Road networks are crucial infrastructures that play a significant role in the progress and advancement of societies. However, roads deteriorate over time due to regular use and external environmental factors. This deterioration leads to discomfort for road users as well as the generation of noise and vibrations, which negatively impact nearby structures. Therefore, it is essential to regularly maintain and monitor road networks. The International Roughness Index (IRI) is commonly used to quantify road roughness and serves as a key indicator for assessing road condition. Traditionally, obtaining the IRI involves manual or automated methods that can be time-consuming and expensive. This study explores the potential of using artificial neural networks (ANNs) and dynamic vehicle accelerations from two simulated car models to reconstruct road roughness profiles. These models include a simplified quarter-car (QC) model with two degrees of freedom, valued for its computational efficiency, and a more intricate full-car (FC) model with seven degrees of freedom, which replicates real-life vehicle behavior. This study also examines the ability of ANNs to predict the mechanical properties of the FC model from dynamic vehicle responses to obstacles. We compare the accuracy and computational efficiency of the two models and find that the QC model is almost 10 times faster than the FC model in reconstructing the road roughness profile whilst achieving higher accuracy.