date: 2026-04-10T12:18:11Z
pdf:PDFVersion: 1.4
pdf:docinfo:title: Machine learning for data-driven pattern recognition of seismic wind turbine emissions
xmp:CreatorTool: OUP
access_permission:can_print_degraded: true
subject: DOI: 10.1093/gji/ggag028 Geophysical Journal International, 245, 0, 22-01-2026. Abstract: Seismic emissions from wind turbines (WTs) depend on the rotation of the WT blades and the wind direction-dependent movement of the WT. Mechanical coupling between the WT foundation and the subsurface generates complex seismic wavefields, making it challenging to manually separate the contributions of different signal sources, thus complicating data labelling. We address this challenge by applying unsupervised machine learning techniques that do not require labelled data. Our analysis focuses on seismic WT emissions recorded near Wind Farm Tegelberg in the eastern Swabian Alb, Southwest Germany. Specifically, we extract time-averaged wavelet features by temporal averaging the wavelet transformation of the continuous three-component seismic data and subsequently apply the clustering algorithm Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The resulting clusters not only capture the variations in the WT rotation rate but also reveal a clear dependence on wind direction, associated with the radiation pattern of different surface waves. Our results demonstrate the potential of HDBSCAN to uncover meaningful, source-related patterns in continuous seismic records.
language: English
dc:format: application/pdf; version=1.4
pdf:docinfo:creator_tool: OUP
access_permission:fill_in_form: true
pdf:encrypted: false
dc:title: Machine learning for data-driven pattern recognition of seismic wind turbine emissions
modified: 2026-04-10T12:18:11Z
cp:subject: DOI: 10.1093/gji/ggag028 Geophysical Journal International, 245, 0, 22-01-2026. Abstract: Seismic emissions from wind turbines (WTs) depend on the rotation of the WT blades and the wind direction-dependent movement of the WT. Mechanical coupling between the WT foundation and the subsurface generates complex seismic wavefields, making it challenging to manually separate the contributions of different signal sources, thus complicating data labelling. We address this challenge by applying unsupervised machine learning techniques that do not require labelled data. Our analysis focuses on seismic WT emissions recorded near Wind Farm Tegelberg in the eastern Swabian Alb, Southwest Germany. Specifically, we extract time-averaged wavelet features by temporal averaging the wavelet transformation of the continuous three-component seismic data and subsequently apply the clustering algorithm Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The resulting clusters not only capture the variations in the WT rotation rate but also reveal a clear dependence on wind direction, associated with the radiation pattern of different surface waves. Our results demonstrate the potential of HDBSCAN to uncover meaningful, source-related patterns in continuous seismic records.
pdf:docinfo:subject: DOI: 10.1093/gji/ggag028 Geophysical Journal International, 245, 0, 22-01-2026. Abstract: Seismic emissions from wind turbines (WTs) depend on the rotation of the WT blades and the wind direction-dependent movement of the WT. Mechanical coupling between the WT foundation and the subsurface generates complex seismic wavefields, making it challenging to manually separate the contributions of different signal sources, thus complicating data labelling. We address this challenge by applying unsupervised machine learning techniques that do not require labelled data. Our analysis focuses on seismic WT emissions recorded near Wind Farm Tegelberg in the eastern Swabian Alb, Southwest Germany. Specifically, we extract time-averaged wavelet features by temporal averaging the wavelet transformation of the continuous three-component seismic data and subsequently apply the clustering algorithm Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The resulting clusters not only capture the variations in the WT rotation rate but also reveal a clear dependence on wind direction, associated with the radiation pattern of different surface waves. Our results demonstrate the potential of HDBSCAN to uncover meaningful, source-related patterns in continuous seismic records.
pdf:docinfo:creator: Gärtner Marie A., Steinmann René, Ga�ner Laura, Ritter Joachim R. R.
meta:author: Gärtner Marie A., Steinmann René, Ga�ner Laura, Ritter Joachim R. R.
