[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291224-105":59,"doc-detail-291224-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","prediction-of-asphalt-rheological-properties-for-paving-and-maintenance-assistance-using-explainable-machine-learning","Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning","","Conventional frequency–temperature sweep testing of asphalt rheological properties is time-consuming and resource-intensive. This study builds predictive models that connect asphalt chemical composition with rheological behavior by using functional-group features from Fourier Transform Infrared Spectroscopy (FTIR) as inputs, and complex modulus (|G*|) and phase angle (δ) from a Dynamic Shear Rheometer (DSR) as outputs. Five machine learning algorithms are tuned via Bayesian optimization, then interpreted with SHAP to reveal key oxygen-containing functional groups. The optimized XGBoost model attains R2 values of 0.9998 for |G*| and 0.9999 for δ, enabling reliable performance evaluation with reduced experimental effort.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/prediction-of-asphalt-rheological-properties-for-paving-and-maintenance-assistance-using-explainable-machine-learning/291224/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/prediction-of-asphalt-rheological-properties-for-paving-and-maintenance-assistance-using-explainable-machine-learning/291224.png","ImageObject",300,407,{"name":92,"@type":93},"Ophelia","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why are predictive models for asphalt rheological properties needed?","Question",{"text":113,"@type":114},"Conventional rheological testing across full temperature and frequency ranges is time-consuming and resource-intensive, motivating data-driven alternatives.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What data sources and target variables are used in the study?",{"text":118,"@type":114},"FTIR measurements provide eleven functional-group input features, while the models predict |G*| and phase angle δ obtained from DSR.",{"name":120,"@type":111,"acceptedAnswer":121},"Which explainability method helps interpret model predictions?",{"text":122,"@type":114},"SHapley Additive exPlanations (SHAP) values are used to explain the underlying drivers of the predictions, highlighting key functional-group relationships.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291224,1789643801,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","Fuel 396 (2025) 135319  \nContents lists available at ScienceDirect  \nFuel  \njournal [homepage:](homepage: www.elsevier.com/locate/fuel)[ www.elsevier.com/locate/fuel](homepage: www.elsevier.com/locate/fuel)  \n| Full Length Article\u003Cbr>Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning\u003Cbr>Fan Zhang a, Augusto Cannone Falchettoa,b, Di Wanga,c, Zhenkun Lia,*, Yuxuan Suna, Weiwei Lina\u003Cbr>a Department of Civil Engineering, Aalto University, Rakentajanaukio 4, 02150 Espoo, Finland\u003Cbr>b Department of Civil Environmental and Architectural Engineering, University of Padova, Via Marzolo 9, 35131 Padova, Italy c Department of Civil Engineering, University of Ottawa, 800 King Edward Ave, Ottawa, ON K1N 6N5, Canada |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Asphalt binders\u003Cbr>Rheological properties Chemical composition Explainable machine learning SHAP |  | Conventional frequency-temperature sweep tests for evaluating asphalt rheological properties are timeconsuming and resource-intensive. The characterization efficiency can be significantly improved by establishing a robust predictive model that links rheological properties to chemical composition. To this end, this study investigates the correlation between asphalt’s chemical and rheological properties and develops precise predictive models using machine learning techniques. The input features include eleven key functional groups measured by Fourier Transform Infrared Spectroscopy (FTIR), while the output variables are the complex modulus (|G*|) and phase angle (δ) from Dynamic Shear Rheometer (DSR). Five machine learning algorithms—multiple linear regression, support vector regression, artificial neural network, random forest, and eXtreme gradient boosting (XGBoost)—were utilized to construct the predictive models. A Bayesian optimization strategy was employed to fine-tune their hyperparameters. Laboratory findings revealed that a strong correlation was identified between changes in these functional groups, especially oxygen-containing functional groups, and the |G*| and δ values of asphalt binders. The optimized XGBoost model achieved exceptional predictive accuracy, with R2 values of 0.9998 for |G*| and 0.9999 for δ. Additionally, SHapley Additive exPlanations (SHAP) values were used to elucidate the underlying principles of the predictions. By leveraging FTIR data and rheological indicators, this work provides a novel data-driven approach to accurately estimate asphalt binder behaviour, reducing experimental effort while ensuring reliable performance evaluation. |\n\n1. Introduction  \nAsphalt properties such as adhesion, rheology, fatigue, etc. are critical to the life of the pavement [1,2]. Rheological properties, among them, determine the deformation behaviour of asphalt binders and directly affect the overall performance of the pavement. The rheological properties of asphalt binders reflect their viscoelastic characteristics and exhibit different mechanical behaviours at different temperatures and loading conditions [3,4]. Changes in these properties are closely linked to pavement distress such as rutting, fatigue, and cracking [5–7]. For instance, rutting is more likely to occur at high temperatures when the viscous component of the binder dominates. Therefore, understanding rheological properties is essential for preventing pavement distress and extending the service life of asphalt pavements. By adjusting the composition, modification technology and optimising the material ratio,  \nthe rheological properties of asphalt can be improved and its adaptability under different environmental conditions can be enhanced.  \nTesting of asphalt rheological properties, however, is usually timeconsuming, with full-temperature and full-frequency tests usually taking several days to complete. For this reason, researchers have attempted to analyze the factors affecting rheological prop","cbCaiog8c7K1OqtV","https://ap.wps.com/l/cbCaiog8c7K1OqtV","pdf",8537701,15,"English","# Introduction\n## Asphalt rheology and pavement performance\n## Chemical composition and predictive modeling\n## Study motivation and research limitations","[{\"question\":\"Why are predictive models for asphalt rheological properties needed?\",\"answer\":\"Conventional rheological testing across full temperature and frequency ranges is time-consuming and resource-intensive, motivating data-driven alternatives.\"},{\"question\":\"What data sources and target variables are used in the study?\",\"answer\":\"FTIR measurements provide eleven functional-group input features, while the models predict |G*| and phase angle δ obtained from DSR.\"},{\"question\":\"Which explainability method helps interpret model predictions?\",\"answer\":\"SHapley Additive exPlanations (SHAP) values are used to explain the underlying drivers of the predictions, highlighting key functional-group relationships.\"}]","Prediction of asphalt rheological properties for paving and maintenance assistance using explainable machine learning | PDF",38]