DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks

Abstract

Electroconvection is a multiphysics problem involving coupling of the flow field with the electric field as well as the cation and anion concentration fields. For small Debye lengths, very steep boundary layers are developed, but standard numerical methods can simulate the different regimes quite accurately. Here, we use electroconvection as a benchmark problem to put forward a new data assimilation framework, the DeepM&Mnet, for simulating multiphysics and multiscale problems at speeds much faster than standard numerical methods using pre-trained neural networks (NNs). We first pre-train DeepONets that can predict independently each field, given general inputs from the rest of the fields of the coupled system. DeepONets can approximate nonlinear operators and are composed of two sub-networks, a branch net for the input fields and a trunk net for the locations of the output field. DeepONets, which are extremely fast, are used as building blocks in the DeepM&Mnet and form constraints for the multiphysics solution along with some sparse available measurements of any of the fields. We demonstrate the new methodology and document the accuracy of each individual DeepONet, and subsequently we present two different DeepM&Mnet architectures that infer accurately and efficiently 2D electroconvection fields for unseen electric potentials. The DeepM&Mnet framework is general and can be applied for building any complex multiphysics and multiscale models based on very few measurements using pre-trained DeepONets in a plug-and-play mode.

References in corpus (21)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Machine Learning for Fluid Mechanics
• DeepXDE: A deep learning library for solving differential equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Turbulence Modeling in the Age of Data
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• fPINNs: Fractional Physics-Informed Neural Networks
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep Learning of Vortex Induced Vibrations
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• Operator learning for predicting multiscale bubble growth dynamics
• On the coupling between buoyancy forces and electroconvective instability near ion-selective surfaces
• State estimation in turbulent channel flow from limited observations
• Reinforcement Learning for Active Flow Control in Experiments

Cited by in corpus (35)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Deep Learning in Deterministic Computational Mechanics
• Reliable extrapolation of deep neural operators informed by physics or sparse observations
• Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• Data-driven cardiovascular flow modeling: examples and opportunities
• A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel construction
• Evolutional Deep Neural Network
• Learning Functional Priors and Posteriors from Data and Physics
• Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
• Simulating progressive intramural damage leading to aortic dissection using an operator-regression neural network
• SVD Perspectives for Augmenting DeepONet Flexibility and Interpretability
• Deep Neural Operator Driven Real Time Inference for Nuclear Systems to Enable Digital Twin Solutions
• A neural operator-based surrogate solver for free-form electromagnetic inverse design
• RiemannONets: Interpretable Neural Operators for Riemann Problems
• On universal approximation and error bounds for Fourier Neural Operators
• BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning
• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• Inferring electrochemical performance and parameters of Li-ion batteries based on deep operator networks
• Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone
• Real-Time Prediction of Gas Flow Dynamics in Diesel Engines using a Deep Neural Operator Framework
• Accelerated replica exchange stochastic gradient Langevin diffusion enhanced Bayesian DeepONet for solving noisy parametric PDEs
• Scattering with Neural Operators
• G2Φnet: Relating Genotype and Biomechanical Phenotype of Tissues with Deep Learning
• Quantum DeepONet: Neural operators accelerated by quantum computing
• Physics-informed Deep Learning to Solve Three-dimensional Terzaghi Consolidation Equation: Forward and Inverse Problems
• Arbitrary-Depth Universal Approximation Theorems for Operator Neural Networks
• MCMC-Net: Accelerating Markov Chain Monte Carlo with Neural Networks for Inverse Problems
• BINet: Learning to Solve Partial Differential Equations with Boundary Integral Networks
• Surrogate Modeling of Landau Damping with Deep Operator Networks
• Physics-Informed Time-Integrated DeepONet: Temporal Tangent Space Operator Learning for High-Accuracy Inference
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification
• Extending deep learning U-Net architecture for predicting unsteady fluid flows in textured microchannels