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

Abstract

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.

Modified Red Blue Vegetation Index for Chlorophyll Estimation and Yield Prediction of Maize from Visible Images Captured by UAV

“…Thus, the results may be influenced by the background such as soil and other disturbances even though methods had been adopted to eliminate the impacts [ 39 , 50 , 51 ]. Thus, the integrated VI calculated from UAV RGB images acquired at important growth stages of maize can reflect more precisely the temporal dynamic changes of growth conditions, which can achieve the highest precision for yield prediction [ 52 , 53 ].…”

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

“…In CART, information gain, Gini Diversity Index (GDI) and gain ratio are used to split the attributes. RF is a powerful tool for the prediction of yield, which has been applied to agricultural research [46] [42] [53] [56] [24]. It generates a wide range of regression trees that are produced by a large set of decision trees for computing regression [75].…”

“…Irrigation ratio [46], number of open wells (OW) [26] [41], number of tanks (TK) [ [40], GDD [24], growing degree days [46], killing degree days [46], day length [51] [13] [43], snow water [13], drought index (DI) [ [66], GCVI [50], VOD [46] [62], RVI [63] [39], GNDVI [63] [39], GRVI [63] [39], EVI2 [63], OSAVI [63] [39], WDRVI [63] [39], NDVIre [64], TSAVI [39], IPVI [39], MSAVI [39], GI [39], PVI [39], SAVI [39]], GESAVI [39], GLAI [39], CWSI [39], NDWI [39], GVI [39] LAI [42] [40] [65], FPAR [42], GPP [42], NIRv [56] [47], CDL [42], cropland census [42], satellite images from the landsat thematic mapper (TM) [42], satellite images from advanced wide field sensor (AWIFS) [42], empty-land [45], harrowed land [45], texture conditions [48], PVI [48].…”

“…Besides these, many classification and regression algorithms have successfully been utilized in crop yield prediction and these algorithms include [46] [26] have also been employed in crop yield prediction. The key characteristics, benefits and drawbacks of widely utilized crop yield prediction algorithms [42] are briefly tabulated in Table 3.…”

Crop lodging detection and susceptibility mapping: a multi-sensor approach

“…This is achieved by weighing the outcome of the model at an instant t based on the outcome of the previous model at instant t-1 and capitalizing on the error. XGB simplifies the objective functions by combining the training loss and regularization terms to prevent overfitting (Zhang et al, 2020). The training loss measures the predictive capability of the model with regard to the training data while the regularization term accounts for the model complexity.…”