Probabilistic, Multi‐Sensor Eruption Forecasting

Abstract We developed an eruption forecasting model using data from multiple sensors or data streams with the Bayesian network method. The model generates probabilistic forecasts that are interpretable and resilient against sensor outage. We applied the model at Whakaari/White Island, an andesite is...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Behr, A. Christophersen, C. Miller
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2024GL112029
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849243686943064064
author Y. Behr
A. Christophersen
C. Miller
author_facet Y. Behr
A. Christophersen
C. Miller
author_sort Y. Behr
collection DOAJ
description Abstract We developed an eruption forecasting model using data from multiple sensors or data streams with the Bayesian network method. The model generates probabilistic forecasts that are interpretable and resilient against sensor outage. We applied the model at Whakaari/White Island, an andesite island volcano off the coast of New Zealand, using seismic tremor recordings, earthquake rate, and CO2, SO2, and H2S emission rates. At Whakaari/White Island, our model shows increases in eruption probability months to weeks prior to the three explosive eruptions that were recorded between 2013 and 2019. Our model outperforms the use of any of the data sets alone as an indicator for impending eruptions. Although developed for Whakaari/White Island, our model can be easily adapted to other volcanoes, complementing existing forecasting methods that rely on single data streams.
format Article
id doaj-art-af5018ddfe5f4400a11332d39b4fc0a4
institution Kabale University
issn 0094-8276
1944-8007
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-af5018ddfe5f4400a11332d39b4fc0a42025-08-20T03:59:22ZengWileyGeophysical Research Letters0094-82761944-80072025-04-01528n/an/a10.1029/2024GL112029Probabilistic, Multi‐Sensor Eruption ForecastingY. Behr0A. Christophersen1C. Miller2Wairakei Research Center GNS Science Taupo New ZealandGNS Science Lower Hutt New ZealandWairakei Research Center GNS Science Taupo New ZealandAbstract We developed an eruption forecasting model using data from multiple sensors or data streams with the Bayesian network method. The model generates probabilistic forecasts that are interpretable and resilient against sensor outage. We applied the model at Whakaari/White Island, an andesite island volcano off the coast of New Zealand, using seismic tremor recordings, earthquake rate, and CO2, SO2, and H2S emission rates. At Whakaari/White Island, our model shows increases in eruption probability months to weeks prior to the three explosive eruptions that were recorded between 2013 and 2019. Our model outperforms the use of any of the data sets alone as an indicator for impending eruptions. Although developed for Whakaari/White Island, our model can be easily adapted to other volcanoes, complementing existing forecasting methods that rely on single data streams.https://doi.org/10.1029/2024GL112029Bayesian networkeruption forecastingWhakaariWhite Island
spellingShingle Y. Behr
A. Christophersen
C. Miller
Probabilistic, Multi‐Sensor Eruption Forecasting
Geophysical Research Letters
Bayesian network
eruption forecasting
Whakaari
White Island
title Probabilistic, Multi‐Sensor Eruption Forecasting
title_full Probabilistic, Multi‐Sensor Eruption Forecasting
title_fullStr Probabilistic, Multi‐Sensor Eruption Forecasting
title_full_unstemmed Probabilistic, Multi‐Sensor Eruption Forecasting
title_short Probabilistic, Multi‐Sensor Eruption Forecasting
title_sort probabilistic multi sensor eruption forecasting
topic Bayesian network
eruption forecasting
Whakaari
White Island
url https://doi.org/10.1029/2024GL112029
work_keys_str_mv AT ybehr probabilisticmultisensoreruptionforecasting
AT achristophersen probabilisticmultisensoreruptionforecasting
AT cmiller probabilisticmultisensoreruptionforecasting