Physics-Informed LeaRnIng for Multiscale Systems (PILgRIMS)
The DARPA Physics of Artificial Intelligence ( PAI ) program is part of a broad initiative by DARPA to develop robust, interpretable machine learning frameworks that incorporate physical principles to solve challenging, large scale problems in applied math, science, engineeering. At the Predictive Science Lab, this involves:
Developing deep learning models to quantify uncertainty in complex high-dimensional systems described by stochastic partial differential equations.
Leveraging the properties of Lie groups to learn potentially chaotic dynamical systems.
Learning the dynamics of complex flows through assimilation of particle image velocimetry data with deep neural networks.
- Sociotechnical Systems to Enable Smart and Connected Energy-Aware Residential Communities
- Automated Decision Support to Address Community Resilience Challenges
- Design of electric machines with manufacturing uncertainties
- Efficient Algorithms for Ultra-fast Detection of Power System Contingencies in the Transient Regime.
- A Theoretical Framework for Understanding Strategic Behavior in Systems Engineering