BIROn - Birkbeck Institutional Research Online

    A little data goes a long way: automating seismic phase arrival picking at Nabro Volcano with transfer learning

    Lapins, S. and Goitom, B. and Kendall, J.-M. and Werner, M.J. and Cashman, K.V. and Hammond, James O.S. (2021) A little data goes a long way: automating seismic phase arrival picking at Nabro Volcano with transfer learning. Journal of Geophysical Research: Solid Earth 126 (7), e2021JB021910. ISSN 0148-0227.

    [img]
    Preview
    Text
    2021JB021910.pdf - Published Version of Record
    Available under License Creative Commons Attribution.

    Download (4MB) | Preview

    Abstract

    Supervised deep learning models have become a popular choice for seismic phase arrival detection. However, they do not always perform well on out-of-distribution data and require large training sets to aid generalization and prevent overfitting. This can present issues when using these models in new monitoring settings. In this work, we develop a deep learning model for automating phase arrival detection at Nabro volcano using a limited amount of training data (2,498 event waveforms recorded over 35 days) through a process known as transfer learning. We use the feature extraction layers of an existing, extensively trained seismic phase picking model to form the base of a new all-convolutional model, which we call U-GPD. We demonstrate that transfer learning reduces overfitting and model error relative to training the same model from scratch, particularly for small training sets (e.g., 500 waveforms). The new U-GPD model achieves greater classification accuracy and smaller arrival time residuals than off-the-shelf applications of two existing, extensively-trained baseline models for a test set of 800 event and noise waveforms from Nabro volcano. When applied to 14 months of continuous Nabro data, the new U-GPD model detects 31,387 events with at least four P-wave arrivals and one S-wave arrival, which is more than the original base model (26,808 events) and our existing manual catalog (2,926 events), with smaller location errors. The new model is also more efficient when applied as a sliding window, processing 14 months of data from seven stations in less than 4 h on a single graphics processing unit.

    Metadata

    Item Type: Article
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Natural Sciences
    Depositing User: James Hammond
    Date Deposited: 21 Jul 2021 18:18
    Last Modified: 02 Aug 2023 18:11
    URI: https://eprints.bbk.ac.uk/id/eprint/45241

    Statistics

    Activity Overview
    6 month trend
    126Downloads
    6 month trend
    129Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item
    Edit/View Item