DeepAI AI Chat
Log In Sign Up

Differentiable Physics-informed Graph Networks

by   Sungyong Seo, et al.

While physics conveys knowledge of nature built from an interplay between observations and theory, it has been considered less importantly in deep neural networks. Especially, there are few works leveraging physics behaviors when the knowledge is given less explicitly. In this work, we propose a novel architecture called Differentiable Physics-informed Graph Networks (DPGN) to incorporate implicit physics knowledge which is given from domain experts by informing it in latent space. Using the concept of DPGN, we demonstrate that climate prediction tasks are significantly improved. Besides the experiment results, we validate the effectiveness of the proposed module and provide further applications of DPGN, such as inductive learning and multistep predictions.


An extended physics informed neural network for preliminary analysis of parametric optimal control problems

In this work we propose an extension of physics informed supervised lear...

Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures

This paper introduces an innovative physics-informed deep learning frame...

Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning

Integrating physical inductive biases into machine learning can improve ...

GPINN: Physics-informed Neural Network with Graph Embedding

This work proposes a Physics-informed Neural Network framework with Grap...

How to Avoid Trivial Solutions in Physics-Informed Neural Networks

The advent of scientific machine learning (SciML) has opened up a new fi...

Interpretability Study on Deep Learning for Jet Physics at the Large Hadron Collider

Using deep neural networks for identifying physics objects at the Large ...

MetaPhysiCa: OOD Robustness in Physics-informed Machine Learning

A fundamental challenge in physics-informed machine learning (PIML) is t...