This course aims to introduce participants to the fundamental and advanced applications of data analytics and machine learning (ML) in the context of pavement engineering. The program will bridge theoretical concepts with practical tools to enable engineers, researchers, and students to effectively analyze pavement performance data, optimize material design, and predict service life. 

Key learning outcomes include:

• Apply Python Programming to Pavement Data Analysis: Develop proficiency in using Python and open-source libraries (NumPy, pandas, scikit-learn, and matplotlib) to clean, visualize, and analyze pavement datasets such as LTPP, RAP/WMA mixture data, and performance records.

• Implement Data-Driven Modeling and Statistical Techniques: Conduct exploratory data analysis, correlation assessment, and regression modeling to identify key performance drivers and understand variability in pavement material and field performance data.

• Develop and Evaluate Machine Learning Models: Build and validate predictive models such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forests, Decision Trees, and K-Nearest Neighbors (KNN) to forecast pavement distresses and material behavior.