Multisource remote sensing and ensemble learning for multidimensional monitoring of heavy metals on mine surfaces.

This study aims to establish monitoring models for surface heavy metals in mining areas by utilizing multi-source remote sensing data and ensemble learning algorithms. By collecting heavy metal content data from soil and crop leaves within the study area, and combining it with data obtained from the Google Earth Engine platform, including Landsat 8, Sentinel-2 spectral data, vegetation indices, and VV and VH polarization information from Sentinel-1, along with terrain factors derived from the Digital Elevation Model such as elevation, hillshade, slope, and aspect, a total of 43 feature indicators were consolidated. Feature importance ranking (FI) and the successive projections algorithm (SPA) feature selection method were employed to filter feature factors, selecting different features for each type of heavy metal. In the soil, the optimal model for predicting Cr and Cd content is AdaBoost-MT, while the optimal model for inverting Zn, As, Hg, and Pb content is FISPA-AdaBoost-MT. In the crops, the optimal model for predicting the content of all six heavy metals is FISPA-AdaBoost-MT. This indicates that the combination of FI and SPA features effectively evaluates the heavy metal content in both soil and crops. Utilizing these multidimensional features, this study combines ensemble learning algorithms with multi-target regression techniques to construct inversion models for six types of heavy metals (Cr, Zn, As, Cd, Hg, and Pb) simultaneously. Based on the optimal prediction models, distribution maps of heavy metals in soil and crops within the study area were generated, achieving comprehensive, multidimensional monitoring of surface heavy metals in mining areas through overlay display.