SMU Data Science Review

Seismology and Volcanology: Exploration of Volcanoes, Long-Periods, and Machines - Predicting Volcano Eruption Using Signature Seismic Data

Kyle Killion, Southern Methodist UniversityFollow
Rajeev Kumar, Southern Methodist UniversityFollow
Celia J. Taylor, Southern Methodist UniversityFollow
Gabriele Morra, University of Louisiana at LafayetteFollow

Abstract

Abstract. Seismo-volcanologists manually isolate and verify long-period waves and Strombolian events using seismic and acoustic waves. This is a very detailed and time-consuming process. This project is to employ machine learning algorithms to find models which locate long-period and Strombolian signatures automatically. By comparing the timing of seismic and acoustic waves, clustering techniques effectively isolated big volcanic events and aided in the further refinement of techniques to capture the hundreds of typical daily Strombolian events at Villarrica volcano. Within the research, we utilized the unsupervised machine learning environment to locate a group of signatures for customizing machine learned long-period signature detection.

Recommended Citation

Killion, Kyle; Kumar, Rajeev; Taylor, Celia J.; and Morra, Gabriele (2018) "Seismology and Volcanology: Exploration of Volcanoes, Long-Periods, and Machines - Predicting Volcano Eruption Using Signature Seismic Data," SMU Data Science Review: Vol. 1: No. 1, Article 11.
Available at: https://scholar.smu.edu/datasciencereview/vol1/iss1/11