[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128072-en":3,"doc-seo-128072-105":31,"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":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},128072,5909887254083,"Miles","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Predictive Modeling of Pavement Rutting Using Machine Learning Techniques","This master’s thesis applies machine learning to improve prediction of pavement deterioration, with a specific focus on rutting in pavement management contexts. Advanced models including Random Forests, Decision Trees, Gradient Boosting, and Artificial Neural Networks are evaluated, showing significant gains in predictive accuracy. The study emphasizes that data quality and feature selection are decisive, particularly accurate maintenance records and careful handling of data inconsistencies. Refined models better represent real maintenance actions and achieve improved performance metrics such as MAE of 1.17 and R2 of 0.81, supporting proactive, data-driven pavement management.","MASTER’S THESIS  \nPREDICTIVE MODELING OF PAVEMENT RUTTING USING MACHINE LEARNING TECHNIQUES  \nS M Zahid Hasan  \nMaster’s Degree in Intelligent Systems (MUSI)  \nSpecialization in Computer Vision.  \nCentre for Postgraduate Studies  \nAcademic year 2023/24  \nPredictive Modeling of Pavement Rutting Using Machine Learning Techniques  \nS M Zahid Hasan  \nTutor: Cristina Suemay Manresa Yee, Stavros Syrigos  \nThesis of the Master’s degree in Intelligent Systems (MUSI) University of the Balearic Islands, 07122 Palma, Illes Balears, Spain [zahid.hasan.0109@gmail.com](zahid.hasan.0109@gmail.com)  \nAbstract—Este Trabajo Final de Máster (TFM) explora la aplicación de técnicas de aprendizaje automático (ML) para mejorar la predicción del deterioro del pavimento, centrándose particularmente en los surcos o rodadas dentro de los sistemas de gestión de pavimentos. Utilizando modelos avanzados de ML como Random Forests, Árboles de Decisión, Gradient Boosting y Redes Neuronales Artificiales, el estudio ha demostrado mejorassignificativas en la precisión predictiva. La investigación destaca el papel fundamental de la calidad de los datos y la selecciónde características, revelando que los registros de mantenimientoprecisos y el manejo cuidadoso de las inconsistencias de datos son fundamentales para optimizar el rendimiento del modelo. En particular en este trabajo, los modelos se perfeccionaron para reflejar las actividades de mantenimiento reales con mayor precisión, resultando en mejores métricas de rendimiento como un Error Absoluto Medio (MAE) de 1.17 y un R2 de 0.81. Este TFM remarca el potencial de ML para transformar las estrategias tradicionales de gestión de pavimentos en enfoques proactivos y basados en datos, allanando el camino para futuras investigaciones para perfeccionar aún más los modelos predictivos y ampliar su aplicabilidad.  \nABSTRACT  \nThis thesis explores the application of machine learning (ML) techniques to enhance the prediction of pavement deterioration, particularly focusing on rutting within pavement management systems. Utilizing advanced ML models such as Random Forests, Decision Trees, Gradient Boosting, and Artificial Neural Networks, the study has demonstrated significant improvements in predictive accuracy. The research highlighted the critical role of data quality and feature selection, revealing that accurate maintenance records and careful handling of data inconsistencies are pivotal for optimizing model performance. Notably, models were refined to reflect true maintenance activities more accurately, resulting in enhanced performance metrics such as a Mean Absolute Error (MAE) of 1.17 and an R2 of 0 .81. This thesis underscores the potential of ML to transform traditional pavement management strategies into proactive, data-driven approaches, paving the way for future research to further refine predictive models and extend their applicability.  \nIndex Terms—Machine Learning, Pavement Prediction, Rutting Analysis, Feature Importance, Random Forests, Decision Trees, Neural Networks  \nI. INTRODUCTION  \nA. Background and Context  \nModern societies rely heavily on roads to facilitate the efficient transportation of goods and services, operating as the arteries of economic and social exchanges. Road infrastructure management must be done well in order to maximize accessibility, reduce transportation costs, and guarantee safety. On the other hand, maintaining of road pavements is a costly project that consumes a large amount of national and public funds allocated to infrastructure development [21, 38] .  \nRutting and cracking caused by deteriorating pavement posea constant threat to preserve the quality and safety of roads. Figure 1 illustrates the visible effects of rutting on a highway surface, showcasing the indentations formed due to repetitive traffic load. The complex behaviors of pavement under dynamic environmental and load conditions are frequently ignored by traditional management systems, which are mostly rea","cbCaiiCrK8o5xanL","https://ap.wps.com/l/cbCaiiCrK8o5xanL","pdf",3748241,3,1,16,"English","en",105,"# Introduction\n## Background and Context\n## Problem Statement","[{\"question\":\"Which machine learning models are used to predict pavement rutting?\",\"answer\":\"The study uses Random Forests, Decision Trees, Gradient Boosting, and Artificial Neural Networks to enhance rutting prediction accuracy.\"},{\"question\":\"What factors most strongly influence model performance?\",\"answer\":\"Data quality and feature selection are highlighted as critical, especially accurate maintenance records and careful treatment of data inconsistencies.\"},{\"question\":\"What performance results are reported for the refined models?\",\"answer\":\"The refined models report improved metrics, including a Mean Absolute Error (MAE) of 1.17 and an R2 value of 0.81.\"}]","Predictive Modeling of Pavement Rutting Using Machine Learning Techniques | PDF",1785944669,40,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"predictive-modeling-of-pavement-rutting-using-machine-learning-techniques","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/predictive-modeling-of-pavement-rutting-using-machine-learning-techniques/128072/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","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},"Which machine learning models are used to predict pavement rutting?","Question",{"text":76,"@type":77},"The study uses Random Forests, Decision Trees, Gradient Boosting, and Artificial Neural Networks to enhance rutting prediction accuracy.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What factors most strongly influence model performance?",{"text":81,"@type":77},"Data quality and feature selection are highlighted as critical, especially accurate maintenance records and careful treatment of data inconsistencies.",{"name":83,"@type":74,"acceptedAnswer":84},"What performance results are reported for the refined models?",{"text":85,"@type":77},"The refined models report improved metrics, including a Mean Absolute Error (MAE) of 1.17 and an R2 value of 0.81.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":30,"slug":119},7,"Healthcare","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":107,"slug":138},19,"General","general"]