[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124045-en":3,"doc-seo-124045-105":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},124045,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Optimizing pervious concrete with machine learning - Predicting permeability and compressive strength using artificial neural networks","This study uses machine learning to predict both hydraulic and mechanical performance of pervious concrete, addressing limitations of existing procedures that depend on labor-intensive trial-and-error experiments. A multilayer perceptron model is trained using a large dataset of 271 mixes and 3,252 experimental data points. The workflow evaluates 22,246 network configurations and applies Monte Carlo cross-validation over 20 iterations with four training algorithms. The optimized model yields permeability and compressive strength predictions with R2 values of 0.97 and 0.98, respectively. Sensitivity analyses confirm consistency with established pervious concrete behavior and support efficient mix-design optimization.","Construction and Building Materials 443 (2024) 137619  \nContents lists available at ScienceDirect  \nConstruction and Building Materials  \njournal [homepage: www.elsevier.com/locate/conbuildmat](homepage: www.elsevier.com/locate/conbuildmat)  \n| Optimizing pervious concrete with machine learning: Predicting\u003Cbr>permeability and compressive strength using artificial neural networks Yinglong Wu a , R. Pieralisib, F. Gersson B. Sandoval c , R.D. L´opez-Carre˜no a, d , P. Pujadas a, d, *\u003Cbr>a Department of Project and Construction Engineering, Universitat Polit`ecnica de Catalunya BarcelonaTech (UPC), Av. Diagonal 647, Barcelona 08028, Spain b Civil Engineering Studies Center (CESEC), Postgraduate Program in Civil Engineering (PPGEC), Federal University of Parana (UFPR), Curitiba, PR, Brazil c Universidad Catόlica del Norte, Departamento de Gesti´on de la Construcci´on, Angamos 0610, Antofagasta, Chile\u003Cbr>d Group of Construction Research and Innovation (GRIC), C/ Colom, 11, Ed. TR5, Terrassa, Barcelona 08222, Spain |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Artificial neural network Pervious concrete Permeability Compressive strength |  | This study makes a significant contribution to the field of pervious concrete by using machine learning to innovatively predict both mechanical and hydraulic performance. Unlike existing methods that rely on laborintensive trial-and-error experiments, our proposed approach leverages a multilayer perceptron network. To develop this approach, we compiled a comprehensive dataset comprising 271 sets and 3,252 experimental data points. Our methodology involved evaluating 22,246 network configurations, employing Monte Carlo crossvalidation over 20 iterations, and using 4 training algorithms, resulting in a total of 1,779,680 training iterations. This results in an optimized model that integrates diverse mix design parameters, enabling accurate predictions of permeability and compressive strength even in the absence of experimental data, achieving R2 values of 0.97 and 0.98, respectively. Sensitivity analyses validate the model’s alignment with established principles of pervious concrete behavior. By demonstrating the efficacy of machine learning as a complementary tool for optimizing pervious concrete mix designs, this research not only addresses current methodological limitations but also lays the groundwork for more efficient and effective approaches in the field. |\n\n1. Introduction  \nPervious concrete (PC) is typically used as the top layer in pervious pavement systems. It is a cementitious material that enables water to flow rapidly through its interconnected network of pores [1]. This porous structure creates channels that guide water efficiently to the underlying layers [2].  \nPC is composed of a mixture of Portland cement (without type restriction), coarse aggregates (of diverse mineralogical nature), and water, creating a three-phase system (solid, liquid, and air) with a final pore proportion ranging from 15 % to 30 %[3,4]. The water-to-cement ratio (w/c) typically ranges from 0.25 to 0.45, and when combined with a high aggregate-to-cement ratio, it leads to a dry concrete mix with zeroslump [3–6]. Depending on the consistency of PC, chemical additives may be added to improve the plasticity and workability of the mixture  \nDue to its porous nature, PC requires specialized mixture design considerations. An appropriate mixture proportion method should account for hydraulic and mechanical balance to meet the material’s  \nfunctional requirements, including load support and transmission (pavement functions), as well as surface runoff management (hydrological functions) [5,7]. Currently, the lack of a standardized mixture proportion method for PC makes its proper application challenging and hampers the accurate prediction of its performance.  \nOne common ACI PRC-522–23 suggests an experimental mixture proportion method that focuses on achieving the optima","cbCaivasnXvQSTJp","https://ap.wps.com/l/cbCaivasnXvQSTJp","pdf",16111950,1,17,"English","en",105,"# Introduction\n## Pervious concrete function and composition\n## Mixture proportion methods and limitations\n## Standard guidance and trial-and-error practice","[{\"question\":\"What performance indicators does the study aim to predict for pervious concrete?\",\"answer\":\"It predicts both hydraulic performance (permeability) and mechanical performance (compressive strength).\"},{\"question\":\"How is the machine learning model developed and validated?\",\"answer\":\"A multilayer perceptron network is trained with 271 mixes and 3,252 experimental data points, evaluating 22,246 configurations and using Monte Carlo cross-validation over 20 iterations with four training algorithms.\"},{\"question\":\"What accuracy does the optimized model achieve?\",\"answer\":\"It reports R2 values of 0.97 for permeability and 0.98 for compressive strength, supported by sensitivity analyses aligned with known pervious concrete behavior.\"}]","Optimizing pervious concrete with machine learning - Predicting permeability and compressive strength using artificial neural networks | PDF",1785820073,43,{"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},"optimizing-pervious-concrete-with-machine-learning-predicting-permeability-and-compressive-strength-using-artificial-neural-networks","",{"@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/optimizing-pervious-concrete-with-machine-learning-predicting-permeability-and-compressive-strength-using-artificial-neural-networks/124045/",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","2026-08-04",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 performance indicators does the study aim to predict for pervious concrete?","Question",{"text":75,"@type":76},"It predicts both hydraulic performance (permeability) and mechanical performance (compressive strength).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning model developed and validated?",{"text":80,"@type":76},"A multilayer perceptron network is trained with 271 mixes and 3,252 experimental data points, evaluating 22,246 configurations and using Monte Carlo cross-validation over 20 iterations with four training algorithms.",{"name":82,"@type":73,"acceptedAnswer":83},"What accuracy does the optimized model achieve?",{"text":84,"@type":76},"It reports R2 values of 0.97 for permeability and 0.98 for compressive strength, supported by sensitivity analyses aligned with known pervious concrete behavior.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"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":106,"slug":138},19,"General","general"]