Applications of Machine Learning in Predicting the Bridge Deck Surface Temperature

Recently, the application of statistical methods and artificial intelligence (AI) techniques such as machine learning and deep learning have gained notable interest in various fields, especially engineering. These data-driven methods can play a crucial role in making predictions faster with higher accuracy. In this study, several machine learning methods were implemented on real engineering data. This paper aims to build a robust model to predict the bridge deck surface temperature by adopting meteorological data obtained from a bridge de-icing project in Texas. Multiple Linear Regression (MLR), Random Forest (RF), k Nearest Neighbors (kNN), Support Vector Regression (SVR), and Extreme Gradient Boosting Decision Tree (XGBDT) were used, and the predicted results were compared and validated by available field data. All machine learning algorithms predicted the surface temperature with high accuracy, demonstrating the applicability of machine learning techniques in temperature prediction tasks. However, the best performance was achieved by XGBDT with R² = 0.99.