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

Tom E Sheldrake, W.P. Aspinall, Henry M Odbert, Geoff Wadge, R S J Sparks

Research output: Contribution to journalArticle (Academic Journal)peer-review

8 Citations (Scopus)
346 Downloads (Pure)

Abstract

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.
Original languageEnglish
Pages (from-to)287-300
Number of pages14
JournalJournal of Volcanology and Geothermal Research
Volume341
Early online date8 Jun 2017
DOIs
Publication statusPublished - 15 Jul 2017

Keywords

  • Bayesian network
  • Expert elicitation
  • Eruption forecasting
  • Uncertainty
  • Evidence synthesis
  • Causal inference

Fingerprint

Dive into the research topics of 'Understanding causality and uncertainty in volcanic observations: An example of forecasting eruptive activity on Soufrière Hills Volcano, Montserrat'. Together they form a unique fingerprint.
  • CREDIBLE (Revision of FEC id 120483)

    Wagener, T.

    1/09/1230/09/17

    Project: Research

Cite this