔节期和孕穗期的决定系数（R²）分别达0.76、0.86和0.82，均方根误差（RMSE）低至0.11、0.10和0.14。（2）消融试验进一步证实所提架构设计的必要性与科学性。缺乏深层空间编码器的ConvLSTM模型R²显著下降0.21~0.24；而相比3D-ResNet的静态时空特征提取，DMFM-Net凭借ConvLSTM模块覆盖全生育期的长程动态记忆机制，使各时期反演模型R²提升了0.07~0.16。（3）基于最优模型生成的田块尺度空间分布图，精准还原不同施氮梯度下冬小麦氮素营养状态的局部空间异质性及其时间演变规律。综上所述，研究结果为复杂大田环境下作物营养状态的多模态时序动态监测提供了全新的理论范式与技术支撑。

关键词

无人机遥感 / 冬小麦 / 氮营养指数 / 深度学习 / 多源数据融合

Abstract

收起

Real-time and accurate monitoring of the winter wheat nitrogen nutrition index (NNI) is of great significance for optimizing field water and fertilizer management and reducing agricultural non-point source pollution. To address the issues of modal confusion in existing deep networks when processing multi-source UAV remote sensing data, as well as the loss of two-dimensional spatial topological information during temporal modeling, this study proposes a dual-branch multi-source feature fusion memory network (DMFM-Net). Multispectral images and canopy structural data of winter wheat at the tillering, jointing, and booting stages were collected by UAV. An enhanced CBAM-ResNet50 dual-branch backbone was employed to separately extract spectral features and canopy structural features. The spatially preserved feature tensors were then directly input into a convolutional long short-term memory (ConvLSTM) network for temporal modeling. The results show that: (1) Compared with the traditional serial network (CBAM-ResNet-LSTM) and the single-branch network (CBAM-ResNet-ConvLSTM), DMFM-Net effectively overcomes the noise interference of multimodal heterogeneous data and achieves the best inversion performance at all key growth stages. The coefficients of determination (R²) of the model at the tillering, jointing, and booting stages reach 0.76, 0.86, and 0.82, respectively, with root mean square errors (RMSE) as low as 0.11, 0.10, and 0.14. (2) Ablation experiments further confirm the necessity and scientific validity of the proposed architectural design. The ConvLSTM model lacking a deep spatial encoder shows a significant decrease in R² of 0.21-0.24. Moreover, compared with the static spatiotemporal feature extraction of 3D-ResNet, DMFM-Net, by virtue of its ConvLSTM module covering a long-range dynamic memory mechanism across the whole growth period, improves the R² of the inversion models at each stage by 0.07-0.16. (3) The field-scale spatial distribution maps generated by the optimal model accurately reconstruct the local spatial heterogeneity and temporal evolution patterns of winter wheat nitrogen nutritional status under different nitrogen application gradients. In summary, this study provides a new theoretical paradigm and technical support for multimodal time-series dynamic monitoring of crop nutritional status in complex field environments.

Key words

UAV remote sensing / winter wheat / nitrogen nutrition index / deep learning / multi-source data fusion

引用本文

张云皓, 孙浩天, 聂灵芝, 云白钰, 徐法虎, 苏宝峰. 基于DMFM-Net的冬小麦氮营养指数反演研究. 智能化农业装备学报（中英文）, 2026 , 7 (2) : 112 -123 . DOI: 10.12398/j.issn.2096-7217.2026.02.010

Yunhao Zhang, Haotian Sun, Lingzhi Nie, Baiyu Yun, Fahu Xu, Baofeng Su. Inversion of winter wheat nitrogen nutrition index based on DMFM-Net[J]. Journal of Intelligent Agricultural Mechanization, 2026 , 7 (2) : 112 -123 . DOI: 10.12398/j.issn.2096-7217.2026.02.010

基金

收起

宁夏回族自治区重点研发计划项目(2023BCF01001)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Zhang S, Duan J, Qi X, et al. Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis [J]. Computers and Electronics in Agriculture, 2024, 222: 109022.

[2]

许童羽，白驹驰，郭忠辉，等．基于无人机高光谱遥感的水稻氮营养诊断方法[J]．农业机械学报，2023，54（2）：189-197.

Xu Tongyu, Bai Juchi, Guo Zhonghui, et al. Rice nitrogen nutrition diagnosis method based on UAV hyperspectral remote sensing [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2): 189-197.

