[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126920-en":3,"doc-seo-126920-105":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},126920,2336474459895,"Aria","https://ap-avatar.wpscdn.com/avatar/22000baeef7a5ed0655?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786071322749376916",8,"Research & Report","Machine Learning for Lithology Analysis using a Multi-Modal Approach of Integrating XRF and XCT data","The study evaluates machine learning models for classifying lithologies using X-ray fluorescence (XRF) and X-ray computed tomography (XCT) measurements. Since lithologies are often labeled over meter-scale intervals, the work augments the interval dataset by subdividing sections into 10 cm segments to create a high-resolution dataset with greatly expanded sample size. It also analyzes how adjacent lithologies influence model generalization. Results show that integrating XRF and XCT improves classification accuracy compared with XRF-only practice and XCT-only alternatives.","Machine Learning for Lithology Analysis using a Multi-Modal Approach of Integrating XRF and XCT data  \nSuraj Neelakantan 1 , Alexander Hansson2 , Jesper Norell2 , Johan Schött2 , Martin Längkvist 1 , Amy Loutfi 1  \nAbstract—We explore the use of various machine learning (ML) models for classifying lithologies utilizing data from Xray fluorescence (XRF) and X-ray computed tomography (XCT). Typically, lithologies are identified over several meters, which restricts the use of ML models due to limited training data. To address this issue, we augment the original interval dataset, where lithologies are marked over extensive sections, into finer segments of 10cm, to produce a high resolution dataset with vastly increased sample size. Additionally, we examine the impact of adjacent lithologies on building a more generalized ML model. We also demonstrate that combining XRF and XCT data leads to an improved classification accuracy compared to using only XRF data, which is the common practice in current studies, or solely relying on XCT data.  \nI. INTRODUCTION  \nDrill cores are cylindrical rock samples drilled from the earth, of which an example is shown in Figure 1. Identification and classification of e.g. different rock types and lithofacies in drill cores is an important stage of mineral exploration.  \nThe process of identifying and classifying distinguishable drill core depth ranges is often denoted as core logging [10] . Manual core logging can be inconsistent, leading to variability that complicates the development of reliable geological models [6], [10] . With the advent of new technologies for data collection from the drill cores using X-rays [1], [2], geochemical analysis can be done at a greater flexibility compared to traditional lab assays, also allowing for extraction of additional information such as 3D rock structures. X-ray fluorescence (XRF) scans are used to obtain elemental concentrations from drill cores [3] and X-ray computed tomography (XCT) scanning can give non-invasive access to the entire 3D volume of the drill core at high spatial resolution [4] . XCT data enables precise characterization of mineral grains based on density. This approach is especially useful for identifying high-density minerals such as gold, clearly differentiating them from other minerals and metals [18] . Additionally, by using 2D slices of attenuation values from 3D XCT data in machine learning (ML) algorithms, we can identify and segment euhedral minerals in the drill cores, improving our insights into geological structures [19] . Even though technology aids in collecting a vast amount of data from drill cores more efficiently, the analysis of this data still necessitates manual work and time. ML could therefore be an ideal tool for better leveraging the data at reduced manual effort.  \n1Center for Applied Autonomous Sensor Systems, Örebro University,Örebro, Sweden [firstname.lastname@oru.se](firstname.lastname@oru.se)  \n2 Orexplore AB, Torshamngatan 30B, 164 40 Kista, Stockholm, Sweden [firstname.lastname@orexplore.com](firstname.lastname@orexplore.com)  \nFig. 1: Illustration of drill core samples from a geological application arranged in a drill core tray.  \nFor example, in a study of Zn-Pb-Ag deposits in a Swedish mine [6], researchers utilized chemical compositional data obtained from XRF analysis to assess the capabilities of various ML algorithms, including Self-Organizing Maps (SOM) and Classification and Regression Trees, in the classification of rock types. Here the ML algorithms were evaluated based on ground truth given by geologists, showcasing the utility of such algorithms in geological studies. In another study on the classification of rock types [7], SOMs were again used to classify rock types based on elemental compositions. Beyond the reliance on XRF data, the integration of digital images has also been utilized, allowing for the classification of rocks through their texture and color. This approach leverages ML and con","cbCailHNNs0L969F","https://ap.wps.com/l/cbCailHNNs0L969F","pdf",597736,1,7,"English","en",105,"# Introduction\n## Core logging and geological data acquisition\n## ML for lithology classification and motivation\n# Data\n## Drill core sources and scanned datasets\n## GeoCore X10TM measurements and resolutions","[{\"question\":\"Why is lithology classification difficult with conventional ML datasets from drill cores?\",\"answer\":\"Lithologies are typically identified over several meters, which limits the number of training samples for machine learning models.\"},{\"question\":\"How does the study improve the dataset for training?\",\"answer\":\"It augments the original interval dataset by segmenting lithology-labeled sections into finer 10 cm segments, producing a high-resolution dataset with much larger sample size.\"},{\"question\":\"What effect does combining XRF and XCT data have on classification accuracy?\",\"answer\":\"Combining XRF and XCT leads to improved classification accuracy compared with using only XRF or relying solely on XCT.\"}]","Machine Learning for Lithology Analysis using a Multi-Modal Approach of Integrating XRF and XCT data | PDF",1785935667,18,{"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},"machine-learning-for-lithology-analysis-using-a-multi-modal-approach-of-integrating-xrf-and-xct-data","",{"@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/machine-learning-for-lithology-analysis-using-a-multi-modal-approach-of-integrating-xrf-and-xct-data/126920/",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","2026-08-21","2026-08-05",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},"Why is lithology classification difficult with conventional ML datasets from drill cores?","Question",{"text":76,"@type":77},"Lithologies are typically identified over several meters, which limits the number of training samples for machine learning models.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the study improve the dataset for training?",{"text":81,"@type":77},"It augments the original interval dataset by segmenting lithology-labeled sections into finer 10 cm segments, producing a high-resolution dataset with much larger sample size.",{"name":83,"@type":74,"acceptedAnswer":84},"What effect does combining XRF and XCT data have on classification accuracy?",{"text":85,"@type":77},"Combining XRF and XCT leads to improved classification accuracy compared with using only XRF or relying solely on XCT.","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},[94,98,102,106,111,116,120,123,128,131,135],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"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"]