• Corpus ID: 238531406

A composable autoencoder-based iterative algorithm for accelerating numerical simulations

  title={A composable autoencoder-based iterative algorithm for accelerating numerical simulations},
  author={Rishikesh Ranade and Chris Hill and Haiyang He and Amir Maleki and Norman Chang and Jay Pathak},
Numerical simulations for engineering applications solve partial differential equations (PDE) to model various physical processes. Traditional PDE solvers are very accurate but computationally costly. On the other hand, Machine Learning (ML) methods offer a significant computational speedup but face challenges with accuracy and generalization to different PDE conditions, such as geometry, boundary conditions, initial conditions and PDE source terms. In this work, we propose a novel ML-based… 


Amortized Finite Element Analysis for Fast PDE-Constrained Optimization
This paper proposes amortized finite element analysis (AmorFEA), in which a neural network learns to produce accurate PDE solutions, while preserving many of the advantages of traditional finite element methods.
Train Once and Use Forever: Solving Boundary Value Problems in Unseen Domains with Pre-trained Deep Learning Models
A transferable framework for solving boundary value problems (BVPs) via deep neural networks which can be trained once and used forever for various domains of unseen sizes, shapes, and boundary conditions is introduced.
Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow
We propose an end‐to‐end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single‐phase smoke simulations in 2D and
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.
Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework
We present a comprehensive framework for augmenting turbulence models with physics-informed machine learning, illustrating a complete workflow from identification of input/output to prediction of
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
We propose to formulate physical reasoning and manipulation planning as an optimization problem that integrates first order logic, which we call Logic-Geometric Programming.
Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize
A novel physics-constrained training approach that generalizes to new fluid domains, requires no fluid simulation data, and allows convolutional neural networks to map a fluid state from time-point t to a subsequent state at time t + dt in a single forward pass is proposed, which simplifies the pipeline to train and evaluate neural fluid models.
Differentiable Molecular Simulations for Control and Learning
This work demonstrates how differentiable simulations where bulk target observables and simulation outcomes can be analytically differentiated with respect to Hamiltonians can be achieved, opening up new routes for parameterizing Hamiltonians to infer macroscopic models and develop control protocols.