Wheat LAI Inversion and Yield Estimation under T-MLP
DOI:
https://doi.org/10.54097/ghhm1r17Keywords:
Winter wheat, leaf area index, PROSAIL, Transformer, MLPAbstract
To address the limited accuracy and poor generalization capabilities of existing winter wheat Leaf Area Index (LAI) inversion methods, such as the NDVI vegetation index model and support vector machine (SVM), this paper proposes a hybrid modeling approach that integrates a radiative transfer model with deep learning. This method uses the PROSAIL model to generate simulated samples, optimizes the input parameter configuration through local and global sensitivity analysis, constructs a lookup table (LUT) to assist in the generation of training sets, and designs a T-MLP network that integrates Transformer and Multilayer Perceptron (MLP). This approach leverages the cross-band global dependencies in Landsat 8multispectral data and enhances LAI modeling capabilities through nonlinear regression. Using ground-truth data from the main wheat-producing region of Shangqiu City, Henan Province, this model's performance is validated and compared with the NDVI, PROSAIL and CNN models. Winter wheat yield estimation is then performed using the LAI inverted by the T-MLP model in combination with the EC-LUE model. Results showed that T-MLP achieved superior inversion accuracy across multiple growth stages (R²=0.83, RMSE=1.04), outperforming the NDVI model (R²=0.55, RMSE=1.58), the PROSAIL model (R²=0.76, RMSE=1.36) and CNN model (R²=0.78, RMSE=1.12). Comparison of the inversion results with the MODIS LAI product revealed that T-MLP demonstrated greater robustness in terms of temporal consistency and cross-plot stability, accurately reflecting the dynamic trends of wheat LAI. The relative error of yield predictions was below 10%. This study provides a practical approach for high-precision LAI inversion and yield estimation that integrates physical constraints with the advantages of deep learning.
Downloads
References
[1] Min H.E.; Jianguang W.E.N.; Dongqing Y.O.U.; Yong T.; Shengbiao W.U.; Dalei H.A.O.; Xingwen L.I.N.; Zhangrong G. Review of forest Leaf Area Index retrieval over rugged terrain based on remotely sensed data. Natl. Remote Sens. Bull. 2022, 26, 2451–2472, doi:10.11834/jrs.20210244.
[2] JIANG H.; JIA K.; ZHAO X.; WEI X.; WANG B.; YAO Y.; ZHANG X.; JIANG B. Review on the theory, method, and research progress of leaf area index estimation in mountainous areas. Natl. Remote Sens. Bull. 2020, 24, 1433–1449, doi:10.11834/jrs.20200229.
[3] Tian, Y.; Jiang, Y.; Zeng, M.; Hui, J.; Jiang, Q. Inversion of Cotton Leaf Area Index under Verticillium Wilt Stress from UAV Multispectral Images: Deep Learning-Based vs. Classical-Based Algorithms. Ind. Crops Prod. 2025, 233, 121345, doi:10.1016/j.indcrop.2025.121345.
[4] Mulero, G.; Bonfil, D.J.; Helman, D. Wheat Leaf Area Index Retrieval from Drone-Derived Hyperspectral and LiDAR Imagery Using Machine Learning Algorithms. Agric. For. Meteorol. 2025, 372, 110648, doi:10.1016/j.agrformet.2025.110648.
[5] Guo, J.; Zeng, X.; Ma, Q.; Yuan, Y.; Zhang, N.; Lin, Z.; Yin, P.; Yang, H.; Liu, X.; Zhang, F. UAV-Based Yield Prediction Based on LAI Estimation in Winter Wheat (Triticum Aestivum L.) Under Different Nitrogen Fertilizer Types and Rates. Plants 2025, 14, 1986, doi:10.3390/plants14131986.
[6] Fu, W.; Chen, Z.; Cheng, Q.; Li, Y.; Zhai, W.; Ding, F.; Kuang, X.; Chen, D.; Duan, F. Maize Leaf Area Index Estimation Based on Machine Learning Algorithm and Computer Vision. Agriculture 2025, 15, 1272, doi:10.3390/agriculture15121272.
[7] Vishwakarma, S.K.; Bhattarai, B.; Kothari, K.; Pandey, A. Intercomparison of Machine Learning Models for Estimating Leaf Area Index of Rice Using UAV-Based Multispectral Imagery. Phys. Chem. Earth Parts ABC 2025, 140, 103977, doi:10.1016/j.pce.2025.103977.
[8] Yang, Q.; Zhou, J.; Zhao, L.; Jin, Z. NeRF-LAI: A Hybrid Method Combining Neural Radiance Field and Gap-Fraction Theory for Deriving Effective Leaf Area Index of Corn and Soybean Using Multi-Angle UAV Images. Remote Sens. Environ. 2025, 328, 114844, doi:10.1016/j.rse.2025.114844.
[9] Wu, Q.; Hou, D.; Xie, M.; Gao, Q.; Li, M.; Hao, S.; Cui, C.; Fan, K.; Zhang, Y.; Zhang, Y. Enhanced Spring Wheat Soil Plant Analysis Development (SPAD) Estimation in Hetao Irrigation District: Integrating Leaf Area Index (LAI) Under Variable Irrigation Conditions. Agriculture 2025, 15, 1372, doi:10.3390/agriculture15131372.
