Generative Network-Based Reduced-Order Model for Prediction, Data Assimilation and Uncertainty Quantification

Abstract

We propose a new method in which a generative network (GN) integrate into a reduced-order model (ROM) framework is used to solve inverse problems for partial differential equations (PDE). The aim is to match available measurements and estimate the corresponding uncertainties associated with the states and parameters of a numerical physical simulation. The GN is trained using only unconditional simulations of the discretized PDE model. We compare the proposed method with the golden standard Markov chain Monte Carlo. We apply the proposed approaches to a spatio-temporal compartmental model in epidemiology. The results show that the proposed GN-based ROM can efficiently quantify uncertainty and accurately match the measurements and the golden standard, using only a few unconditional simulations of the full-order numerical PDE model.

arXiv commentarXiv admin note: text overlap with arXiv:2105.07729

References in corpus (15)

• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Fourier Neural Operator for Parametric Partial Differential Equations
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Enhancing Computational Fluid Dynamics with Machine Learning
• A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
• Cluster-based reduced-order modelling of a mixing layer
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion
• Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matching
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Non-linearly stable reduced-order models for incompressible flow with energy-conserving finite volume methods
• DeepFlow: History Matching in the Space of Deep Generative Models
• Verification of a real-time ensemble-based method for updating earth model based on GAN
• Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19