[3]

Tilman D, Cassman K G, Matson P A, et al. Agricultural sustainability and intensive production practices [J]. Nature, 2002, 418(6898): 671-677.

[4]

Godfray H C J, Beddington J R, Crute I R, et al. Food security: the challenge of feeding 9 Billion people [J]. Science, 2010, 327(5967): 812-818.

[5]

聂鹏程，钱程，覃锐苗，等．天空地一体化信息感知与融合技术发展现状与趋势[J]．智能化农业装备学报（中英文），2023，4（2）：1-11.

Nie Pengcheng, Qian Cheng, Qin Ruimiao, et al. Development status and trends of space-air-ground integrated information sensing and fusion technology [J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(2): 1-11.

[6]

王俊，吴振伟，姜海，等．基于随机森林及遥感植被指数的无人农场水稻产量预测研究[J]．智能化农业装备学报（中英文），2025，6（2）：97-104.

Wang Jun, Wu Zhenwei, Jiang Hai, et al. Rice yield prediction of unmanned farm based on random forest and remote sensing vegetation index [J]. Journal of Intelligent Agricultural Mechanization, 2025, 6(2): 97-104.

[7]

李世隆，许辰一，王楠，等．基于BWO-ELM的水稻氮素无人机高光谱反演研究[J]．智能化农业装备学报（中英文），2024，5（3）：14-21.

Li Shilong, Xu Chenyi, Wang Nan, et al. Research on rice nitrogen unmanned aerial vehicle hyperspectral inversion based on BWO-ELM [J]. Journal of Intelligent Agricultural Mechanization, 2024, 5(3): 14-21.

[8]

潘时佳，吴津乐，程梅，等．基于改进CNN的猕猴桃根区土壤含水率反演方法[J]．农业工程学报，2024，40（11）：85-91.

Pan Shijia, Wu Jinle, Cheng Mei, et al. Inversion method for soil moisture content in kiwifruit root zone using improved CNN [J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(11): 85-91.

[9]

刘开东，曹先林，张金凯，等．基于改进SegFormer的无人机遥感影像小麦冠层分割与高度估计[J]．农业工程学报，2026，42（7）：192-202.

Liu Kaidong, Cao Xianlin, Zhang Jinkai, et al. Wheat canopy segmentation and height estimation from UAV remote sensing images using improved SegFormer [J]. Transactions of the Chinese Society of Agricultural Engineering, 2026, 42(7): 192-202.

[10]

Sun L, Yang C, Wang J, et al. Automatic modeling prediction method of nitrogen content in maize leaves based on machine vision and CNN [J]. Agronomy, 2024, 14(1): 124.

[11]

Xu L, Su X, Wang K, et al. Enhancing canopy nitrogen estimation in Torreya Grandis based on advanced SLIC-EVI and HMT-seCNN methods using hyperspectral UAV data [J]. Computers and Electronics in Agriculture, 2025, 231: 109977.

[12]

Zhang L, Zhang B, Zhang H, et al. Multi-Source feature fusion network for LAI estimation from UAV multispectral imagery [J]. Agronomy, 2025, 15(4): 988.

[13]

Li C, Yang B, Zhang G, et al. Collaboration of hyperspectral data and generative adversarial networks for improved nitrogen nutrition diagnosis and nitrogen requirement estimation in winter wheat [J]. Smart Agricultural Technology, 2025, 12: 101112.

[14]

Wang D, Cao W, Zhang F, et al. A review of deep learning in multiscale agricultural sensing [J]. Remote Sensing, 2022, 14(3): 559.

[15]

程智楷，周智辉，谷晓博，等．基于多模态深度特征模型的冬小麦冠层等效水厚度反演方法[J]．农业工程学报，2025，41（10）：119-128.

Cheng Zhikai, Zhou Zhihui, Gu Xiaobo, et al. Inversion method for canopy equivalent water thickness of winter wheat based on multimodal deep feature model [J]. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(10): 119-128.

[16]

Zaji A, Liu Z, Xiao G, et al. A survey on deep learning applications in wheat phenotyping [J]. Applied Soft Computing, 2022, 131: 109761.

[17]

Li D, Yang S, Du Z, et al. Application of unmanned aerial vehicle optical remote sensing in crop nitrogen diagnosis: a systematic literature review [J]. Computers and Electronics in Agriculture, 2024, 227: 109565.

[18]

Li J, Lu J, Fu H, et al. Research on the inversion of key growth parameters of rice based on multisource remote sensing data and deep learning [J]. Agriculture, 2024, 14(12): 2326.

