气候变化领域集成服务门户(CCPortal): Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport

CCPortal

DOI	10.1016/j.advwatres.2020.103610
	Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport
	He Q.; Barajas-Solano D.; Tartakovsky G.; Tartakovsky A.M.
发表日期	2020
ISSN	0309-1708
卷号	141
英文摘要	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. © 2020
关键词	Deep neural networks Hydraulic conductivity Learning systems Porous materials State estimation Accuracy of parameters Computational costs Concentration fields Concentration Measurement Data assimilation Governing equations Parameter and state estimation Subsurface transport Parameter estimation artificial neural network data assimilation hydraulic conductivity hydraulic head porous medium subsurface flow transport process
语种	英语
来源机构	Advances in Water Resources
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/131791
推荐引用方式 GB/T 7714	He Q.,Barajas-Solano D.,Tartakovsky G.,et al. Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport[J]. Advances in Water Resources,2020,141.
APA	He Q.,Barajas-Solano D.,Tartakovsky G.,&Tartakovsky A.M..(2020).Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport.,141.
MLA	He Q.,et al."Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport".141(2020).