TechPrufer
Get started
DeepMind
DeepMind logoDeepMind · Feature trail

AI for Fluid Dynamics Research

1 post · Sep 2025

What this trail covers

This post introduces a novel method for discovering new families of unstable singularities in fluid dynamics equations using AI techniques, specifically Physics-Informed Neural Networks (PINNs) and second-order optimizers. This approach pushes the boundaries of accuracy in mathematical research, enabling computer-assisted proofs and tackling long-standing challenges in mathematics, physics, and engineering.

All DeepMind trails
  1. Discovering new solutions to century-old problems in fluid dynamicsIntroduces a new method for discovering unstable singularities in fluid dynamics equations by incorporating machine learning techniques, specifically second-order optimizers for training neural networks. Leverages Physics-Informed Neural Networks (PINNs) with a high-precision framework to achieve near-machine precision for computer-assisted proofs. Identifies a pattern in the blow-up speed (lambda) against the order of instability for the Incompressible Porous Media (IPM) and Boussinesq equations.