Large-scale demonstration of machine learning for the detection of volcanic deformation in Sentinel-1 satellite imagery
Problem
Radar satellites systematically image over 1000 volcanoes, but detecting deformation signals requires manual inspection of huge datasets, delaying timely eruption information.
Why it matters
Timely detection of volcanic deformation can characterise magmatic systems and potentially forecast eruptions, protecting lives.
What the AI did
Machine learning was applied to automatically processed Sentinel-1 satellite images to detect volcanic deformation signals across a global five-year dataset.
Results
~600,000 images of >1000 volcanoes processed (2015-2020); detection threshold 5.9 cm (1.2 cm/year); of 16 most-flagged volcanoes: 5 eruptions, 6 slow deformation, 2 non-volcanic, 3 atmospheric artefacts.
Impact
Demonstrates ML can screen global satellite data for volcanic deformation while exposing limitations such as atmospheric artefacts.
Record
| Venue | Bulletin of Volcanology |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Juliet Biggs, Nantheera Anantrasirichai, F. Albino, Milan Lazecký, Yasser Maghsoudi |
| Citations | 31 (OpenAlex, at import time) |
| References | 55 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1007/s00445-022-01608-x |
| Open access | hybrid |
| Keywords | machine learning, volcanic deformation, Sentinel-1, SAR imagery, eruption detection |
Importance rating
significant — thousands to millions affected
Abstract quantifies global scope: ~600,000 images of >1000 volcanoes over 5 years; timely deformation detection can characterise magmatic systems and potentially forecast eruptions, protecting lives, though routine use needs tailored processing.
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
|