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. 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.