paper-with-me

홈 › Papers

Physics-constrained Unsupervised Learning of Partial Differential Equations using Meshes

2022-03-30 · Mike Y. Michelis, Robert K. Katzschmann

Enhancing neural networks with knowledge of physical equations has become an efficient way of solving various physics problems, from fluid flow to electromagnetism. Graph neural networks show promise in accurately representing irregularly meshed objects and learning their dynamics, but have so far required supervision through large datasets. In this work, we represent meshes naturally as graphs, process these using Graph Networks, and formulate our physics-based loss to provide an unsupervised learning framework for partial differential equations (PDE). We quantitatively compare our results to a classical numerical PDE solver, and show that our computationally efficient approach can be used as an interactive PDE solver that is adjusting boundary conditions in real-time and remains sufficiently close to the baseline solution. Our inherently differentiable framework will enable the application of PDE solvers in interactive settings, such as model-based control of soft-body deformations, or in gradient-based optimization methods that require a fully differentiable pipeline.

📄 PDF Abstract BibTeX arXiv:2203.16628

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator

2022-10-21 · A. Mavi, A. C. Bekar, E. Haghighat, E. Madenci

This study presents a novel unsupervised convolutional Neural Network (NN) architecture with nonlocal interactions for solving Partial Differential Equations (PDEs). The nonlocal Peridynamic Differential Operator (PDDO) …

Decoder

Super-resolving sparse observations in partial differential equations: A physics-constrained convolutional neural network approach

2023-06-19 · Daniel Kelshaw, Luca Magri

We propose the physics-constrained convolutional neural network (PC-CNN) to infer the high-resolution solution from sparse observations of spatiotemporal and nonlinear partial differential equations. Results are shown fo…

Super-Resolution

Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations

2022-02-24 · Benjamin Wu, Oliver Hennigh, Jan Kautz, Sanjay Choudhry 외

Physics-informed neural networks allow models to be trained by physical laws described by general nonlinear partial differential equations. However, traditional architectures struggle to solve more challenging time-depen…

Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations

2017-11-28 · Maziar Raissi, Paris Perdikaris, George Em. Karniadakis

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations…

Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

2020-03-03 · CVPR 2020 6 · Vincent Le Guen, Nicolas Thome

Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods. Since physics is too restrictive for describing the full visual conte…

DisentanglementPredictionVideo PredictionWeather Forecasting