基于遥感多参数和CNN-Transformer的冬小麦单产估测  

Yield Estimation of Winter Wheat Based on Multiple Remotely Sensed Parameters and CNN-Transformer

作　　者：王鹏新[1,2] 杜江莉 张悦 刘峻明 李红梅 王春梅 WANG Pengxin;DU Jiangli;ZHANG Yue;LIU Junming;LI Hongmei;WANG Chunme(College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications,Ministry of Agriculture and Rural Affairs,Beijing 100083,China;College of Land Science and Technology,China Agricultural University,Beijing 100193,China;Shaanxi Provincial Meteorological Bureau,Xi'an 710014,China;Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China)

机构地区：[1]中国农业大学信息与电气工程学院,北京100083 [2]农业农村部农机作业监测与大数据应用重点实验室,北京100083 [3]中国农业大学土地科学与技术学院,北京100193 [4]陕西省气象局,西安710014 [5]中国科学院空天信息创新研究院,北京100094

出　　处：《农业机械学报》2024年第3期173-182,共10页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金项目(42171332)。

摘　　要：为了提高冬小麦单产估测精度,改善估产模型存在的高产低估和低产高估等现象,以陕西省关中平原为研究区域,选取旬尺度条件植被温度指数(VTCI)、叶面积指数(LAI)和光合有效辐射吸收比率(FPAR)为遥感特征参数,结合卷积神经网络(CNN)局部特征提取能力和基于自注意力机制的Transformer网络的全局信息提取能力,构建CNN-Transformer深度学习模型,用于估测关中平原冬小麦产量。与Transformer模型(R^(2)为0.64,RMSE为465.40 kg/hm^(2),MAPE为8.04%)相比,CNN-Transformer模型具有更高的冬小麦单产估测精度(R^(2)为0.70,RMSE为420.39 kg/hm^(2),MAPE为7.65%),能够从遥感多参数中提取更多与产量相关的信息,且对于Transformer模型存在的高产低估和低产高估现象均有所改善。基于5折交叉验证法和留一法进一步验证了CNN-Transformer模型的鲁棒性和泛化能力。此外,基于CNN-Transformer模型捕获冬小麦生长过程的累积效应,分析逐步累积旬尺度输入参数对产量估测的影响,评估模型对于冬小麦不同生长阶段的累积过程的表征能力。结果表明,模型能有效捕捉冬小麦生长的关键时期,3月下旬至5月上旬是冬小麦生长的关键时期。In order to improve the accuracy of winter wheat yield estimation and the phenomena of underestimation of high yield and overestimation of low yield that exist in yield estimation models,the Guanzhong Plain in Shaanxi Province,China was taken as the study area,and the vegetation temperature condition index(VTCI),leaf area index(LAI)and fraction of photosynthetically active radiation(FPAR)at the ten-day interval were selected as remotely sensed parameters,and a deep learning model was proposed for estimating winter wheat yield by combining the local feature extraction capability of convolutional neural network(CNN)and the global information extraction capability of Transformer network based on the mechanism of self-attention.Compared with the Transformer model(R^(2) was 0.64,RMSE was 465.40kg/hm^(2),MAPE was 8.04%),the CNN-Transformer model had higher accuracy in estimating winter wheat yield(R^(2) was 0.70,RMSE was 420.39kg/hm^(2),MAPE was 7.65%),which can extract more yield-related information from the multiple remotely sensed parameters,and improved the underestimation of high yield and overestimation of low yield which existed in the Transformer model.The robustness and generalization ability of the CNN-Transformer model were further validated based on the five-fold cross-validation method and the leave-one-out method.In addition,based on the CNN-Transformer model,the cumulative effect of the winter wheat growth process was revealed,the impact of gradually accumulating ten-day scale input information on yield estimation was analyzed,and the ability of the model to characterize the accumulation process of winter wheat at different growth stages was assessed.The results showed that the model can effectively capture the critical period of winter wheat growth,which was from late March to early May.

关 键 词：冬小麦 作物估产 遥感多参数 卷积神经网络 Transformer模型 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]