Industrial activities induce various impacts on ecosystems that influence species richness and distribution. An effective way to assess the resulting impacts on biodiversity lies in vegetation mapping. Species classification achieved through supervised machine learning algorithms at the pixel level has shown promising results using hyperspectral images and multispectral, multitemporal images. This study aims to determine whether airborne hyperspectral images with a high spatial resolution or phenological information obtained by spaceborne multispectral time series (Sentinel-2) are suitable to discriminate species and assess biodiversity in a complex impacted context. The industrial heritage of the study site has indeed induced high spatial heterogeneity in terms of stressors and species over a reduced scale. First, vegetation indices, derivative spectra, continuum removed spectra, and components provided by three feature extraction techniques, namely, Principal Component Analysis, Minimal Noise Fraction, and Independent Component Analysis, were calculated from reflectance spectra. These features were then analyzed through Sequential Floating Feature Selection. Supervised classification was finally performed using various machine learning algorithms (Random Forest, Support Vector Machines, and Regularized Logistic Regression) considering a probability-based rejection approach. Biodiversity metrics were derived from resulted maps and analyzed considering the impacts. Average Overall Accuracy (AOA) reached up to 94% using the hyperspectral image and Regularized Logistic Regression algorithm, whereas the time series of multispectral images never exceeded 72% AOA. From all tested spectral transformations, only vegetation indices applied to the time series of multispectral images increased the performance. The results obtained with the hyperspectral image degraded to the specifications of Sentinel-2 emphasize the importance of fine spatial and spectral resolutions to achieve accurate mapping in this complex context. While no significant difference was found between impacted and reference sites through biodiversity metrics, vegetation mapping highlighted some differences in species distribution.

Ore processing is a source of soil heavy metal pollution. Vegetation traits (structural characteristics such as spatial cover and repartition; biochemical parameters—pigment and water contents, growth rate, phenological cycle…) and plant species identity are indirect and powerful indicators of residual contamination detection in soil. Multi-temporal multispectral satellite imagery, such as the Sentinel-2 time series, is an operational environment monitoring system widely used to access vegetation traits and ensure vegetation surveillance across large areas. For this purpose, methodology based on a multi-temporal fusion method at the feature level is applied to vegetation monitoring for several years from the closure and revegetation of an ore processing site. Features are defined by 26 spectral indices from the literature and seasonal and annual change detection maps are inferred. Three indices—CI_red-edge (CIREDEDGE), IRECI (Inverted Red-Edge Chlorophyll Index) and PSRI (Plant Senescence Reflectance Index)—are particularly suitable for detecting changes spatially and temporally across the study area. The analysis is conducted separately for phyto-stabilized vegetation zones and natural vegetation zones. Global and specific changes are emphasized and explained by information provided by the site operator or meteorological conditions.