Mapping Recent Lava Flows at Mount Etna Using Multispectral Sentinel-2 Images and Machine Learning Techniques

A novel machine learning classifier achieves high accuracy in mapping recent lava flows at Mount Etna using multispectral Sentinel-2 imagery, addressing challenges in distinguishing fresh from older lava fields. The method leverages bands 2, 3, 4, and 8 (10 m resolution) to automatically classify pixels based on reflectance properties, validated against ground measurements of 2017–2018 eruptions. This approach offers a scalable solution for monitoring hazardous volcanic events with moderate-resolution satellite data, enhancing predictive capabilities for lava flow behavior.

Corradino, C., Ganci, G., Cappello, A., Bilotta, G., Hérault, A., & Del Negro, C. (2019). Mapping Recent Lava Flows at Mount Etna Using Multispectral Sentinel-2 Images and Machine Learning Techniques. Remote Sensing, 11(16), 1916. https://doi.org/10.3390/rs11161916