en
Scientific article
Open access
English

Understanding causality and uncertainty in volcanic observations: An example of forecasting eruptive activity on Soufrière Hills Volcano, Montserrat

Published inJournal of Volcanology and Geothermal Research, vol. 341, p. 287-300
Publication date2017
Abstract

Following a cessation in eruptive activity it is important to understand how a volcano will behave in the future and when it may next erupt. Such an assessment can be based on the volcano's long-term pattern of behaviour and insights into its current state via monitoring observations. We present a Bayesian network that integrates these two strands of evidence to forecast future eruptive scenarios using expert elicitation. The Bayesian approach provides a framework to quantify the magmatic causes in terms of volcanic effects (i.e., eruption and unrest). In October 2013, an expert elicitation was performed to populate a Bayesian network designed to help forecast future eruptive (in-)activity at Soufrière Hills Volcano. The Bayesian network was devised to assess the state of the shallow magmatic system, as a means to forecast the future eruptive activity in the context of the long-term behaviour at similar dome-building volcanoes. The findings highlight coherence amongst experts when interpreting the current behaviour of the volcano, but reveal considerable ambiguity when relating this to longer patterns of volcanism at dome-building volcanoes, as a class. By asking questions in terms of magmatic causes, the Bayesian approach highlights the importance of using short-term unrest indicators from monitoring data as evidence in long-term forecasts at volcanoes. Furthermore, it highlights potential biases in the judgements of volcanologists and identifies sources of uncertainty in terms of magmatic causes rather than scenario-based outcomes.

Keywords
  • Bayesian network
  • Expert elicitation
  • Eruption forecasting
  • Uncertainty
  • Evidence synthesis
  • Causal inference
Citation (ISO format)
SHELDRAKE, Thomas Edward et al. Understanding causality and uncertainty in volcanic observations: An example of forecasting eruptive activity on Soufrière Hills Volcano, Montserrat. In: Journal of Volcanology and Geothermal Research, 2017, vol. 341, p. 287–300. doi: 10.1016/j.jvolgeores.2017.06.007
Main files (1)
Article (Published version)
Identifiers
ISSN of the journal0377-0273
824views
155downloads

Technical informations

Creation08/24/2017 11:08:00 AM
First validation08/24/2017 11:08:00 AM
Update time03/15/2023 1:57:08 AM
Status update03/15/2023 1:57:08 AM
Last indexation02/12/2024 11:28:01 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack