Chloride diffusion modeling of concrete using tree‐based forest models

Reinforced concrete structures can experience various harsh environments during their service life, among which chloride ion exposure, especially in marine environments, cause the durability reduction and deterioration of structures. Artificial intelligence (AI)-based modeling non-steady-state apparent diffusion coefficient (DC) for a long exposure time using experimental field results assist identifying influential factors better estimating life structure. In this study, two novel extensions ensemble AI algorithms, including genetic programming forest (GPF) linear (LGPF) were proposed to model DC concrete. The data gathered from literature. Different methods developed examined, best-developed was selected further analysis, sensitivity analysis parametric study. addition, random (RF) method used as control technique have comparison. show that best LGPF possesses superior performance than GPF RF models. silica fume-to-binder ratio, time, conditions most significant impacts on This study contributes civil engineering practice by developing new tool facilitates assessment