Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches

doi:10.3390/rs12010021

	Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches
	Zhang, Liangliang 2; Zhang, Zhao 2; Luo, Yuchuan 2; Cao, Juan 2; Tao, Fulu 1,3
刊名	REMOTE SENSING
	2020
卷号	12 期号:1 页码:20
关键词	maize yield prediction EVI SIF LST machine learning LSTM
DOI	10.3390/rs12010021
通讯作者	Zhang, Zhao(zhangzhao@bnu.edu.cn)
英文摘要	Maize is an extremely important grain crop, and the demand has increased sharply throughout the world. China contributes nearly one-fifth of the total production alone with its decreasing arable land. Timely and accurate prediction of maize yield in China is critical for ensuring global food security. Previous studies primarily used either visible or near-infrared (NIR) based vegetation indices (VIs), or climate data, or both to predict crop yield. However, other satellite data from different spectral bands have been underutilized, which contain unique information on crop growth and yield. In addition, although a joint application of multi-source data significantly improves crop yield prediction, the combinations of input variables that could achieve the best results have not been well investigated. Here we integrated optical, fluorescence, thermal satellite, and environmental data to predict county-level maize yield across four agro-ecological zones (AEZs) in China using a regression-based method (LASSO), two machine learning (ML) methods (RF and XGBoost), and deep learning (DL) network (LSTM). The results showed that combining multi-source data explained more than 75% of yield variation. Satellite data at the silking stage contributed more information than other variables, and solar-induced chlorophyll fluorescence (SIF) had an almost equivalent performance with the enhanced vegetation index (EVI) largely due to the low signal to noise ratio and coarse spatial resolution. The extremely high temperature and vapor pressure deficit during the reproductive period were the most important climate variables affecting maize production in China. Soil properties and management factors contained extra information on crop growth conditions that cannot be fully captured by satellite and climate data. We found that ML and DL approaches definitely outperformed regression-based methods, and ML had more computational efficiency and easier generalizations relative to DL. Our study is an important effort to combine multi-source remote sensed and environmental data for large-scale yield prediction. The proposed methodology provides a paradigm for other crop yield predictions and in other regions.
资助项目	Science and Technology Innovation Project of Improving Food Yield and Efficiency Project[2017YFD0300301] ; Science and Technology Innovation Project of Improving Food Yield and Efficiency Project[2017YFA0604700] ; Science and Technology Innovation Project of Improving Food Yield and Efficiency Project[2016YFD0300201] ; National Natural Science Foundation of China[41977405] ; National Natural Science Foundation of China[41571493] ; National Natural Science Foundation of China[41571088] ; National Natural Science Foundation of China[31561143003] ; State Key Laboratory of Earth Surface Processes and Resource Ecology
WOS关键词	INDUCED CHLOROPHYLL FLUORESCENCE ; PAST 3 DECADES ; CROP YIELD ; CLIMATE-CHANGE ; WINTER-WHEAT ; NEURAL-NETWORKS ; GRAIN WEIGHT ; MODIS LST ; RICE ; REGIONS
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000515391700021
资助机构	Science and Technology Innovation Project of Improving Food Yield and Efficiency Project ; National Natural Science Foundation of China ; State Key Laboratory of Earth Surface Processes and Resource Ecology
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/132973]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhang, Zhao
作者单位	1.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 2.Beijing Normal Univ, Fac Geog Sci, State Key Lab Earth Surface Proc & Resource Ecol, Key Lab Environm Change & Nat Hazards, Beijing 100875, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Liangliang,Zhang, Zhao,Luo, Yuchuan,et al. Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches[J]. REMOTE SENSING,2020,12(1):20.
APA	Zhang, Liangliang,Zhang, Zhao,Luo, Yuchuan,Cao, Juan,&Tao, Fulu.(2020).Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches.REMOTE SENSING,12(1),20.
MLA	Zhang, Liangliang,et al."Combining Optical, Fluorescence, Thermal Satellite, and Environmental Data to Predict County-Level Maize Yield in China Using Machine Learning Approaches".REMOTE SENSING 12.1(2020):20.