The effective identification of reclaimed vegetation species is important for the subsequent management of ecological restoration projects in mining areas. Hyperspectral remote sensing has been used for identifying vegetation species. However, few studies have focused on mine-reclaimed vegetation. Even if there are studies in this field, the methods used by the researches are mainly traditional discriminant analyses. The environmental conditions of reclaimed mining areas lead to significant intraclass spectral differences in reclaimed vegetation, and there is uncertainty in the identification of reclaimed vegetation species using traditional classification models. In this study, in situ hyperspectral data were used to analyze the spectral variation in the reclaimed vegetation canopy in mine restoration areas and evaluate their potential in the identification of reclaimed vegetation species. We measured the canopy spectral reflectance of five vegetation species in the study area using the ASD FieldSpec 4. The spectral characteristics of vegetation canopy were analyzed by mathematically transforming the original spectra, including Savitzky–Golay smoothing, first derivative, reciprocal logarithm, and continuum removal. In addition, we calculated indicators for identifying vegetation species using mathematically transformed hyperspectral data. The metrics were submitted to a feature selection procedure (recursive feature elimination) to optimize model performance and reduce its complexity. Different classification algorithms (regularized logistic regression, back propagation neural network, support vector machines with radial basis function kernel, and random forest) were constructed to explore optimal procedures for identifying reclaimed vegetation species based on the best feature metrics. The results showed that the separability between the spectra of reclaimed vegetation can be improved by applying different mathematical transformations to the spectra. The most important spectral metrics extracted by the recursive feature elimination (RFE) algorithm were related to the visible and near-infrared spectral regions, mainly in the vegetation pigments and water absorption bands. Among the four identification models, the random forest had the best recognition ability for reclaimed vegetation species, with an overall accuracy of 0.871. Our results provide a quantitative reference for the future exploration of reclaimed vegetation mapping using hyperspectral 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 post-mining 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 Machines, 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, R² = 0.597, 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, 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. Additionally, it provides valuable insights for dynamically guiding the recovery and monitoring of restored ecosystems.