Data-driven physics informed deep learning of solute transport with anomalous diffusion
For researchers studying anomalous transport in porous media, this method offers a data-driven approach to estimate model parameters that are otherwise difficult to determine experimentally.
The paper develops a data-driven deep learning algorithm using feedforward neural networks to infer parameters of fractional advection-dispersion equations for anomalous solute transport. Numerical experiments on synthetic and field data demonstrate the algorithm's effectiveness and robustness.
The fractional advection-dispersion equation (FADE) has attracted increased attention from researchers as it provides an accurate description for challenging phenomenas with long-range time memory and spatial interactions, such as the anomalous diffusion behavior in the solute transport in porous media. Practically, a full characterization of the model parameters, such as the fluid velocity, dispersion coefficient and the order of the fractional derivative, often implies a huge amount of experiments and measurements and thus are hard to be determined. In this paper, we employ the framework of feedforward deep neural networks (DNNs) to develop an efficient data-driven deep learning algorithm for inferring the aforementioned parameters of the FADE, such as the time-dependent space-fractional advection-dispersion equation (sFADE) and the variable-order fractional mobile/immobile equation (VoFMIE), in which the feedforward DNNs are trained to minimize the mean square error loss function formulated by means of the finite difference approximations of sFADE and VoFMIE, respectively. Several numerical experiments, in which we discover the model parameters by the feedforward DNNs for both the synthetic and field data, are presented to demonstrate the effectiveness and robustness of the proposed data-driven deep learning algorithm.