Estimation of Agronomic Characters of Wheat Based on Variable Selection and Machine Learning Algorithms

Wheat is one of the most important food crops in the world, and its high and stable yield is of great significance for ensuring food security. Timely, non-destructive, and accurate monitoring of wheat growth information is of great significance for optimizing cultivation management, improving fertilizer utilization efficiency, and improving wheat yield and quality. Different color indices and vegetation indices were calculated based on the reflectance of the wheat canopy obtained by a UAV remote sensing platform equipped with a digital camera and a hyperspectral camera. Three variable-screening algorithms, namely competitive adaptive re-weighted sampling (CARS), iteratively retains informative variables (IRIVs), and the random forest (RF) algorithm, were used to screen the acquired indices, and then three regression algorithms, namely gradient boosting decision tree (GBDT), multiple linear regression (MLR), and random forest regression (RFR), were used to construct the monitoring models of wheat aboveground biomass (AGB) and leaf nitrogen content (LNC), respectively. The results showed that the three variable-screening algorithms demonstrated different performances for different growth indicators, with the optimal variable-screening algorithm for AGB being RF and the optimal variable-screening algorithm for LNC being CARS. In addition, using different variable-screening algorithms results in more vegetation indices being selected than color indices, and it can effectively avoid autocorrelation between variables input into the model. This study indicates that constructing a model through variable-screening algorithms can reduce redundant information input into the model and achieve a better estimation of growth parameters. A suitable combination of variable-screening algorithms and regression algorithms needs to be considered when constructing models for estimating crop growth parameters in the future.