Yonatan Garkebo Doyoro, Samuel Kebede Gelena, Chih-Ping Lin
{"title":"Improving subsurface structural interpretation in complex geological settings through geophysical imaging and machine learning","authors":"Yonatan Garkebo Doyoro, Samuel Kebede Gelena, Chih-Ping Lin","doi":"10.1016/j.enggeo.2024.107839","DOIUrl":null,"url":null,"abstract":"This study employs seismic refraction tomography (SRT) and electrical resistivity tomography (ERT) to assess subsurface geological conditions along the proposed Porsgrunn Highway in Norway. The primary objective is to analyze SRT and ERT tomograms to identify subsurface geological structures. However, interpreting tomograms is often limited by smoothed boundaries and reduced resolution. To address these challenges, we apply <ce:italic>k</ce:italic>-means clustering, a machine learning technique that groups data based on similarities in physical properties, to post-process the geophysical tomograms. This study pioneers the use of <ce:italic>k</ce:italic>-means clustering to interpret tomograms from SRT and ERT data in complex geological settings. We first evaluate the effectiveness of clustering techniques using numerical modeling for two geological scenarios: a horizontally layered case and a layered case with undulation and a fault structure. Utilizing automated methods (Elbow and Silhouette), we objectively determine the optimal number of clusters for each geophysical tomogram. Subsequently, we compare the performance of the <ce:italic>k</ce:italic>-means clustering algorithm with subjective expert interpretations and the Laplacian edge detection method. Borehole data validate the clustering results and confirm the effectiveness of optimal cluster selection techniques. The findings of this study demonstrate that <ce:italic>k</ce:italic>-means clustering significantly enhances the detection of geological structures by establishing clearer boundaries and minimizing noise interference, enabling more accurate fault zone delineation. Compared to traditional edge detection and subjective interpretation methods, <ce:italic>k</ce:italic>-means clustering offers a systematic and objective approach that improves consistency and reliability across diverse geological settings. Moreover, its automated classification of geophysical data into meaningful clusters enables efficient analysis of large datasets. This study underscores the value of integrating machine learning techniques with geophysical methods such as SRT and ERT to improve interpretability and accurately identify subsurface geological structures, particularly in fault zone identification.","PeriodicalId":11567,"journal":{"name":"Engineering Geology","volume":"5 1","pages":""},"PeriodicalIF":6.9000,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Geology","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1016/j.enggeo.2024.107839","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}
引用次数: 0
Abstract
This study employs seismic refraction tomography (SRT) and electrical resistivity tomography (ERT) to assess subsurface geological conditions along the proposed Porsgrunn Highway in Norway. The primary objective is to analyze SRT and ERT tomograms to identify subsurface geological structures. However, interpreting tomograms is often limited by smoothed boundaries and reduced resolution. To address these challenges, we apply k-means clustering, a machine learning technique that groups data based on similarities in physical properties, to post-process the geophysical tomograms. This study pioneers the use of k-means clustering to interpret tomograms from SRT and ERT data in complex geological settings. We first evaluate the effectiveness of clustering techniques using numerical modeling for two geological scenarios: a horizontally layered case and a layered case with undulation and a fault structure. Utilizing automated methods (Elbow and Silhouette), we objectively determine the optimal number of clusters for each geophysical tomogram. Subsequently, we compare the performance of the k-means clustering algorithm with subjective expert interpretations and the Laplacian edge detection method. Borehole data validate the clustering results and confirm the effectiveness of optimal cluster selection techniques. The findings of this study demonstrate that k-means clustering significantly enhances the detection of geological structures by establishing clearer boundaries and minimizing noise interference, enabling more accurate fault zone delineation. Compared to traditional edge detection and subjective interpretation methods, k-means clustering offers a systematic and objective approach that improves consistency and reliability across diverse geological settings. Moreover, its automated classification of geophysical data into meaningful clusters enables efficient analysis of large datasets. This study underscores the value of integrating machine learning techniques with geophysical methods such as SRT and ERT to improve interpretability and accurately identify subsurface geological structures, particularly in fault zone identification.
期刊介绍:
Engineering Geology, an international interdisciplinary journal, serves as a bridge between earth sciences and engineering, focusing on geological and geotechnical engineering. It welcomes studies with relevance to engineering, environmental concerns, and safety, catering to engineering geologists with backgrounds in geology or civil/mining engineering. Topics include applied geomorphology, structural geology, geophysics, geochemistry, environmental geology, hydrogeology, land use planning, natural hazards, remote sensing, soil and rock mechanics, and applied geotechnical engineering. The journal provides a platform for research at the intersection of geology and engineering disciplines.