Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning

Seismic data recorded at industrial sites contain valuable information on anthropogenic activities. With advances in machine learning and computing power, new opportunities have emerged to explore the seismic wavefield in these complex environments. We applied two unsupervised machine learning algor...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengping Chai, Omar Marcillo, Monica Maceira, Junghyun Park, Stephen Arrowsmith, James O. Thomas, Joshua Cunningham
Format: Article
Language:English
Published: Seismological Society of America 2025-01-01
Series:The Seismic Record
Online Access:https://doi.org/10.1785/0320240046
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850235728246603776
author Chengping Chai
Omar Marcillo
Monica Maceira
Junghyun Park
Stephen Arrowsmith
James O. Thomas
Joshua Cunningham
author_facet Chengping Chai
Omar Marcillo
Monica Maceira
Junghyun Park
Stephen Arrowsmith
James O. Thomas
Joshua Cunningham
author_sort Chengping Chai
collection DOAJ
description Seismic data recorded at industrial sites contain valuable information on anthropogenic activities. With advances in machine learning and computing power, new opportunities have emerged to explore the seismic wavefield in these complex environments. We applied two unsupervised machine learning algorithms to analyze continuous seismic data collected from an industrial facility in Texas, United States. The Uniform Manifold Approximation and Projection for Dimension Reduction algorithm was used to reduce the dimensionality of the data and generate 2D embeddings. Then, the Hierarchical Density-Based Spatial Clustering of Applications with Noise method was employed to automatically group these embeddings into distinct signal clusters. Our analysis of over 1400 hr (around 59 days) of continuous seismic data revealed five and seven signal clusters at two separate stations. At both stations, we identified clusters associated with background noise and vehicle traffic, with the latter’s temporal patterns aligning closely with the facility’s work schedule. Furthermore, the algorithms detected signal clusters from unknown sources and underline the ability of unsupervised machine learning for uncovering previously unrecognized patterns. Our analysis demonstrates the effectiveness of unsupervised approaches in examining continuous seismic data without requiring prior knowledge or pre-existing labels.
format Article
id doaj-art-5db5d2258a88482ba1d9372bb46284fc
institution OA Journals
issn 2694-4006
language English
publishDate 2025-01-01
publisher Seismological Society of America
record_format Article
series The Seismic Record
spelling doaj-art-5db5d2258a88482ba1d9372bb46284fc2025-08-20T02:02:09ZengSeismological Society of AmericaThe Seismic Record2694-40062025-01-0151647210.1785/0320240046tsr2024046Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine LearningChengping Chai0https://orcid.org/0000-0002-6792-6014Omar Marcillo1Monica Maceira2https://orcid.org/0000-0003-1248-2185Junghyun Park3https://orcid.org/0000-0001-6370-6877Stephen Arrowsmith4https://orcid.org/0000-0002-9150-0363James O. Thomas5https://orcid.org/0009-0004-5802-0810Joshua Cunningham6Oak Ridge National Laboratory, Oak Ridge, Tennessee, U.S.A.Oak Ridge National Laboratory, Oak Ridge, Tennessee, U.S.A.Oak Ridge National Laboratory, Oak Ridge, Tennessee, U.S.A.Southern Methodist University, Dallas, Texas, U.S.A.Southern Methodist University, Dallas, Texas, U.S.A.Consolidated Nuclear Security, LLC, Amarillo, Texas, U.S.A.Consolidated Nuclear Security, LLC, Amarillo, Texas, U.S.A.Seismic data recorded at industrial sites contain valuable information on anthropogenic activities. With advances in machine learning and computing power, new opportunities have emerged to explore the seismic wavefield in these complex environments. We applied two unsupervised machine learning algorithms to analyze continuous seismic data collected from an industrial facility in Texas, United States. The Uniform Manifold Approximation and Projection for Dimension Reduction algorithm was used to reduce the dimensionality of the data and generate 2D embeddings. Then, the Hierarchical Density-Based Spatial Clustering of Applications with Noise method was employed to automatically group these embeddings into distinct signal clusters. Our analysis of over 1400 hr (around 59 days) of continuous seismic data revealed five and seven signal clusters at two separate stations. At both stations, we identified clusters associated with background noise and vehicle traffic, with the latter’s temporal patterns aligning closely with the facility’s work schedule. Furthermore, the algorithms detected signal clusters from unknown sources and underline the ability of unsupervised machine learning for uncovering previously unrecognized patterns. Our analysis demonstrates the effectiveness of unsupervised approaches in examining continuous seismic data without requiring prior knowledge or pre-existing labels.https://doi.org/10.1785/0320240046
spellingShingle Chengping Chai
Omar Marcillo
Monica Maceira
Junghyun Park
Stephen Arrowsmith
James O. Thomas
Joshua Cunningham
Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
The Seismic Record
title Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
title_full Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
title_fullStr Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
title_full_unstemmed Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
title_short Exploring Continuous Seismic Data at an Industry Facility Using Unsupervised Machine Learning
title_sort exploring continuous seismic data at an industry facility using unsupervised machine learning
url https://doi.org/10.1785/0320240046
work_keys_str_mv AT chengpingchai exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT omarmarcillo exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT monicamaceira exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT junghyunpark exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT stephenarrowsmith exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT jamesothomas exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning
AT joshuacunningham exploringcontinuousseismicdataatanindustryfacilityusingunsupervisedmachinelearning