[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120194-en":3,"doc-seo-120194-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120194,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Applying Machine Learning for Seismic Interpretation - Master of Philosophy Thesis","Seismic interpretation is a time-consuming and challenging workflow in geophysics, so this thesis applies machine learning to improve efficiency and reliability. Interpretation focuses on pre-stack seismic data, supported by prior rock physics relationships that create learnable patterns in seismic responses. A two-stage pipeline is developed: pseudo wells generate post-stack and pre-stack synthetic seismic traces, then a neural network detects layer boundaries from these traces. Two architectures, a convolutional neural network and dense neurons, are benchmarked against deconvolution using TP/TN/FP/FN-weighted performance metrics.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n• This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n• A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n• This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n• The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n• When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nApplying Machine Learning for Seismic Interpretation  \nMohammed Benalshaikh  \nMaster of Philosophy  \nThe University of Edinburgh School of Geoscience  \n2022  \nContents  \n1 Introduction 1  \n2 Methods and Theory 6  \n2.1 Reflectivity and AVO ......................... 6  \n2.2 Convolution Model .......................... 10  \n2.3 Rock Physics and Empirical Relations ............... 11  \n2.4 Machine Learning ........................... 13  \n2.5 Related Applications of Machine Learning ............. 20  \n2.6 Implementation in Python ...................... 20  \n3 Pseudo Wells 26  \n3.1 Create Blocky Models ........................ 27  \n3.2 Adding Noise ............................. 28  \n3.3 Build Pseudo Well Structure ..................... 30  \n3.4 Generate Synthetic Seismic ...................... 34  \n4 Application to Layer Boundary Detection 37  \n4.1 Methodology ............................. 38  \n4.2 Comparing Results .......................... 49  \n4.3 Predicting Thinner Layers ...................... 58  \n4.4 Additional Intermediate Layer Thicknesses ............. 67  \n4.5 CNN Results Summary ........................ 72  \n4.6 AVO Curves .............................. 80  \nCONTENTS iii  \n5 Predicting Lithologies 83  \n5.1 Methodology ............................. 83  \n5.2 Results ................................. 91  \n5.3 Lessons Learned and Suggestions .................. 93  \n6 Discussion 96  \n6.1 Research Assumptions ........................ 96  \n6.2 Significance of Findings ........................ 99  \n6.3 Future Work .............................. 101  \n6.4 Computational Aspects ........................ 102  \n7 Conclusions 103  \nBibliography 106  \niv CONTENTS  \nAbstract  \nSeismic interpretation can be a time-consuming and challenging process for geophysicists, and in this thesis, we investigate how to utilise machine learning techniques to address these challenges. Most seismic data interpretation happens on the post-stack seismic data; however, we would like to interpret the pre-stack seismic data because it is more informative than post-stack seismic data. We also want to use the prior knowledge of rock physics relationships between different rocks. These rock physics relationships give rise to patterns in the seismic data that perhaps can be learned by the machine learning algorithm. In this thesis, we approach these problems of seismic interpretation with a two-stage process. Firstly, we compute pseudo wells and their associated post-stack and pre-stack synthetic seismic traces. Secondly, we set up a neural network algorithm to detect layer boundaries from the post-stack and pre-stack synthetic seismic traces. We showed two methods of interpreting seismic data using different neural network architectures: the convolutional neural network and the dense neurons. We compared the neural network methods against the commonly known deconvolution method. We evaluated the performance of the layer boundary prediction methods using performance measures that take into account different weighting for the True-Positives TP, True-Negatives TN, False-Positives FP and False-Ne","cbCaibklQGvRYQWi","https://ap.wps.com/l/cbCaibklQGvRYQWi","pdf",18929787,1,122,"English","en",105,"# Introduction\n# Methods and Theory\n## Reflectivity and AVO\n## Convolution Model\n## Rock Physics and Empirical Relations\n## Machine Learning\n## Related Applications of Machine Learning\n## Implementation in Python\n# Pseudo Wells\n## Create Blocky Models\n## Adding Noise\n## Build Pseudo Well Structure\n## Generate Synthetic Seismic\n# Application to Layer Boundary Detection\n## Methodology\n## Comparing Results\n## Predicting Thinner Layers\n## Additional Intermediate Layer Thicknesses\n## CNN Results Summary\n## AVO Curves\n# Predicting Lithologies\n## Methodology\n## Results\n## Lessons Learned and Suggestions\n# Discussion\n## Research Assumptions\n## Significance of Findings\n## Future Work\n## Computational Aspects\n# Conclusions","[{\"question\":\"What problem does the thesis address in seismic interpretation?\",\"answer\":\"It targets the time-consuming and difficult nature of seismic interpretation by leveraging machine learning to detect subsurface geological features more effectively.\"},{\"question\":\"How does the proposed two-stage approach work?\",\"answer\":\"First, pseudo wells produce associated post-stack and pre-stack synthetic seismic traces. Second, a neural network uses these synthetic traces to detect layer boundaries.\"},{\"question\":\"Which neural network performs best and under what conditions?\",\"answer\":\"The convolutional neural network is the most favorable method, achieving about 96.5%–99.8% interface prediction in noise-free, thicker layered data, while performance degrades with noise, reduced acoustic impedance contrast, or thinner layers.\"}]","Applying Machine Learning for Seismic Interpretation - Master of Philosophy Thesis | PDF",1785728653,307,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"applying-machine-learning-for-seismic-interpretation-master-of-philosophy-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/applying-machine-learning-for-seismic-interpretation-master-of-philosophy-thesis/120194/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address in seismic interpretation?","Question",{"text":76,"@type":77},"It targets the time-consuming and difficult nature of seismic interpretation by leveraging machine learning to detect subsurface geological features more effectively.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed two-stage approach work?",{"text":81,"@type":77},"First, pseudo wells produce associated post-stack and pre-stack synthetic seismic traces. Second, a neural network uses these synthetic traces to detect layer boundaries.",{"name":83,"@type":74,"acceptedAnswer":84},"Which neural network performs best and under what conditions?",{"text":85,"@type":77},"The convolutional neural network is the most favorable method, achieving about 96.5%–99.8% interface prediction in noise-free, thicker layered data, while performance degrades with noise, reduced acoustic impedance contrast, or thinner layers.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]