Mapping lava flows at Etna Volcano using Google Earth Engine, open-access satellite data, and machine learning

Estimating eruptive parameters is fundamental to assess the volcanic hazards posed to the community living at the edge of active volcanoes. Here, we analyzed satellite remote sensing data by using machine learning unsupervised and supervised techniques and analytical approaches, i.e., mathematical-physics and statistics formulations, to map lava flows emitted during the long sequences of short-lived, violent eruptions occurred at Etna volcano between December 2020 and March 2021. Satellite observations allowed to follow the evolution of eruptions thanks to their capability to survey large areas with frequent revisit time and accurate spatial resolution. We quantified the areal coverage of lava flows, the lava effusion rates, and the volumes of lava erupted. The algorithms for estimating the lava flow extents are implemented in Google Earth Engine platform. Results show the advantages of jointly using a variety of satellite sensors (optical and radar) to quantify lava flows. We demonstrate that machine learning algorithms combined with analytical approaches improved the accuracy and reliability of lava flow mapping.