A robust methodology for assessing and predicting permeability in pervious concrete is indispensable for the design of pervious concrete pavements, as well as for quality control and performance evaluation during construction and throughout the service life of the pavement. This chapter provides a comprehensive analysis of flow through porous media, permeability testing, and prediction models specific to pervious concrete. Literature findings reveal variations in hydraulic conductivity corresponding to changes in the hydraulic gradient, highlighting inaccuracies in applying Darcy's law. This study investigates discrepancies between permeability measurements conducted in the laboratory and those observed in the field, emphasizing the limitations of Darcy’s law and reflecting on alternative sources of potential inconsistency. Additionally, there is a gap in investigating nonlinear aspects of analytical, empirical, and numerical models for permeability prediction. In conclusion, this study underscores the potential of machine learning models to predict permeability and optimize pervious concrete mixture designs.
