Symbolic Graph Networks for Robust PDE Discovery from Noisy Sparse Data

1. 1Propose a Symbolic Graph Network (SGN) framework to discover PDEs from noisy sparse data
2. 2Utilize graph neural networks to learn symbolic representations of PDEs
3. 3Apply the SGN framework to real-world problems, such as physics and engineering, to uncover governing physical laws

Data scientists and AI engineers on a team can benefit from this framework as it enables the discovery of governing physical laws from observational data, which can be applied to various fields such as physics and engineering

💡 The SGN framework provides a robust approach to PDE discovery from noisy sparse data, overcoming challenges posed by numerical differentiation or integral formulations

💡 Discover PDEs from noisy sparse data with Symbolic Graph Networks!