Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization
Seismology and ocean acoustics are important remote sensing tools, enabling observation of environments that are difficult to access and directly measure. Seismic and ocean acoustic remote sensing are data-intensive tasks, and the proliferation of remote sensing systems has led to the generation of...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | English |
Published: |
eScholarship, University of California
2023
|
Subjects: | |
Online Access: | https://escholarship.org/uc/item/26p4w53f |
id |
ftcdlib:oai:escholarship.org:ark:/13030/qt26p4w53f |
---|---|
record_format |
openpolar |
spelling |
ftcdlib:oai:escholarship.org:ark:/13030/qt26p4w53f 2024-02-11T09:56:43+01:00 Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization Jenkins II, William Frost Gerstoft, Peter 2023-01-01 https://escholarship.org/uc/item/26p4w53f en eng eScholarship, University of California qt26p4w53f https://escholarship.org/uc/item/26p4w53f public Artificial intelligence Acoustics Geophysics Bayesian optimization Clustering Deep learning Gaussian process Geoacoustic inversion Unsupervised learning etd 2023 ftcdlib 2024-01-15T19:06:29Z Seismology and ocean acoustics are important remote sensing tools, enabling observation of environments that are difficult to access and directly measure. Seismic and ocean acoustic remote sensing are data-intensive tasks, and the proliferation of remote sensing systems has led to the generation of vast amounts of data. Meanwhile, advances in machine learning (ML) techniques and computational capacity have yielded state-of-the-art methodologies for processing and analyzing large seismic and acoustic data sets. This dissertation presents two ML-based paradigms for the characterization of environments using seismic and acoustic data.First, unsupervised ML is demonstrated for automatically identifying dominant types of seismicity present data recorded from a 34-station broadband seismic array deployed on the Ross Ice Shelf (RIS), Antarctica from 2014 to 2017. The data set contains signals generated by glaciological processes that have been used to monitor the integrity and dynamics of ice shelves. Deep clustering automatically groups these signals into classes without the need for manual labeling, enabling comparison of potential source mechanisms with not only the spatial and temporal distributions of the signals but also their characteristics. The method learns the salient features of spectrograms and encodes them into a lower-dimensional latent representation using an autoencoder, a type of deep neural network. Two clustering methods are applied to the latent data and compared: a Gaussian mixture model (GMM) and deep-embedded clustering (DEC). Dominant types of seismic signals are identified and compared with environmental data such as temperature, wind speed, tides, and sea ice concentration. The highest seismicity occurred at the RIS front during the 2016 El Niño summer, and diurnally near grounding zones throughout the deployment.The second paradigm presents Bayesian optimization (BO) as a method for efficiently estimating geoacoustic parameters within a fixed computational budget. An objective function is ... Thesis Antarc* Antarctica Ice Shelf Ice Shelves Ross Ice Shelf Sea ice University of California: eScholarship Ross Ice Shelf |
institution |
Open Polar |
collection |
University of California: eScholarship |
op_collection_id |
ftcdlib |
language |
English |
topic |
Artificial intelligence Acoustics Geophysics Bayesian optimization Clustering Deep learning Gaussian process Geoacoustic inversion Unsupervised learning |
spellingShingle |
Artificial intelligence Acoustics Geophysics Bayesian optimization Clustering Deep learning Gaussian process Geoacoustic inversion Unsupervised learning Jenkins II, William Frost Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
topic_facet |
Artificial intelligence Acoustics Geophysics Bayesian optimization Clustering Deep learning Gaussian process Geoacoustic inversion Unsupervised learning |
description |
Seismology and ocean acoustics are important remote sensing tools, enabling observation of environments that are difficult to access and directly measure. Seismic and ocean acoustic remote sensing are data-intensive tasks, and the proliferation of remote sensing systems has led to the generation of vast amounts of data. Meanwhile, advances in machine learning (ML) techniques and computational capacity have yielded state-of-the-art methodologies for processing and analyzing large seismic and acoustic data sets. This dissertation presents two ML-based paradigms for the characterization of environments using seismic and acoustic data.First, unsupervised ML is demonstrated for automatically identifying dominant types of seismicity present data recorded from a 34-station broadband seismic array deployed on the Ross Ice Shelf (RIS), Antarctica from 2014 to 2017. The data set contains signals generated by glaciological processes that have been used to monitor the integrity and dynamics of ice shelves. Deep clustering automatically groups these signals into classes without the need for manual labeling, enabling comparison of potential source mechanisms with not only the spatial and temporal distributions of the signals but also their characteristics. The method learns the salient features of spectrograms and encodes them into a lower-dimensional latent representation using an autoencoder, a type of deep neural network. Two clustering methods are applied to the latent data and compared: a Gaussian mixture model (GMM) and deep-embedded clustering (DEC). Dominant types of seismic signals are identified and compared with environmental data such as temperature, wind speed, tides, and sea ice concentration. The highest seismicity occurred at the RIS front during the 2016 El Niño summer, and diurnally near grounding zones throughout the deployment.The second paradigm presents Bayesian optimization (BO) as a method for efficiently estimating geoacoustic parameters within a fixed computational budget. An objective function is ... |
author2 |
Gerstoft, Peter |
format |
Thesis |
author |
Jenkins II, William Frost |
author_facet |
Jenkins II, William Frost |
author_sort |
Jenkins II, William Frost |
title |
Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
title_short |
Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
title_full |
Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
title_fullStr |
Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
title_full_unstemmed |
Listening to Ice and Ocean: Machine Learning for Seismic and Acoustic Environmental Characterization |
title_sort |
listening to ice and ocean: machine learning for seismic and acoustic environmental characterization |
publisher |
eScholarship, University of California |
publishDate |
2023 |
url |
https://escholarship.org/uc/item/26p4w53f |
geographic |
Ross Ice Shelf |
geographic_facet |
Ross Ice Shelf |
genre |
Antarc* Antarctica Ice Shelf Ice Shelves Ross Ice Shelf Sea ice |
genre_facet |
Antarc* Antarctica Ice Shelf Ice Shelves Ross Ice Shelf Sea ice |
op_relation |
qt26p4w53f https://escholarship.org/uc/item/26p4w53f |
op_rights |
public |
_version_ |
1790605254082953216 |