Estimating Reclaimed Grass Aboveground Biomass of Reclaimed Mining Area Across Spatial and Temporal Scales With Sentinel-1 and Sentinel-2 Data

Mining activities destroy vegetation and soil systems, posing a serious threat to ecological security. Reclamation is considered to be an effective and sustainable strategy for improving postmining ecological quality and ecosystem function. Monitoring aboveground biomass (AGB) in reclaimed mining areas is crucial for assessing and managing reclamation. The combination of remote sensing and machine learning algorithms is widely used for regional-scale AGB estimation. However, the feasibility of this approach for assessing AGB in reclaimed mine sites still remains poorly understood. In this study, we employed a variety of data sources (Sentinel-1, Sentinel-2, and their combinations) and coupled them with diverse regression algorithms (including the linear model, LMR; support vector regression (SVR); random forest, RF; and cubist, CB) to estimate herbaceous AGB in typical reclaimed mining areas of Sichuan Province, China. Moreover, we evaluated the temporal–spatial generalizability of the model by training and validating it across distinct geographic regions and time periods. The results showed that 1) with regard to the aspects of model accuracy and stability, the SVR model employing the combination of MSI and SAR data is a superior approach for estimating the AGB of reclaimed mines at the Sentinel scale (RMSE = 90.367 g/m2, R ${^{\textrm {2} }} =0.597$ , and mean absolute error (MAE) = 59.721 g/m2). 2) The most informative SAR metric for estimating AGB is VV. The spectral information from the visible (VIS), red-edge, and shortwave infrared (SWIR) regions is of considerable importance, with significant contributions from both water and soil-adjusted indices. 3) Integration of Sentinel optical and SAR datasets helps to improve AGB estimation for reclaimed mining area grass. 4) The models demonstrated suboptimal performance in temporal and spatial cross-validation (CV), exhibiting limited temporal–spatial generalizability. The proposed framework in this study has great potential to generate robust grass AGB for reclaimed mining areas across regions and time scales. In addition, it provides valuable insights for dynamically guiding the recovery and monitoring of restored ecosystems.