[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119195-en":3,"doc-seo-119195-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},119195,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Analysis of geochemical characteristics of rocks using machine learning methods","This study classifies rock types by leveraging machine learning models built on geochemical composition data. The work uses measurements of elemental and oxide contents in rocks, aiming to predict rock type from chemical characteristics. Four algorithms are compared: decision tree, logistic regression, random forest, and gradient boosting. Results indicate the random forest achieves the highest classification accuracy (0.832612), supported by its capacity to model diverse features and their interactions. Correlation analysis further reveals meaningful relationships among geochemical variables, emphasizing careful model selection for accurate interpretation.","Analysis of geochemical characteristics of rocks using machine learning methods  \nKsenia Degtyareva1,2*, Oksana Kukartseva2, Vadim Tynchenko1,2, Timofey Mariupolskiy1, and Denis Pereverzev3  \n1Reshetnev Siberian State University of Science and Technology, 660037 Krasnoyarsk, Russia  \n2Bauman Moscow State Technical University, 105005 Moscow, Russia  \n3Siberian Federal University, 660041 Krasnoyarsk, Russia  \nAbstract. This work is devoted to the classification of rock types based on their geochemical characteristics using machine learning methods. The study used data on the content of various elements in rocks to develop classification models. Four methods were investigated and compared:  \ndecision tree, logistic regression, random forest and gradient boosting. The results showed that the random forest model demonstrates the highest classification accuracy (0.832612), which is explained by its ability to efficiently process a variety of features and their interactions. Correlation analysis has shown significant correlations between the geochemical characteristics of rocks, which underlines the importance of choosing appropriate machine learning methods for processing such data. This work highlights the importance of using ensemble methods that can take into account complex interactions between features for accurate classification of geochemical data and can be useful for specialists in the field of geology,  \nmining and related industries.  \n1 Introduction  \nIn the mining and energy industry, knowledge of the type of rocks, as well as their properties and characteristics, plays a key role. Determining the composition and geochemical changes in rocks allows not only to better understand their origin and evolution, but also to effectively apply this knowledge in practice. This study uses a dataset containing various geochemical properties of rocks, such as the content of SiO2, TiO2, Al2O3, Fe2O3 and other elements. The main objectives ofthis study are to develop classification models and assess their quality in order to accurately determine the type of rock based on its properties [1-6] .  \nAs part of the study, several machine learning methods were applied and compared, including decision tree, random forest, logistic regression and gradient boosting. Each of these methods has its own characteristics and advantages in the context of classification tasks. Their effectiveness was evaluated using the accuracy metric [7-10] .  \nThe purpose of this study is to compare the accuracy of various classification models and determine the most effective method for predicting the type of rock based on its geochemical properties [11-14] .  \n* Corresponding author: [sofaglu2000@mail.ru](sofaglu2000@mail.ru)  \n© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)).  \n2 Research Methods  \nThe decision tree is a simple and interpretable classification algorithm that builds a model in the form of a tree structure. During the learning process, the decision tree recursively splits the data into subsets, choosing at each node the features that ensure the best class separation. The advantage of this method is its visibility and the ability to easily interpret the results obtained. However, the decision tree is prone to overfitting, especially on small samples [15- 19] .  \nLogistic regression is a statistical method used for binary and multiclass classification. The method is based on a logistic function that allows you to model the probability of an object belonging to one of the classes. Logistic regression works well with linearly separable data and allows you to assess the importance of each feature in the model [20-22] . However, in the presence of complex nonlinear dependencies, its effectiveness may be limited.  \nA random forest is an ensemble classification me","cbCaiiJOKIkvzbJ0","https://ap.wps.com/l/cbCaiiJOKIkvzbJ0","pdf",1823348,1,6,"English","en",105,"# Abstract\n# Introduction\n# Research Methods","[{\"question\":\"What task does the study address?\",\"answer\":\"The study addresses rock-type classification using geochemical characteristics as input features.\"},{\"question\":\"Which machine learning methods were compared in the research?\",\"answer\":\"Decision tree, logistic regression, random forest, and gradient boosting were investigated and compared.\"},{\"question\":\"Why does the random forest model perform best according to the results?\",\"answer\":\"It shows the highest classification accuracy because it can efficiently handle many features and their interactions, improving predictive performance.\"}]","Analysis of geochemical characteristics of rocks using machine learning methods | PDF",1785723032,15,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"analysis-of-geochemical-characteristics-of-rocks-using-machine-learning-methods","",{"@graph":36,"@context":85},[37,54,68],{"@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/analysis-of-geochemical-characteristics-of-rocks-using-machine-learning-methods/119195/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What task does the study address?","Question",{"text":75,"@type":76},"The study addresses rock-type classification using geochemical characteristics as input features.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods were compared in the research?",{"text":80,"@type":76},"Decision tree, logistic regression, random forest, and gradient boosting were investigated and compared.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the random forest model perform best according to the results?",{"text":84,"@type":76},"It shows the highest classification accuracy because it can efficiently handle many features and their interactions, improving predictive performance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]