Improvement of a Machine Learning Model for Estimating Pavement Bearing Capacity on Expressways

Key Points

• This research aims to improve a machine learning model for estimating pavement bearing capacity on expressways.
• Utilized data from pavement management systems
• Enhanced a flexural indicator estimation model
• Focused on improving model generality and predictive accuracy
• Achieved a coefficient of determination (R²) of 0.794 between observed and estimated values
• Demonstrated the potential to quickly assess lower support strength over approximately 250km of roadway