Optimizing Transport Predictive Modeling with Simulation-Based Statistical Inference

Abstract

Simulation-based statistical inference (SBI) leverages computer simulations to help scientists understand and analyze complex data. This project explores how SBI techniques can be used to analyze transportation data. We use modern computational methods, including machine learning models, to improve the accuracy of predictions and decision-making in transportation planning. Our study focuses on applying two SBI methods, Approximate Bayesian Computation - Markov Chain Monte Carlo and Synthetic Likelihood, to create synthetic data for training machine learning models. These models show the potential of SBI to handle uncertain data. It also highlights the practical benefits of SBI in making predictions and decisions for transportation systems.