Abstract
A principal goal of volcanology is to successfully forecast the start of volcanic eruptions. This paper introduces a general forecasting method, which relies on a stream of monitoring data and a statistical description of a given threshold criterion for an eruption to start. Specifically we investigate the timing of intrusive and eruptive events at inflating volcanoes. The gradual inflation of the ground surface is a wellknown phenomenon at many volcanoes and is attributable to pressurised magma accumulating within a shallow chamber. Inflation usually culminates in a rapid deflation event caused by magma escaping from the chamber to produce a shallow intrusion and, in some cases, a volcanic eruption. We show that the ground elevation during 15 inflation periods at Krafla volcano, Iceland, increased with time towards a limiting value by following a decaying exponential with characteristic timescale τ. The available data for Krafla, Kilauea and Mauna Loa volcanoes show that the duration of inflation (t ^{⁎}) is approximately equal to τ. The distribution of t ^{⁎}/τ values follows a loglogistic distribution in which the central 60% of the data lie between 0.99<t ^{⁎}/τ<1.76. Therefore, if τ can be constrained during an ongoing inflation period, then the cumulative distribution function of t ^{⁎}/τ values calibrated from other inflation periods allows the probability of a deflation event starting during a specified time interval to be estimated. The time window in which there is a specified probability of deflation starting can also be forecast, and forecasts can be updated after each new deformation measurement. The method provides stronger forecasts than one based on the distribution of repose times alone and is transferable to other types of monitoring data and/or other patterns of preeruptive unrest.
Original language  English 

Pages (fromto)  246254 
Number of pages  9 
Journal  Earth Planetary Science Letters 
Volume  481 
Issue number  481 
Early online date  5 Nov 2017 
DOIs  
Publication status  Published  1 Jan 2018 
Keywords
 Krafla
 eruption forecasting
 conditional probability
Fingerprint Dive into the research topics of 'Forecasting deflation, intrusion and eruption at inflating volcanoes'. Together they form a unique fingerprint.
Profiles

JOAQUIN ALBERTO CORTES CARRILLO, PhD
 Geography and Geology  Senior Lecturer in Geology
Person: Academic