G. Porta

Probabilistic Inverse Modeling of Contaminant Transport via a Conditioned-on-Design Bayesian Physics Informed Neural Network

We address the inverse problem of reactive transport in heterogeneous porous media, where unknown model parameters must be inferred from sparse experimental observations. The problem is complicated by strong nonlinearities, spatial heterogeneity, and limited data availability. We propose a Conditioned-on-Design Bayesia...