meta:creation-date: 2026-02-19T18:00:18Z
created: 2026-02-19T18:00:18Z
access_permission:extract_for_accessibility: true
Creation-Date: 2026-02-19T18:00:18Z
pdf:docinfo:custom:doi: 10.1093/gji/ggag028
Author: Gärtner Marie A., Steinmann René, Ga�ner Laura, Ritter Joachim R. R.
producer: Acrobat Distiller 25.0 (Windows); modified using iTextSharp.LGPLv2.Core 3.7.4.0
pdf:docinfo:producer: Acrobat Distiller 25.0 (Windows); modified using iTextSharp.LGPLv2.Core 3.7.4.0
doi: 10.1093/gji/ggag028
pdf:unmappedUnicodeCharsPerPage: 1
dc:description: DOI: 10.1093/gji/ggag028 Geophysical Journal International, 245, 0, 22-01-2026. Abstract: Seismic emissions from wind turbines (WTs) depend on the rotation of the WT blades and the wind direction-dependent movement of the WT. Mechanical coupling between the WT foundation and the subsurface generates complex seismic wavefields, making it challenging to manually separate the contributions of different signal sources, thus complicating data labelling. We address this challenge by applying unsupervised machine learning techniques that do not require labelled data. Our analysis focuses on seismic WT emissions recorded near Wind Farm Tegelberg in the eastern Swabian Alb, Southwest Germany. Specifically, we extract time-averaged wavelet features by temporal averaging the wavelet transformation of the continuous three-component seismic data and subsequently apply the clustering algorithm Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The resulting clusters not only capture the variations in the WT rotation rate but also reveal a clear dependence on wind direction, associated with the radiation pattern of different surface waves. Our results demonstrate the potential of HDBSCAN to uncover meaningful, source-related patterns in continuous seismic records.
Keywords: 
access_permission:modify_annotations: true
dc:creator: Gärtner Marie A., Steinmann René, Ga�ner Laura, Ritter Joachim R. R.
description: DOI: 10.1093/gji/ggag028 Geophysical Journal International, 245, 0, 22-01-2026. Abstract: Seismic emissions from wind turbines (WTs) depend on the rotation of the WT blades and the wind direction-dependent movement of the WT. Mechanical coupling between the WT foundation and the subsurface generates complex seismic wavefields, making it challenging to manually separate the contributions of different signal sources, thus complicating data labelling. We address this challenge by applying unsupervised machine learning techniques that do not require labelled data. Our analysis focuses on seismic WT emissions recorded near Wind Farm Tegelberg in the eastern Swabian Alb, Southwest Germany. Specifically, we extract time-averaged wavelet features by temporal averaging the wavelet transformation of the continuous three-component seismic data and subsequently apply the clustering algorithm Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The resulting clusters not only capture the variations in the WT rotation rate but also reveal a clear dependence on wind direction, associated with the radiation pattern of different surface waves. Our results demonstrate the potential of HDBSCAN to uncover meaningful, source-related patterns in continuous seismic records.
dcterms:created: 2026-02-19T18:00:18Z
Last-Modified: 2026-04-10T12:18:11Z
dcterms:modified: 2026-04-10T12:18:11Z
title: Machine learning for data-driven pattern recognition of seismic wind turbine emissions
xmpMM:DocumentID: uuid:cd595fd3-886b-358b-be5c-cd62165a1906
Last-Save-Date: 2026-04-10T12:18:11Z
pdf:docinfo:keywords: 
pdf:docinfo:modified: 2026-04-10T12:18:11Z
meta:save-date: 2026-04-10T12:18:11Z
Content-Type: application/pdf
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Gärtner Marie A., Steinmann René, Ga�ner Laura, Ritter Joachim R. R.
dc:language: English
dc:subject: 
access_permission:assemble_document: true
xmpTPg:NPages: 22
pdf:charsPerPage: 4871
access_permission:extract_content: true
access_permission:can_print: true
meta:keyword: 
access_permission:can_modify: true
pdf:docinfo:created: 2026-02-19T18:00:18Z