Társilo Girona

2 months ago | nature.com | Alberto Ardid |David Frank Dempsey |Corentin Caudron |Shane J. Cronin |Ben Kennedy |Társilo Girona | +4 more

AbstractSeismic data recorded before volcanic eruptions provides important clues for forecasting. However, limited monitoring histories and infrequent eruptions restrict the data available for training forecasting models. We propose a transfer machine learning approach that identifies eruption precursors—signals that consistently change before eruptions—across multiple volcanoes.