[19]

Tian H, Wang P, Tansey K, et al. An LSTM neural network for improving wheat yield estimates by integrating remote sensing data and meteorological data in the Guanzhong Plain, PR China [J]. Agricultural and Forest Meteorology, 2021, 310: 108629.

[20]

Cai Y, Li Y, Qi X, et al. A deep learning approach for deriving wheat phenology from near-surface RGB image series using spatiotemporal fusion [J]. Plant Methods, 2024, 20(1): 153.

[21]

Mirhoseini Nejad S M, Abbasi-Moghadam D, Sharifi A. ConvLSTM-ViT: A deep neural network for crop yield prediction using earth observations and remotely sensed data [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 17489-17502.

[22]

Zhao J, Li H, Liu J, et al. Integration of spatial attention mechanism into 1D-CNN for prediction of wheat leaf nitrogen concentration from UAV-borne hyperspectral imagery [J]. Computers and Electronics in Agriculture, 2025, 239: 110906.

[23]

Wang J, Wang P, Tian H, et al. A deep learning framework combining CNN and GRU for improving wheat yield estimates using time series remotely sensed multi-variables [J]. Computers and Electronics in Agriculture, 2023, 206: 107705.

[24]

李学琨，刘勇，吕丰顺，等．基于IPSO-LSTM神经网络的施肥量预测系统[J]．中国农机化学报，2025，46（12）：208-214.

Li Xuekun, Liu Yong, Lü Fengshun, et al. Fertilization amount prediction system based on IPSO-LSTM neural network [J]. Journal of Chinese Agricultural Mechanization, 2025, 46(12): 208-214.

[25]

王鹏新，韩弘炜，李明启，等．基于LSTM-AM的冬小麦单产估测模型构建及其可解释性分析[J]．农业机械学报，2026，57（6）：206-214.

Wang Pengxin, Han Hongwei, Li Mingqi, et al. Construction and interpretability analysis of winter wheat yield estimation model based on LSTM-AM [J]. Transactions of the Chinese Society for Agricultural Machinery, 2026, 57(6): 206-214.

[26]

王晓玲．长江中下游稻麦两熟区冬小麦植株器官临界氮浓度模型构建及氮素诊断调控研究[D]．南京：南京农业大学，2017：28.

Wang Xiaoling. Establishment of critical nitrogen concentration model and nitrogen diagnosis and regulation in winter wheat organs in rice-wheat rotation area in the middle and lower reaches of Yangtze River [D]. Nanjing: Nanjing Agricultural University, 2017: 28.

[27]

韩宜秀．基于无人机多光谱遥感的冬小麦生长估测与氮营养诊断[D]．杨凌：西北农林科技大学，2023：117.

Han Yixiu. Estimation of winter wheat growth and nitrogen nutrition diagnosis based on UAV multispectral remote sensing [D]. Yangling: Northwest A&F University, 2023: 117.

[28]

Jiang J, Atkinson P M, Zhang J, et al. Combining fixed-wing UAV multispectral imagery and machine learning to diagnose winter wheat nitrogen status at the farm scale [J]. European Journal of Agronomy, 2022, 138: 126537.

[29]

Xu S, Xu X, Blacker C, et al. Estimation of leaf nitrogen content in rice using vegetation indices and feature variable optimization with information fusion of multiple-sensor images from UAV [J]. Remote Sensing, 2023, 15(3): 854.

2026年第7卷第2期

预览PDF | 下载PDF

引用本文

BibTeX

文章信息

doi: 10.12398/j.issn.2096-7217.2026.02.010

接收时间：2026-04-19
首发时间：2026-11-05
出版时间：2026-05-15

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2026-04-19
修回日期：2026-05-06

基金

Ningxia Hui Autonomous Region Key Research and Development Program Project(2023BCF01001)

宁夏回族自治区重点研发计划项目(2023BCF01001)

作者信息

^1.西北农林科技大学机械与电子工程学院，陕西杨凌，712100

^2.农业农村部农业物联网重点实验室，陕西杨凌，712100

通讯作者:

^* 苏宝峰，男，1981年生，山东济南人，博士，教授；研究方向为田间植物表型获取及应用。E-mail：bfs@nwsuaf.edu.cn

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/znhnyzbxb/CN/10.12398/j.issn.2096-7217.2026.02.010

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

BibTeX
EndNote
RefWorks
TxT