Discrimination of the degree of heavy metal pollution in corn leaves in mining areas based on semi-supervised learning

To assess the degree of heavy metal pollution in crops, this study focused on crop leaves subjected to varying levels of heavy metal copper (Cu) stress. After removing outliers and applying smoothing techniques, the spectral data underwent derivative (D) and multiplicative scatter correction (MSC). Competitive adaptive reweighted sampling (CARS) and specific spectral ranges (SSR) were employed to extract the feature bands. Six different combinations of data preprocessing methods were utilized. This model incorporates the semi-supervised learning method, which enables the reduction of time and cost associated with annotating large-scale data. It addresses the identification problem when the labelled data is limited. Finally, the eXtreme Gradient Boosting algorithm (XGBoost) is used to select the best model and discriminate the degree of heavy metal pollution in corn. The D-CARS-XGBoost model achieved an accuracy rate exceeding 98%.