Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach

Abstract This study presents a data-driven framework to identify and evaluate key variables contributing to four major distresses in Continuously Reinforced Concrete Pavement (CRCP): longitudinal cracking, spalling, punchouts, and transverse cracking. A Random Forest regression approach was applied...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Alnaqbi, Ghazi G. Al-Khateeb, Waleed Zeiada, Muamer Abuzwidah
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Discover Civil Engineering
Subjects:
Online Access:https://doi.org/10.1007/s44290-025-00302-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331648784498688
author Ali Alnaqbi
Ghazi G. Al-Khateeb
Waleed Zeiada
Muamer Abuzwidah
author_facet Ali Alnaqbi
Ghazi G. Al-Khateeb
Waleed Zeiada
Muamer Abuzwidah
author_sort Ali Alnaqbi
collection DOAJ
description Abstract This study presents a data-driven framework to identify and evaluate key variables contributing to four major distresses in Continuously Reinforced Concrete Pavement (CRCP): longitudinal cracking, spalling, punchouts, and transverse cracking. A Random Forest regression approach was applied to 395 observations extracted from the Long-Term Pavement Performance (LTPP) database, incorporating structural, climatic, and traffic-related inputs. Feature importance analysis revealed that temperature, Annual Average Daily Truck Traffic (AADTT), and Layer 3 thickness consistently ranked among the top predictors across multiple distress types. Spalling was highly predictable using only a few variables (R² >0.85), whereas longitudinal and transverse cracking required more features to reach moderate accuracy, indicating complex, multifactorial mechanisms. Punchouts showed moderate predictability, influenced primarily by freeze index and heavy truck traffic. Sequential feature addition analysis confirmed that model performance improved significantly with the top-ranked variables, with diminishing returns thereafter. The proposed framework supports the development of parsimonious, interpretable models that can inform efficient CRCP design and maintenance strategies across varying environmental and operational conditions.
format Article
id doaj-art-7f8f033470a142059cffbf5d202cd938
institution Kabale University
issn 2948-1546
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Discover Civil Engineering
spelling doaj-art-7f8f033470a142059cffbf5d202cd9382025-08-20T03:46:27ZengSpringerDiscover Civil Engineering2948-15462025-08-012112010.1007/s44290-025-00302-zRandom forest-based frame work for multi-distress prediction in CRCP: a feature importance approachAli Alnaqbi0Ghazi G. Al-Khateeb1Waleed Zeiada2Muamer Abuzwidah3Department of Civil and Environmental Engineering, University of SharjahDepartment of Civil and Environmental Engineering, University of SharjahDepartment of Civil and Environmental Engineering, University of SharjahDepartment of Civil and Environmental Engineering, University of SharjahAbstract This study presents a data-driven framework to identify and evaluate key variables contributing to four major distresses in Continuously Reinforced Concrete Pavement (CRCP): longitudinal cracking, spalling, punchouts, and transverse cracking. A Random Forest regression approach was applied to 395 observations extracted from the Long-Term Pavement Performance (LTPP) database, incorporating structural, climatic, and traffic-related inputs. Feature importance analysis revealed that temperature, Annual Average Daily Truck Traffic (AADTT), and Layer 3 thickness consistently ranked among the top predictors across multiple distress types. Spalling was highly predictable using only a few variables (R² >0.85), whereas longitudinal and transverse cracking required more features to reach moderate accuracy, indicating complex, multifactorial mechanisms. Punchouts showed moderate predictability, influenced primarily by freeze index and heavy truck traffic. Sequential feature addition analysis confirmed that model performance improved significantly with the top-ranked variables, with diminishing returns thereafter. The proposed framework supports the development of parsimonious, interpretable models that can inform efficient CRCP design and maintenance strategies across varying environmental and operational conditions.https://doi.org/10.1007/s44290-025-00302-zContinuously reinforced concrete pavementPavement distressesMachine learningFeature importanceSustainable pavement management
spellingShingle Ali Alnaqbi
Ghazi G. Al-Khateeb
Waleed Zeiada
Muamer Abuzwidah
Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
Discover Civil Engineering
Continuously reinforced concrete pavement
Pavement distresses
Machine learning
Feature importance
Sustainable pavement management
title Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
title_full Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
title_fullStr Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
title_full_unstemmed Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
title_short Random forest-based frame work for multi-distress prediction in CRCP: a feature importance approach
title_sort random forest based frame work for multi distress prediction in crcp a feature importance approach
topic Continuously reinforced concrete pavement
Pavement distresses
Machine learning
Feature importance
Sustainable pavement management
url https://doi.org/10.1007/s44290-025-00302-z
work_keys_str_mv AT alialnaqbi randomforestbasedframeworkformultidistresspredictionincrcpafeatureimportanceapproach
AT ghazigalkhateeb randomforestbasedframeworkformultidistresspredictionincrcpafeatureimportanceapproach
AT waleedzeiada randomforestbasedframeworkformultidistresspredictionincrcpafeatureimportanceapproach
AT muamerabuzwidah randomforestbasedframeworkformultidistresspredictionincrcpafeatureimportanceapproach