Physics Model-Based AI for Rare Events

Objectives:

• To develop a novel strategy to perform reliable extrapolation with machine learning (ML) by space-unwrapping 
• Efficiently handle extreme value modelling via machine learning using model-based strategies like exponentially tiled estimators
• Solving stochastic partial differential equations via physics informed neural networks for transport equations

Expected Results:

• Efficient approximators for rare events, in particular in high-energy physics (phase space modelling)
• Guarantees of approximation quality
• Uncertainties of multiple standard deviations