[10] Li, H.; Li, Q.; Yu, C.; Luo, S. Unified Estimation of Rice Canopy Leaf Area Index over Multiple Periods Based on UAV Multispectral Imagery and Deep Learning. Plant Methods 2025, 21, 73, doi:10.1186/s13007-025-01398-1.
[11] Yin, G.; Verger, A.; Qu, Y.; Zhao, W.; Xu, B.; Zeng, Y.; Liu, K.; Li, J.; Liu, Q. Retrieval of High Spatiotemporal Resolution Leaf Area Index with Gaussian Processes, Wireless Sensor Network, and Satellite Data Fusion. Remote Sens. 2019, 11, 244, doi:10.3390/rs11030244.
[12] Dongyan Z.; Xuanxuan H.; Fenfang L.; Shizhou D.; Gan Z.; Qi H. Estimation of winter wheat leaf area index using multi-source UAV image feature fusion. Trans. Chin. Soc. Agric. Eng. Trans. CSAE 2022, 38, 171–179, doi:10.11975/j.issn.1002-6819.2022.09.018.
[13] Zhu Sunan. Estimation of crop canopy structural parameters based on Sentinel-2 band. Master's thesis, Nanjing University of Information Science and Technology, 2024.
[14] Zhang Yi. Soybean Leaf Area Index Retrieval Based on UAV Hyperspectral, Multispectral, and LiDAR Remote Sensing Images. Master's Thesis, Yunnan University, 2024.
[15] Yao, Y.; Wang, H.; Yang, X.; Gao, X.; Yang, S.; Zhao, Y.; Li, S.; Zhang, X.; Liu, Z. Interpretable LAI Fine Inversion of Maize by Fusing Satellite, UAV Multispectral, and Thermal Infrared Images. Agriculture 2025, 15, 243, doi:10.3390/agriculture15030243.
[16] Wu, T.; Zhang, Z.; Wang, Q.; Jin, W.; Meng, K.; Wang, C.; Yin, G.; Xu, B.; Shi, Z. Estimating Rice Leaf Area Index at Multiple Growth Stages with Sentinel-2 Data: An Evaluation of Different Retrieval Algorithms. Eur. J. Agron. 2024, 161, 127362, doi:10.1016/j.eja.2024.127362.
[17] WANG Yanlong, W.J. Inversion of Leaf Area Index of Silage Corn Based on PROSAIL Model. Nongye Jixie XuebaoTransactions Chin. Soc. Agric. Mach. 2024, 55.
[18] Li, S.; Lin, Y.; Zhu, P.; Jin, L.; Bian, C.; Liu, J. Combining UAV Multispectral Imaging and PROSAIL Model to Estimate LAI of Potato at Plot Scale. Agriculture 2024, 14, 2159, doi:10.3390/agriculture14122159.
[19] Li Pingping. Winter wheat LAI inversion based on spiking-hybrid method and machine learning. Chinese Agricultural Information 2024, 36, 29–44.
[20] Fan, L.; Fang, S.; Fan, J.; Wang, Y.; Zhan, L.; He, Y. Rice Yield Estimation Using Machine Learning and Feature Selection in Hilly and Mountainous Chongqing, China. Agriculture 2024, 14, 1615, doi:10.3390/agriculture14091615.
[21] Fu, G.; Li, C.; Liu, W.; Pan, K.; He, J.; Li, W. Maize Yield Estimation Based on UAV Multispectral Monitoring of Canopy LAI and WOFOST Data Assimilation. Eur. J. Agron. 2025, 168, 127614, doi:10.1016/j.eja.2025.127614.
[22] Guo, F.; Wang, P.; Tansey, K.; Zhang, Y.; Li, M.; Liu, J.; Zhang, S. A Novel Transformer-Based Neural Network under Model Interpretability for Improving Wheat Yield Estimation Using Remotely Sensed Multi-Variables. Comput. Electron. Agric. 2024, 223, 109111, doi:10.1016/j.compag.2024.109111.
[23] Zhang, L.; Li, C.; Wu, X.; Xiang, H.; Jiao, Y.; Chai, H. BO-CNN-BiLSTM Deep Learning Model Integrating Multisource Remote Sensing Data for Improving Winter Wheat Yield Estimation. Front. Plant Sci. 2024, 15, 1500499, doi:10.3389/fpls.2024.1500499.
[24] Li, C.; Zhang, L.; Wu, X.; Chai, H.; Xiang, H.; Jiao, Y. Winter Wheat Yield Estimation by Fusing CNN–MALSTM Deep Learning with Remote Sensing Indices. Agriculture 2024, 14, 1961, doi:10.3390/agriculture14111961.
[25] Zhang, C.; Diao, C. A Phenology-Guided Bayesian-CNN (PB-CNN) Framework for Soybean Yield Estimation and Uncertainty Analysis. ISPRS J. Photogramm. Remote Sens. 2023, 205, 50–73, doi:10.1016/j.isprsjprs.2023.09.025.
