• Login
    View Item 
    •   Home
    • University of Alaska Fairbanks
    • UAF Graduate School
    • Geosciences
    • View Item
    •   Home
    • University of Alaska Fairbanks
    • UAF Graduate School
    • Geosciences
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of Scholarworks@UACommunitiesPublication DateAuthorsTitlesSubjectsTypeThis CollectionPublication DateAuthorsTitlesSubjectsType

    My Account

    Login

    First Time Submitters, Register Here

    Register

    Statistics

    Display statistics

    Automatic classification of volcanic earthquakes using multi-station waveforms and dynamic neural networks

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Bruton_uaf_0006N_10145.pdf
    Size:
    6.716Mb
    Format:
    PDF
    Download
    Author
    Bruton, Christopher Patrick
    Chair
    West, Michael
    Committee
    Tape, Carl
    Freymueller, Jeffrey
    Metadata
    Show full item record
    URI
    http://hdl.handle.net/11122/4538
    Abstract
    Earthquakes and seismicity have long been used to monitor volcanoes. In addition to the time, location, and magnitude of an earthquake, the characteristics of the waveform itself are important. For example, low-frequency or hybrid type events could be generated by magma rising toward the surface. A rockfall event could indicate a growing lava dome. Classification of earthquake waveforms is thus a useful tool in volcano monitoring. A procedure to perform such classification automatically could flag certain event types immediately, instead of waiting for a human analyst's review. Inspired by speech recognition techniques, we have developed a procedure to classify earthquake waveforms using artificial neural networks. A neural network can be "trained" with an existing set of input and desired output data; in this case, we use a set of earthquake waveforms (input) that has been classified by a human analyst (desired output). After training the neural network, new sets of waveforms can be classified automatically as they are presented. Our procedure uses waveforms from multiple stations, making it robust to seismic network changes and outages. The use of a dynamic time-delay neural network allows waveforms to be presented without precise alignment in time, and thus could be applied to continuous data or to seismic events without clear start and end times. We have evaluated several different training algorithms and neural network structures to determine their effects on classification performance. We apply this procedure to earthquakes recorded at Mount Spurr and Katmai in Alaska, and Uturuncu Volcano in Bolivia. The procedure can successfully distinguish between slab and volcanic events at Uturuncu, between events from four different volcanoes in the Katmai region, and between volcano-tectonic and long-period events at Spurr. Average recall and overall accuracy were greater than 80% in all three cases.
    Description
    Thesis (M.S.) University of Alaska Fairbanks, 2014
    Table of Contents
    Chapter 1. Introduction -- 1.1. Motivation -- 1.2. Background -- Chapter 2. Methods -- 2.1. Defining a Classification Problem -- 2.2. Time-delay Neural Networks -- 2.3. Preparing a Dataset -- 2.4. Spectrograms and Targets -- 2.5. Neural Networks -- 2.6. Post-processing -- 2.7. Classification Performance -- Chapter 3. Data and Results -- 3.1. Uturuncu -- 3.1.1. Data Description and Event Types -- 3.1.2. Classifier Parameters -- 3.1.3. Performance and Remarks -- 3.2. Katmai -- 3.2.1. Data Description and Event Types -- 3.2.2. Classifier Parameters -- 3.2.3. Performance and Remarks -- 3.3. Spurr -- 3.3.1. Data Description and Event Types -- 3.3.2. Classifier Parameters -- 3.3.3. Performance and Remarks -- Chapter 4. Discussion -- 4.1. Application to Real-Time Monitoring -- 4.2. Neuron Weight Analysis -- 4.2.1. Interpretation of Uturuncu Hinton Diagram -- 4.3. Source and Path Effect Considerations -- 4.4. Alignment Errors in Training Data -- 4.5. Numerical Class Output -- 4.6. Role of Continuous Waveform Input -- Chapter 5. Conclusions -- Appendix -- A.1. Classification Performance -- A.1.1. True and False Positives and Negatives -- A.1.2. Accuracy -- A.1.3. Precision, Recall, and F-score -- A.2. Balancing Training Data -- A.3. Training Error Function -- A.4. Training Algorithm -- A.5. Neural Network Structure -- A.6. Neuron Activation Function -- References.
    Date
    2014-05
    Type
    Thesis
    Collections
    Geosciences

    entitlement

     
    ABOUT US|HELP|BROWSE|ADVANCED SEARCH

    The University of Alaska Fairbanks is an affirmative action/equal opportunity employer and educational institution and is a part of the University of Alaska system.

    ©UAF 2013 - 2023 | Questions? ua-scholarworks@alaska.edu | Last modified: September 25, 2019

    Open Repository is a service operated by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.