[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126430-en":3,"doc-seo-126430-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126430,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning for thermal conductivity estimation from optical image","Thermal conductivity is critical for tasks such as geological disposal of spent nuclear fuel and geothermal energy, yet conventional estimation relies on lab testing or time-consuming in-situ measurements that yield limited data. This work develops faster, more cost-effective machine-learning approaches that predict thermal conductivity directly from optical image data. Using rock specimens from Olkiluoto with measured conductivity, the study describes optical acquisition, color correction and mineral-based image processing, then applies predictive modelling to map image-derived mineral features to conductivity.","Tunnelling into a Sustainable Future – Methods and Technologies – Johansson et al (Eds)© 2025 The Author(s), ISBN 978-1-032-90462-7  \n[Open Access: www.taylorfrancis.com](Open Access: www.taylorfrancis.com), CC BY-NC-ND 4.0 license  \nMachine learning for thermal conductivity estimation from optical image  \nR. Kiuru  \nOy Rock Physics Finland Ltd, Finland  \nDepartment of Civil Engineering, Aalto University, Finland  \nD.M. Wawita Widanalage Don  \nUniversity of Oulu, Oulu Mining School, Finland  \nABSTRACT: Thermal conductivity is a parameter of interest in a wide variety of applications, such as the geological final disposal of spent nuclear fuel or geothermal energy. Traditional methods for estimating thermal conductivity rely on laboratory testing or time-consuming in-situ measurements that provide at best sparse data. Thus, there exists a demand for methods that can produce reliable and comprehensive thermal conductivity data faster and more cost-effectively. This study continues to explore the possibility of predicting thermal conductivity based on optical image data using machine learning.  \n1 INTRODUCTION  \n1.1 Motivation  \nPosiva Oy is responsible for the final disposal of the spent nuclear fuel of its owners Teollisuuden Voima Oy and Fortum Power & Heat Oy. Posiva is carrying out deep geological disposal using the multiple release barriers approach (Palomäki & Ristimäki (eds.) 2013) . Some parts of the multiple barriers, namely the bentonite buffer, are likely to be somewhat sensitive to excess heat. This results in the need of thermal layout design for the repository, in order to optimise the layout and avoid any potential hot spots. This thermal design is based on solving the heat conduction equation and requires input data on, among other parameters, thermal conductivity of the rock mass.  \nSpecifically in the case of geological final disposal of spent nuclear fuel, there typically exist both pilot holes for the tunnels, imaged with optical and/or acoustic borehole imaging, as well as detailed photogrammetric models of the excavated tunnels. It is known that thermal conductivity is controlled by not only the thermal conductivities of the individual mineral components of the rock mass, but also by their structure, such as orientation, foliation, discontinuities etc. These are all parameters that are routinely evaluated based on existing imaging data. This study continues building on the work ofKiuru & Wawita Widanalage Don (2024) by exploring various additional machine learning methods, and by increasing the number of realisations run for each model.  \n1.2 Study location and geology  \nPosiva is building its final disposal facility ONKALO® on the island of Olkiluoto in Western Finland, at a depth of approximately 450 metres below ground level. Geologically Olkiluoto is dominated by a set of variably migmatised supracrustal high-grade metamorphic rocks of Paleoproterozoic age, intruded by Paleoproterozoic granitic-tonalitic plutonic rocks and granitic pegmatoids (Aaltonen et al. 2016) . As most of the rock mass shares a common origin, it has been observed that in terms of thermal conductivity, the rock mass can be treated as a single rock mass, with normally distributed thermal conductivity (Kiuru & Haapalehto 2023, Kiuru 2023) .  \nDOI: 10. 1201/9781003559047-139  \n2 METHODS  \n2.1 Image acquisition  \nA set of 200 rock specimens from Olkiluoto, with existing thermal conductivity data (Kiuru 2023), were used for this study. Thermal conductivity of the specimens has been measured using the TCi™ Thermal Conductivity Analyzer by C-Therm Technologies Ltd, which utilizes a patented modified transient plane source (MTPS) sensor (Mathis & Chandler 2004) . During the measurement, 3D-printed specimen holders were used to centralise the sensor on the specimen, resulting inexact information on the measured area. Optical data was produced by scanning the specimens using a Canon scanner. This resulted in images with 24-bit colour depth a","cbCaiu9HLN4Ahkh1","https://ap.wps.com/l/cbCaiu9HLN4Ahkh1","pdf",564964,6,1,5,"English","en",105,"# Introduction\n## Motivation\n## Study location and geology\n# Methods\n## Image acquisition\n## Image processing\n## Predictive modelling","[{\"question\":\"Why is thermal conductivity estimation important in this study?\",\"answer\":\"Thermal conductivity is required for heat conduction–based thermal design, including repository layout optimization to avoid hot spots, especially for deep geological disposal of spent nuclear fuel and geothermal applications.\"},{\"question\":\"What role do optical images play in the proposed method?\",\"answer\":\"The study predicts thermal conductivity using optical image data, leveraging optical scanning of specimens and image processing to extract mineral-related pixel information.\"},{\"question\":\"How are the images processed before modelling?\",\"answer\":\"Images are color corrected, converted to greyscale for edge contrast enhancement, specimen locations are detected and cropped, and the measured area is discretized into four main minerals using mineral identification and a decision tree classifier.\"}]","Machine learning for thermal conductivity estimation from optical image | PDF",1785905015,13,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"machine-learning-for-thermal-conductivity-estimation-from-optical-image","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/machine-learning-for-thermal-conductivity-estimation-from-optical-image/126430/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is thermal conductivity estimation important in this study?","Question",{"text":77,"@type":78},"Thermal conductivity is required for heat conduction–based thermal design, including repository layout optimization to avoid hot spots, especially for deep geological disposal of spent nuclear fuel and geothermal applications.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What role do optical images play in the proposed method?",{"text":82,"@type":78},"The study predicts thermal conductivity using optical image data, leveraging optical scanning of specimens and image processing to extract mineral-related pixel information.",{"name":84,"@type":75,"acceptedAnswer":85},"How are the images processed before modelling?",{"text":86,"@type":78},"Images are color corrected, converted to greyscale for edge contrast enhancement, specimen locations are detected and cropped, and the measured area is discretized into four main minerals using mineral identification and a decision tree classifier.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":22,"slug":138},19,"General","general"]