Gaussian process regression and conditional Karhunen-Lo'eve models for data assimilation in inverse problems
Not on the map. Why?
Abstract (arXiv)
We present a model inversion algorithm, CKLEMAP, for data assimilation and parameter estimation in partial differential equation models of physical systems with spatially heterogeneous parameter fields. These fields are approximated using low-dimensional conditional Karhunen-Lo'eve expansions, which are constructed using Gaussian process regression models of these fields trained on the parameters' measurements. We then assimilate measurements of the state of the system and compute the maximum a posteriori estimate of the CKLE coefficients by solving a nonlinear least-squares problem. When solving this optimization problem, we efficiently compute the Jacobian of the vector objective by exploiting the sparsity structure of the linear system of equations associated with the forward solution of the physics problem. The CKLEMAP method provides better scalability compared to the standard MAP method. In the MAP method, the number of unknowns to be estimated is equal to the number of elements in the numerical forward model. On the other hand, in CKLEMAP, the number of unknowns (CKLE coefficients) is controlled by the smoothness of the parameter field and the number of measurements, and is in general much smaller than the number of discretization nodes, which leads to a significant reduction of computational cost with respect to the standard MAP method. To show its advantage in scalability, we apply CKLEMAP to estimate the transmissivity field in a two-dimensional steady-state subsurface flow model of the Hanford Site by assimilating synthetic measurements of transmissivity and hydraulic head. We find that the execution time of CKLEMAP scales nearly linearly as N1.33, where N is the number of discretization nodes, while the execution time of standard MAP scales as N2.91. The CKLEMAP method improved execution time without sacrificing accuracy when compared to the standard MAP.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 26 Jan 2023.
Builds on
13 of 32 references.
References · 13
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
- 2019Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transportcited by 60
- 2018Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous mediacited by 56
- 2021A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networkscited by 30
- 2018Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identificationcited by 26
- 2020Iterative Ensemble Kalman Methods: A Unified Perspective with Some New Variantscited by 13
- 2019Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEscited by 11
- 2015A penalty method for PDE-constrained optimization in inverse problemscited by 9
- 2019Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivitiescited by 7
- 2019Conditional Karhunen-Lo`eve expansion for uncertainty quantification and active learning in partial differential equation modelscited by 6
- 2019Learning to regularize with a variational autoencoder for hydrologic inverse analysiscited by 6
- 2021Physics-Informed Machine Learning Method for Large-Scale Data Assimilation Problemscited by 6
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.