Ergodic seismic precursors and transfer learning for short term eruption forecasting at data scarce volcanoes
Open Access
- 25 February 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Abstract
Seismic 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. Using seismic data from 41 eruptions at 24 volcanoes over 73 years, our approach forecasts eruptions at unobserved (out-of-sample) volcanoes. Tested without data from the target volcano, the model demonstrated accuracy comparable to direct training on the target and exceeded benchmarks based on seismic amplitude. These results indicate that eruption precursors exhibit ergodicity, sharing common patterns that allow observations from one group of volcanoes to approximate the behavior of others. This approach addresses data limitations at individual sites and provides a useful tool to support monitoring efforts at volcano observatories, improving the ability to forecast eruptions and mitigate volcanic risks.Keywords
All Related Versions
Funding Information
- Ministry for Business Innovation and Employment (E7774, E7370)
This publication has 69 references indexed in Scilit:
- Large-scale demonstration of machine learning for the detection of volcanic deformation in Sentinel-1 satellite imageryBulletin of Volcanology, 2022
- Seismic precursors to the Whakaari 2019 phreatic eruption are transferable to other eruptions and volcanoesNature Communications, 2022
- Insights into the 9 December 2019 eruption of Whakaari/White Island from analysis of TROPOMI SO 2 imageryScience Advances, 2021
- Time-series forecasting with deep learning: a surveyPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2021
- Automatic precursor recognition and real-time forecasting of sudden explosive volcanic eruptions at Whakaari, New ZealandNature Communications, 2020
- Forecasting the Eruption of an Open‐Vent Volcano Using Resonant Infrasound TonesGeophysical Research Letters, 2018
- Global link between deformation and volcanic eruption quantified by satellite imageryNature Communications, 2014
- A route to more tractable expert adviceNature, 2010
- Ergodicity in natural earthquake fault networksPhysical Review E, 2007
- An empirical investigation of bias and variance in time series forecasting: modeling considerations and error evaluationIEEE Transactions on Neural Networks, 2003