EuroMineNet: A Multitemporal Sentinel-2 Benchmark for Spatiotemporal Mining Footprint Analysis in the European Union (2015-2024)

TL;DR

EuroMineNet delivers a decade-long, multitemporal benchmark for mining footprint mapping and monitoring in the European Union using Sentinel-2 data (2015–2024). It introduces two tasks—annual multitemporal footprint mapping and cross-temporal change detection—and the Change-Aware Temporal IoU (CA-TIoU) metrics to assess temporal consistency. Benchmarking 11 semantic segmentation and 20 change-detection models reveals that transformer-based backbones excel in per-year accuracy and temporal coherence, but short-term dynamics remain difficult to detect robustly. The dataset, with 51,330 patches across 133 sites, enables robust, scalable assessments of spatiotemporal mining dynamics and supports policy, environmental governance, and ESG-oriented monitoring at continental scales.

Abstract

Mining activities are essential for industrial and economic development, but remain a leading source of environmental degradation, contributing to deforestation, soil erosion, and water contamination. Sustainable resource management and environmental governance require consistent, long-term monitoring of mining-induced land surface changes, yet existing datasets are often limited in temporal depth or geographic scope. To address this gap, we present EuroMineNet, the first comprehensive multitemporal benchmark for mining footprint mapping and monitoring based on Sentinel-2 multispectral imagery. Spanning 133 mining sites across the European Union, EuroMineNet provides annual observations and expert-verified annotations from 2015 to 2024, enabling GeoAI-based models to analyze environmental dynamics at a continental scale. It supports two sustainability-driven tasks: (1) multitemporal mining footprint mapping for consistent annual land-use delineation, evaluated with a novel Change-Aware Temporal IoU (CA-TIoU) metric, and (2) cross-temporal change detection to capture both gradual and abrupt surface transformations. Benchmarking 20 state-of-the-art deep learning models reveals that while GeoAI methods effectively identify long-term environmental changes, challenges remain in detecting short-term dynamics critical for timely mitigation. By advancing temporally consistent and explainable mining monitoring, EuroMineNet contributes to sustainable land-use management, environmental resilience, and the broader goal of applying GeoAI for social and environmental good. We release the codes and datasets by aligning with FAIR and the open science paradigm at https://github.com/EricYu97/EuroMineNet.

Figures (7)

• Figure 1: Geospatial distribution of the 133 mining sites investigated in this study. The study area of the European Union is highlighted.
• Figure 2: Samples of EuroMineNet benchmark. The evolution of each mining site is demonstrated in a color map from 2015 to 2024.
• Figure 3: Multitemporal Earth observation data from Nástup-Tušimice Coal Mine in Czechia from 2015 (top-left) to 2024 (bottom-right). Only optical bands are demonstrated for visualization.
• Figure 4: Overall of the EuroMineNet benchmark, consisting of two tasks of mining footprint monitoring and mapping. The mining footprint mapping focuses on the accurate mapping from a single observation by semantic segmentation models, while the mining footprint monitoring focuses on the identification of spatial-temporal variations triggered by the mining activities by change detection models. Only RGB bands are demonstrated for visualization.
• Figure 5: Illustration of cross-temporal change detection. We investigate the mining changes from different starting years with dynamic interval years across the whole period of the last decade. As a result, we obtained a total of $C_{10}^{2}=45$ bitemporal pairs for mining footprint monitoring from each scene.