Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization

Abstract The predictive performance of probabilistic pavement condition deterioration is critical for effective maintenance and rehabilitation decisions. Currently, numerous improved models exist, but few rely on probabilistic models to improve pavement deterioration prediction. Therefore, this stud...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Xiao, Biying Shi, Jie Gao, Huapeng Chen, Di Yang
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92469-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040020856995840
author Feng Xiao
Biying Shi
Jie Gao
Huapeng Chen
Di Yang
author_facet Feng Xiao
Biying Shi
Jie Gao
Huapeng Chen
Di Yang
author_sort Feng Xiao
collection DOAJ
description Abstract The predictive performance of probabilistic pavement condition deterioration is critical for effective maintenance and rehabilitation decisions. Currently, numerous improved models exist, but few rely on probabilistic models to improve pavement deterioration prediction. Therefore, this study proposed an improved probabilistic model for pavement deterioration prediction based on the coupling of Bayesian neural network (BNN) and cuckoo search (CS) algorithm. The model prediction performance is evaluated against two metrics: determination coefficient (R2) and standard deviation (stability). Finally, based on the data from the pavement management system in Shanxi Province, it was verified that the CS-BNN model outperforms the genetic algorithm-BNN, particle swarm optimization-BNN, and BNN models in terms of the two metrics. Sensitivity analysis further confirms the robustness of the CS-BNN model. The findings indicate that the CS-BNN model provides more reliable predictions with lower uncertainty, aiding road engineers in optimizing maintenance schedules and costs.
format Article
id doaj-art-ca4c1699e297454ea062cd61592c2b08
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ca4c1699e297454ea062cd61592c2b082025-08-20T02:56:11ZengNature PortfolioScientific Reports2045-23222025-03-0115111810.1038/s41598-025-92469-9Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimizationFeng Xiao0Biying Shi1Jie Gao2Huapeng Chen3Di Yang4School of Transportation Engineering, East China JiaoTong UniversitySchool of Architectural and Art, Jiangxi Industry Polytechnic CollegeSchool of Civil Engineering and Architecture, East China JiaoTong UniversitySchool of Transportation Engineering, East China JiaoTong UniversityInstitute of Transportation Development Strategy & Planning of Sichuan ProvinceAbstract The predictive performance of probabilistic pavement condition deterioration is critical for effective maintenance and rehabilitation decisions. Currently, numerous improved models exist, but few rely on probabilistic models to improve pavement deterioration prediction. Therefore, this study proposed an improved probabilistic model for pavement deterioration prediction based on the coupling of Bayesian neural network (BNN) and cuckoo search (CS) algorithm. The model prediction performance is evaluated against two metrics: determination coefficient (R2) and standard deviation (stability). Finally, based on the data from the pavement management system in Shanxi Province, it was verified that the CS-BNN model outperforms the genetic algorithm-BNN, particle swarm optimization-BNN, and BNN models in terms of the two metrics. Sensitivity analysis further confirms the robustness of the CS-BNN model. The findings indicate that the CS-BNN model provides more reliable predictions with lower uncertainty, aiding road engineers in optimizing maintenance schedules and costs.https://doi.org/10.1038/s41598-025-92469-9Pavement management systemsDeteriorationProbabilistic predictionBayesian neural networkCuckoo search algorithm
spellingShingle Feng Xiao
Biying Shi
Jie Gao
Huapeng Chen
Di Yang
Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
Scientific Reports
Pavement management systems
Deterioration
Probabilistic prediction
Bayesian neural network
Cuckoo search algorithm
title Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
title_full Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
title_fullStr Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
title_full_unstemmed Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
title_short Enhanced probabilistic prediction of pavement deterioration using Bayesian neural networks and cuckoo search optimization
title_sort enhanced probabilistic prediction of pavement deterioration using bayesian neural networks and cuckoo search optimization
topic Pavement management systems
Deterioration
Probabilistic prediction
Bayesian neural network
Cuckoo search algorithm
url https://doi.org/10.1038/s41598-025-92469-9
work_keys_str_mv AT fengxiao enhancedprobabilisticpredictionofpavementdeteriorationusingbayesianneuralnetworksandcuckoosearchoptimization
AT biyingshi enhancedprobabilisticpredictionofpavementdeteriorationusingbayesianneuralnetworksandcuckoosearchoptimization
AT jiegao enhancedprobabilisticpredictionofpavementdeteriorationusingbayesianneuralnetworksandcuckoosearchoptimization
AT huapengchen enhancedprobabilisticpredictionofpavementdeteriorationusingbayesianneuralnetworksandcuckoosearchoptimization
AT diyang enhancedprobabilisticpredictionofpavementdeteriorationusingbayesianneuralnetworksandcuckoosearchoptimization