Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport

12/06/2019
by   Qizhi He, et al.
18

Data assimilation for parameter and state estimation in subsurface transport problems remains a significant challenge due to the sparsity of measurements, the heterogeneity of porous media, and the high computational cost of forward numerical models. We present a physics-informed deep neural networks (DNNs) machine learning method for estimating space-dependent hydraulic conductivity, hydraulic head, and concentration fields from sparse measurements. In this approach, we employ individual DNNs to approximate the unknown parameters (e.g., hydraulic conductivity) and states (e.g., hydraulic head and concentration) of a physical system, and 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 joint inversion of the conductivity, hydraulic head, and concentration fields in a steady-state advection–dispersion problem. We study the accuracy of the physics-informed DNN approach with respect to data size, number of variables (conductivity and head versus conductivity, head, and concentration), DNNs size, and DNN initialization during training. We demonstrate that the physics-informed DNNs are significantly more accurate than standard data-driven DNNs when the training set consists of sparse data. We also show that the accuracy of parameter estimation increases as additional variables are inverted jointly.

READ FULL TEXT

page 13

page 22

page 28

page 29

page 30

research
07/30/2021

Physics-Informed Machine Learning Method for Large-Scale Data Assimilation Problems

We develop a physics-informed machine learning approach for large-scale ...
research
03/03/2023

Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook

For its robust predictive power (compared to pure physics-based models) ...
research
07/20/2022

Automated machine learning for borehole resistivity measurements

Deep neural networks (DNNs) offer a real-time solution for the inversion...
research
10/17/2022

Asymptotic-Preserving Neural Networks for hyperbolic systems with diffusive scaling

With the rapid advance of Machine Learning techniques and the deep incre...
research
01/26/2023

Gaussian process regression and conditional Karhunen-Loéve models for data assimilation in inverse problems

We present a model inversion algorithm, CKLEMAP, for data assimilation a...
research
12/17/2022

Physics-informed Neural Networks with Periodic Activation Functions for Solute Transport in Heterogeneous Porous Media

Solute transport in porous media is relevant to a wide range of applicat...
research
10/29/2017

Weight Initialization of Deep Neural Networks(DNNs) using Data Statistics

Deep neural networks (DNNs) form the backbone of almost every state-of-t...

Please sign up or login with your details

Forgot password? Click here to reset