Search

Accurate characterization of subsurface hydraulic conductivity is vital for modeling of subsurface flow and transport. The iterative ensemble smoother (IES) has been proposed to estimate the heterogeneous parameter field. As a Monte Carlo-based method, IES requires a relatively large ensemble size to guarantee its performance. To improve the computational efficiency, we propose an adaptive Gaussian process (GP)-based iterative ensemble smoother (GPIES) in this study. At each iteration, the GP surrogate is adaptively refined by adding a few new base points chosen from the updated parameter realizations. Then the sensitivity information between model parameters and measurements is calculated from a large number of realizations generated by the GP surrogate with virtually no computational cost. Since the original model evaluations are only required for base points, whose number is much smaller than the ensemble size, the computational cost is significantly reduced. The applicability of GPIES in estimating heterogeneous conductivity is evaluated by the saturated and unsaturated flow problems, respectively. Without sacrificing estimation accuracy, GPIES achieves about an order of magnitude of speed-up compared with the standard IES. Although subsurface flow problems are considered in this study, the proposed method can be equally applied to other hydrological models. [ABSTRACT FROM AUTHOR]

• Standard DNN methods might lead to highly uncertain and inaccurate predictions. • Multiphysics-informed neural network (MPINN) method is proposed. • Multiphisics constraints improve predictive ability of DNNs. • MPINN allows assimilating multiphysics data. • MPINN reduces data requirements for parameter estimation. Data assimilation for parameter and state estimation in subsurface transport problems remains a significant challenge because of the sparsity of measurements, the heterogeneity of porous media, and the high computational cost of forward numerical models. We present a multiphysics-informed deep neural network machine learning method for estimating space-dependent hydraulic conductivity, hydraulic head, and concentration fields from sparse measurements. In this approach, we employ individual deep neural networks (DNNs) to approximate the unknown parameters (e.g., hydraulic conductivity) and states (e.g., hydraulic head and concentration) of a physical system. Next, we jointly train these DNNs by minimizing the loss function that consists of the governing equations residuals in addition to the error with respect to measurement data. We apply this approach to assimilate conductivity, hydraulic head, and concentration measurements for the joint inversion of these parameter and states in a steady-state advection–dispersion problem. We study the accuracy of the proposed data assimilation approach with respect to the data size (i.e., the number of measured variables and the number of measurements of each variable), DNN size, and the complexity of the parameter field. We demonstrate that the physics-informed DNNs are significantly more accurate than the standard data-driven DNNs, especially when the training set consists of sparse data. We also show that the accuracy of parameter estimation increases as more different multiphysics variables are inverted jointly. [ABSTRACT FROM AUTHOR]