[26] Démoulin, R.; Gastellu-Etchegorry, J.-P.; Lefebvre, S.; Briottet, X.; Zhen, Z.; Adeline, K.; Marionneau, M.; Le Dantec, V. Modeling 3D Radiative Transfer for Maize Traits Retrieval: A Growth Stage-Dependent Study on Hyperspectral Sensitivity to Field Geometry, Soil Moisture, and Leaf Biochemistry. Remote Sens. Environ. 2025, 327, 114784, doi:10.1016/j.rse.2025.114784.
[27] Qiu, L.; Ke, X.; Sun, X.; Lu, Y.; Shi, S.; Liu, W. Investigating the Influence of the Weed Layer on Crop Canopy Reflectance and LAI Inversion Using Simulations and Measurements in a Sugarcane Field. Remote Sens. 2025, 17, 2014, doi:10.3390/rs17122014.
[28] Wang Linfeng. Remote Sensing Assessment of Soybean Waterlogging in Typical Areas of Jilin Province Based on PROSAIL. Master's Thesis, Jilin University, 2025.
[29] Ma, H.; Weiss, M.; Malik, D.; Berthelot, B.; Yebra, M.; Nolan, R.H.; Mialon, A.; Zeng, J.; Quan, X.; Tagesson, H.T.; et al. Satellite Canopy Water Content from Sentinel-2, Landsat-8 and MODIS: Principle, Algorithm and Assessment. Remote Sens. Environ. 2025, 326, 114801, doi:10.1016/j.rse.2025.114801.
[30] Tsele, P.; Ramoelo, A.; Moleleki, L.; Laurie, S.; Mphela, W.; Tshuma, N. Leaf Area Index-Based Phenotypic Assessment of Sweet Potato Varieties Using UAV Multispectral Imagery and a Hybrid Retrieval Approach. Smart Agric. Technol. 2025, 11, 100960, doi:10.1016/j.atech.2025.100960.
[31] Yao, Y.; Wang, H.; Yang, X.; Gao, X.; Yang, S.; Zhao, Y.; Li, S.; Zhang, X.; Liu, Z. Interpretable LAI Fine Inversion of Maize by Fusing Satellite, UAV Multispectral, and Thermal Infrared Images. Agriculture 2025, 15, 243, doi:10.3390/agriculture15030243.
[32] Fan, W.; Wu, J.; Zheng, G.; Zhang, Q.; Xu, X.; Du, H.; Zheng, M.; Zhang, K.; Zhang, F. Retrieving the Leaf Area Index of Dense and Highly Clumped Moso Bamboo Canopies from Sentinel-2 MSI Data. Remote Sens. 2025, 17, 1891, doi:10.3390/rs17111891.
[33] Miranda, R.D.Q.; Nóbrega, R.L.B.; Moura, M.S.B.D.; Raghavan, S.; Galvíncio, J.D. Realistic and Simplified Models of Plant and Leaf Area Indices for a Seasonally Dry Tropical Forest. Int. J. Appl. Earth Obs. Geoinformation 2020, 85, 101992, doi:10.1016/j.jag.2019.101992.
[34] Ma, B.; Xu, M. Identifying Outliers of the MODIS Leaf Area Index Data by Including Temporal Patterns in Post-Processing. Remote Sens. 2023, 15, 5042, doi:10.3390/rs15205042.
[35] Ji, J.; Li, X.; Du, H.; Mao, F.; Fan, W.; Xu, Y.; Huang, Z.; Wang, J.; Kang, F. Multiscale Leaf Area Index Assimilation for Moso Bamboo Forest Based on Sentinel-2 and MODIS Data. Int. J. Appl. Earth Obs. Geoinformation 2021, 104, 102519, doi:10.1016/j.jag.2021.102519.
[36] Alexandridis, T.K.; Ovakoglou, G.; Clevers, J.G.P.W. Relationship between MODIS EVI and LAI across Time and Space. Geocarto Int. 2020, 35, 1385–1399, doi:10.1080/10106049.2019.1573928.
[37] Ganguly, S.; Samanta, A.; Schull, M.; Shabanov, N.; Milesi, C.; Nemani, R.; Knyazikhin, Y.; Myneni, R. Generating Vegetation Leaf Area Index Earth System Data Record from Multiple Sensors. Part 2: Implementation, Analysis and Validation. Remote Sens. Environ. 2008, 112, 4318–4332, doi:10.1016/j.rse.2008.07.013.
[38] Yuan, W.; Liu, S.; Yu, G.; Bonnefond, J.-M.; Chen, J.; Davis, K.; Desai, A.R.; Goldstein, A.H.; Gianelle, D.; Rossi, F.; et al. Global Estimates of Evapotranspiration and Gross Primary Production Based on MODIS and Global Meteorology Data. Remote Sens. Environ. 2010, 114, 1416–1431, doi:10.1016/j.rse.2010.01.022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Advanced Engineering and Technology Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
