Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest

Significant regional environmental differences result in varied patterns of pavement temperature changes. To enhance the cross-regional adaptability of temperature prediction models, transfer learning (TL) was introduced into the random forest (RF) model to improve its generalization capability. Fir...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiang Yuan, Huailei Cheng, Lijun Sun, Yadong Cao, Ruikang Yang, Tian Jin, Mingchen Li
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7436
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849701747988103168
author Jiang Yuan
Huailei Cheng
Lijun Sun
Yadong Cao
Ruikang Yang
Tian Jin
Mingchen Li
author_facet Jiang Yuan
Huailei Cheng
Lijun Sun
Yadong Cao
Ruikang Yang
Tian Jin
Mingchen Li
author_sort Jiang Yuan
collection DOAJ
description Significant regional environmental differences result in varied patterns of pavement temperature changes. To enhance the cross-regional adaptability of temperature prediction models, transfer learning (TL) was introduced into the random forest (RF) model to improve its generalization capability. Firstly, meteorological data on air temperature, solar radiation, relative humidity, and wind speed were collected from different regions. Pavement temperatures at various depths were also monitored over a long period. Secondly, prediction models were constructed using the RF method. The prediction performance of the models was evaluated. Thirdly, the RF model was optimized using TL with a feature enhancement strategy. Finally, the optimized model was validated using data from other regions not included in the initial training set. The results indicated that although the RF model achieved good prediction accuracy within individual regions, its performance declined when applied across different regions. After optimization through TL with feature enhancement, the model’s prediction accuracy in target regions was significantly improved. Specifically, the mean squared error was reduced from 44.91 to 14.88, the mean absolute error from 4.91 to 2.78, and the coefficient of determination increased from 0.75 to 0.92. Further validation revealed that the determination coefficient exceeded 0.94 and the mean absolute error remained below 2.3 °C at all depths. In summary, the transfer learning approach based on the random forest model demonstrates strong adaptability to different regions. It effectively addresses the issue of reduced prediction accuracy caused by regional differences and provides a reliable method for accurate pavement temperature prediction across multiple regions.
format Article
id doaj-art-2baad170f9bf447785b5e928f4b290fd
institution DOAJ
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2baad170f9bf447785b5e928f4b290fd2025-08-20T03:17:52ZengMDPI AGApplied Sciences2076-34172025-07-011513743610.3390/app15137436Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random ForestJiang Yuan0Huailei Cheng1Lijun Sun2Yadong Cao3Ruikang Yang4Tian Jin5Mingchen Li6The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, ChinaShanghai Highway and Bridge Co., Ltd., Shanghai 200433, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, ChinaSchool of Infrastructure Engineering, Dalian University of Technology, Dalian 116024, ChinaSignificant regional environmental differences result in varied patterns of pavement temperature changes. To enhance the cross-regional adaptability of temperature prediction models, transfer learning (TL) was introduced into the random forest (RF) model to improve its generalization capability. Firstly, meteorological data on air temperature, solar radiation, relative humidity, and wind speed were collected from different regions. Pavement temperatures at various depths were also monitored over a long period. Secondly, prediction models were constructed using the RF method. The prediction performance of the models was evaluated. Thirdly, the RF model was optimized using TL with a feature enhancement strategy. Finally, the optimized model was validated using data from other regions not included in the initial training set. The results indicated that although the RF model achieved good prediction accuracy within individual regions, its performance declined when applied across different regions. After optimization through TL with feature enhancement, the model’s prediction accuracy in target regions was significantly improved. Specifically, the mean squared error was reduced from 44.91 to 14.88, the mean absolute error from 4.91 to 2.78, and the coefficient of determination increased from 0.75 to 0.92. Further validation revealed that the determination coefficient exceeded 0.94 and the mean absolute error remained below 2.3 °C at all depths. In summary, the transfer learning approach based on the random forest model demonstrates strong adaptability to different regions. It effectively addresses the issue of reduced prediction accuracy caused by regional differences and provides a reliable method for accurate pavement temperature prediction across multiple regions.https://www.mdpi.com/2076-3417/15/13/7436pavement temperature predictionensemble learningrandom foresttransfer learningcross-regional modeling
spellingShingle Jiang Yuan
Huailei Cheng
Lijun Sun
Yadong Cao
Ruikang Yang
Tian Jin
Mingchen Li
Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
Applied Sciences
pavement temperature prediction
ensemble learning
random forest
transfer learning
cross-regional modeling
title Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
title_full Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
title_fullStr Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
title_full_unstemmed Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
title_short Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest
title_sort cross regional pavement temperature prediction using transfer learning and random forest
topic pavement temperature prediction
ensemble learning
random forest
transfer learning
cross-regional modeling
url https://www.mdpi.com/2076-3417/15/13/7436
work_keys_str_mv AT jiangyuan crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT huaileicheng crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT lijunsun crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT yadongcao crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT ruikangyang crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT tianjin crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest
AT mingchenli crossregionalpavementtemperaturepredictionusingtransferlearningandrandomforest