Predicting Multiple Properties of Pervious Concrete through the Gaussian Process Regression
Yun Zhang, Xiaojie Xu
Abstract
ABSTRACT Pervious concrete creates a very porous medium that allows water to penetrate the pavement to underlying soils. It is a promising candidate in permeable pavement systems in urban areas, which could be an efficient solution to sustainable drainage systems. Concrete mixture design usually requires labor-intensive and time-consuming work, which involves a significant amount of “trial batching” approaches. Recently, machine learning methods have demonstrated that a robust model might help reduce the experimental work. Thus, we develop the Gaussian process regression (GPR) model to shed light on the relationship between predictors (nominal coarse aggregate sizes, cement content, water-to-cement ratios, and coarse aggregates content) and each of the different properties (density, compressive strength, tensile strength, and porosity) of pervious concrete. The modeling approach has a high degree of accuracy and stability, contributing to fast, low-cost estimations of multiple properties of pervious concrete.