Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning
Problem
Surface mines and mining tailings dams across Brazil, including unregistered ones, needed automatic identification from satellite imagery.
Why it matters
Unregistered mines and dams escape official government monitoring across vast territory.
What the AI did
Fully convolutional neural networks, trained on Sentinel-2 imagery processed in Google Earth Engine using TensorFlow 2, searched large areas for mines and tailings dams.
Results
Discovery of 263 mines lacking official mining concessions
Impact
Demonstrated a low-cost, scalable approach that located 263 previously unregistered mines in Brazil.
Record
| Venue | Sensors |
|---|---|
| Published | 2020 |
| Work type | article |
| Authors | Remis Balaniuk, Olga Isupova, Steven Reece |
| Citations | 3 (OpenAlex, at import time) |
| References | 39 |
| Model or method | fully convolutional neural networks (TensorFlow 2) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/s20236936 |
| Open access | gold |
| Keywords | deep learning, satellite imagery, tailings dams, mining detection, Sentinel-2, Brazil |
Importance rating
significant — thousands to millions affected
Abstract describes country-wide identification of illegal mines and tailings dams posing high risks to population and environment, with high social impact claimed and 263 unregistered mines found.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|