作物学报2025，Vol.51Issue(5)：1389-1399,中插10-中插19,21.DOI:10.3724/SP.J.1006.2025.43050
耦合多源无人机遥感数据和机器学习方法的玉米SPAD估测
Maize SPAD estimation by combining multi-source unmanned aerial vehicle remote sensing data and machine learning methods
摘要
Abstract
Accurately identifying chlorophyll content is essential for precise fertilization management in maize.The SPAD(Soil and plant analyzer development)value of leaves serves as a reliable indicator of chlorophyll content.For SPAD prediction using remote sensing,most existing studies rely on single data sources combined with machine learning methods.To enhance SPAD prediction accuracy,this study explores the feasibility of integrating multi-source unmanned aerial vehicle(UAV)data with vari-ous machine learning methods,comparing the results to traditional approaches.A maize field experiment was conducted with different treatments,including organic fertilizer,inorganic fertilizer,straw return,and varying planting densities.UAV multispec-tral and RGB images were acquired at the V4 and V9 growth stages,and SPAD values of maize leaves were measured subse-quently.Using a multi-scale analysis approach,RGB images were fused with multispectral images to produce a dataset combining high spatial resolution with multispectral information.Additionally,an ensemble learning method(ELM)was developed by inte-grating multiple machine learning models,including the backpropagation artificial neural network(BP-ANN),support vector machine(SVM),generalized additive model(GAM),and random forest(RF).Different scenarios were designed by coupling various data sources and machine learning models.The dataset was divided into calibration and validation subsets.SPAD predic-tion models were developed by calibration dataset,and their performance was evaluated using the validation dataset.Comparative analysis identified the optimal model and data source.Results showed that multi-source data significantly improved SPAD predic-tion accuracy by combining the spectral information of multispectral images with the texture information of RGB images.Fur-thermore,the ensemble learning method outperformed single machine learning methods,achieving higher SPAD prediction accu-racy.Among all scenarios,the SPAD prediction model using the ELM method and fused images exhibited the highest accuracy,with an a Rcal2 value of 0.83 and RMSEcal value of 1.93 during calibration,and an Rval2 value of 0.80 and RMSEval value of 2.07 during validation.In contrast,models based on other scenarios yielded Rcal2 values ranging from 0.64 to 0.88 and RMSEcal values ranging from 1.63 to 2.84 during calibration,and Rval2 values ranging from 0.60 to 0.78 and RMSEval values ranging from 2.18 to 3.01 during validation.This study demonstrates that the optimal strategy for SPAD prediction in maize involves using multi-source data and ensemble learning models.These findings provide technical support for further advancements in precision nitrogen management.关键词
机器学习/多源数据/玉米/SPAD/无人机Key words
machine learning method/multi-source data/maize/SPAD/unmanned aerial vehicle引用本文复制引用
周科,陈鹏飞..耦合多源无人机遥感数据和机器学习方法的玉米SPAD估测[J].作物学报,2025,51(5):1389-1399,中插10-中插19,21.基金项目
本研究由中国科学院先导A专项(XDA28040502)和国家自然科学基金项目(41871344)资助. This study was supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA28040502)and the National Natural Science Foundation of China(41871344). （XDA28040502）
