[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124118-en":3,"doc-seo-124118-105":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},124118,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Automated Petrographic Image Analysis by Supervised and Unsupervised Machine Learning Methods - Study","This study applies machine learning to automate petrographic workflows, emphasizing grain segmentation and feature extraction. Two software tools are introduced: GrainSight, using a supervised deep learning model (FastSAM) for automated grain detection and morphological characterization, and PetroSeg, using unsupervised segmentation to explore rock properties and quantify porosity. GrainSight improves efficiency and accuracy versus manual methods, enabling rapid morphological feature extraction linked to depositional environments and reservoir quality. PetroSeg supports porosity estimation, mineral association identification, and textural domain characterization, advancing efficiency, objectivity, and data processing for teaching and research across geology. ","Method article  \nAutomated petrographic image analysis by supervised and unsupervised machine learning methods  \nFares Azzam* , Thomas Blaise , Benjamin Brigaud   \nUniversité Paris-Saclay, CNRS, GEOPS, 91405 Orsay, France  \n*corresponding author: Fares Azzam ([azzamfares.199@gmail.com) doi: 10.57035/journals/sdk.2024.e22.1594](azzamfares.199@gmail.com) doi: 10.57035/journals/sdk.2024.e22.1594)  \nEditors: Giovanna Della Porta and Abosede Abubakre  \nReviewers: Georgios Pantopoulos and one anonymous reviewer  \nCopyediting, layout and production: Romain Vaucher, Georgina Virgo and Faizan Sabir  \nSubmitted: 17.06.2024  \nAccepted: 07.10.2024  \nPublished: 01.11.2024  \nAbstract | This study explores the application of machine learning techniques to automate and enhance petrographic workflows, focusing on grain segmentation and feature extraction. We present two novel software tools: GrainSight, which utilizes a supervised deep learning model (FastSAM) for automated grain detection and morphological characterization; and PetroSeg, which employs an unsupervised segmentation approach to explore rock properties and calculate porosity. GrainSight application significantly improves efficiency and accuracy compared to manual methods. The FastSam model enables rapid and accurate grain detection and extraction of morphological features, which can provide insights into depositional environments, sediment routing systems, and reservoir quality. PetroSeg, on the other hand, offers an exploratory approach for porosity quantification, identification of mineral associations, and characterization of textural domains. Both methods offer unique advantages and demonstrate the potential of machine learning in petrographic analysis. Utilizing these tools has the potential to greatly enhance efficiency, objectivity, and data processing, thereby enabling new opportunities for teaching, research, and applications across multiple geological fields. The code of the two applications, GrainSight and PetroSeg, is open-source, available on GitHub and data. gouv.fr.  \nLay summary | The study of rock samples under a microscope is essential for gaining knowledge about Earth’s history and its valuable resources. However, traditional methods are slow, inefficient, and can be biased. This study presents two new computer programs, GrainSight and PetroSeg, powered by artificial intelligence, to automate and improve rock analysis. GrainSight automatically identifies the boundaries of individual grains in a rock and measures their shape, size, and other morphological parameters. This information helps scientists understand how the rock was formed and how the grains were transported. PetroSeg analyzes the distribution of minerals and empty spaces (pores) within the rock.  \nThis helps determine important properties like porosity, which is crucial for understanding how fluids, like oil and gas, flow through rocks. These user-friendly programs can significantly speed up analysis, reduce human error, and enable the study of larger datasets, leading to a more comprehensive and objective understanding of rocks and their formation processes.  \nKeywords: Petrographic analysis, Textural analysis, Grain detection, Machine learning, Image segmentation  \n1. Introduction  \nMachine learning algorithms can be broadly categorized into supervised and unsupervised learning approaches (Hastie et al., 2009; Alpaydin, 2020) . Supervised learning involves training models on labeled datasets to make predictions on new data (Hastie et al., 2009), while unsupervised learning aims to identify patterns and structures in unlabeled data without explicit guidance (Jain, 2010) . Image segmentation, which involves partitioning an  \nimage into meaningful segments or objects, is a common task in computer vision and plays an increasing role in automated petrographic analysis (Sharma & Aggarwal, 2010; Cheng et al., 2017) . Traditional image segmentation techniques, such as thresholding and edge detection (Zhan","cbCaiuJav1HjFije","https://ap.wps.com/l/cbCaiuJav1HjFije","pdf",6659891,1,12,"English","en",105,"# Introduction\n# Methods and Tools (GrainSight, PetroSeg)\n# Supervised Learning for Grain Segmentation\n# Unsupervised Learning for Rock Property Segmentation\n# Results and Comparative Performance\n# Applications, Implications, and Open-Source Availability","[{\"question\":\"What problems in traditional petrographic analysis does the study target?\",\"answer\":\"The study targets slow, inefficient, and potentially biased manual workflows, especially for tracing grain boundaries and measuring morphological features and porosity.\"},{\"question\":\"How does GrainSight perform grain detection and characterization?\",\"answer\":\"GrainSight uses a supervised deep learning model (FastSAM) to automatically detect grains and extract morphological characteristics such as shape and size.\"},{\"question\":\"What does PetroSeg do and what is it used for?\",\"answer\":\"PetroSeg uses an unsupervised segmentation approach to explore rock properties, quantify porosity, identify mineral associations, and characterize textural domains.\"}]","Automated Petrographic Image Analysis by Supervised and Unsupervised Machine Learning Methods - Study | PDF",1785820534,30,{"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},"automated-petrographic-image-analysis-by-supervised-and-unsupervised-machine-learning-methods-study","",{"@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/automated-petrographic-image-analysis-by-supervised-and-unsupervised-machine-learning-methods-study/124118/",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","2026-08-04",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 problems in traditional petrographic analysis does the study target?","Question",{"text":76,"@type":77},"The study targets slow, inefficient, and potentially biased manual workflows, especially for tracing grain boundaries and measuring morphological features and porosity.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does GrainSight perform grain detection and characterization?",{"text":81,"@type":77},"GrainSight uses a supervised deep learning model (FastSAM) to automatically detect grains and extract morphological characteristics such as shape and size.",{"name":83,"@type":74,"acceptedAnswer":84},"What does PetroSeg do and what is it used for?",{"text":85,"@type":77},"PetroSeg uses an unsupervised segmentation approach to explore rock properties, quantify porosity, identify mineral associations, and characterize textural domains.","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},[94,98,102,106,111,116,121,123,128,131,135],{"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":29,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]