V14B-03
Eruption Forecasting in Alaska: A Retrospective and Test of the Distal VT Model

Monday, 14 December 2015: 16:30
308 (Moscone South)
Stephanie G Prejean1, Jeremy D Pesicek1, Jay Wellik1, Cheryl Cameron2, Randall A White3, Wendy A McCausland4 and Helena Buurman5, (1)USGS Volcano Disaster Assistance Program, Anchorage, AK, United States, (2)State of Alaska, Fairbanks, AK, United States, (3)USGS, Menlo Park, CA, United States, (4)U.S.Geological Survey, Vancouver, WA, United States, (5)University of Alaska Fairbanks, Fairbanks, AK, United States
Abstract:
United States volcano observatories have successfully forecast most significant US eruptions in the past decade. However, eruptions of some volcanoes remain stubbornly difficult to forecast effectively using seismic data alone. The Alaska Volcano Observatory (AVO) has responded to 28 eruptions from 10 volcanoes since 2005. Eruptions that were not forecast include those of frequently active volcanoes with basaltic-andesite magmas, like Pavlof, Veniaminof, and Okmok volcanoes.

In this study we quantify the success rate of eruption forecasting in Alaska and explore common characteristics of eruptions not forecast. In an effort to improve future forecasts, we re-examine seismic data from eruptions and known intrusive episodes in Alaska to test the effectiveness of the distal VT model commonly employed by the USGS-USAID Volcano Disaster Assistance Program (VDAP). In the distal VT model, anomalous brittle failure or volcano-tectonic (VT) earthquake swarms in the shallow crust surrounding the volcano occur as a secondary response to crustal strain induced by magma intrusion. Because the Aleutian volcanic arc is among the most seismically active regions on Earth, distinguishing distal VT earthquake swarms for eruption forecasting purposes from tectonic seismicity unrelated to volcanic processes poses a distinct challenge. In this study, we use a modified beta-statistic to identify pre-eruptive distal VT swarms and establish their statistical significance with respect to long-term background seismicity. This analysis allows us to explore the general applicability of the distal VT model and quantify the likelihood of encountering false positives in eruption forecasting using this model alone.