中国农业信息2025，Vol.37Issue(2)：13-27,15.DOI:10.12105/j.issn.1672-0423.20250202
基于人工智能的农业气象遥感关键参数联合反演方法
Joint inversion method for key parameters of agricultural meteorological remote sensing based on artificial intelligence
摘要
Abstract
[Purpose]To improve the inversion accuracy of key agricultural meteorological remote sensing parameters—land surface temperature(LST),land surface emissivity(LSE),atmospheric water vapor content(WVC),and near-surface air temperature(NSAT)—and to address the issue of insufficient overall accuracy caused by traditional methods not fully utilizing the interdependencies between the parameters.[Method]This paper proposed an artificial intelligence(AI)-based multi-parameter joint inversion method for thermal infrared remote sensing.This method integrated deep learning with physical radiation transfer equations and statistical methods.First,a physical inversion model was derived,and the two conditions required for parameter inversion were clarified to obtain a physically representative solution.Then,a statistical representative solution was constructed based on multi-source data,combining both solutions to form a deep learning training and testing database.The inversion framework directly inverted LST and LSE,using them as prior knowledge to iteratively optimize the inversion accuracy of WVC and NSAT through cross-iteration,eliminating uncertainty and achieving multi-parameter joint inversion.[Result]Practical inversion application analysis was performed using MODIS bands 27,28,29,31,and 32.Data analysis showed that the relative inversion errors for LST under a five-band combination were 0.42 K for mean absolute error(MAE)and 0.71 K for root mean square error(RMSE).The relative inversion errors for LSE31 and LSE32 were MAE values of 0.004 and 0.003 respectively,with an RMSE value of 0.005 for both.The inversion relative errors for WVC were 0.46 g/cm² for MAE and 0.62 g/cm² for RMSE.The relative errors for the NSAT inversion was 1.26 K for the MAE and 1.86 K for the RMSE.Introducing LST and LSE into the NSAT inversion and stabilised the inversion accuracy.These results were also confirmed by ground observation station data.[Conclusion]Under the joint inversion strategy,the accuracy of LST and LSE remains stable.Meanwhile,WVC and NSAT overcome the limitations of traditional methods'accuracy by iterative optimization with prior knowledge.Analysis indicates that the AI-based multi-parameter joint inversion method for thermal infrared remote sensing effectively utilizes the relationships between parameters,significantly enhancing the overall inversion accuracy,which is of great importance for agricultural meteorological remote sensing and satellite sensor design.关键词
人工智能/热红外遥感/农业气象遥感参数/联合反演Key words
artificial intelligence/thermal infrared remote sensing/agricultural meteorological remote sensing parameters/joint inversion引用本文复制引用
毛克彪,肖柳瑞,郭中华,代旺,袁紫晋,施建成..基于人工智能的农业气象遥感关键参数联合反演方法[J].中国农业信息,2025,37(2):13-27,15.基金项目
中央级公益性科研院所基本科研业务费专项"人工智能农业和地学应用研究"(No.Y2025YC86) （No.Y2025YC86）
宁夏科技厅自然科学基金重点项目"人工智能地表温度遥感参数反演范式模型研究"(No.2024AC02032) （No.2024AC02032）
