Probabilistic neural networks for fluid flow surrogate modeling and data recovery

Understand

We consider the use of probabilistic neural networks for fluid flow {surrogate modeling} and data recovery.

• This framework is constructed by assuming that the target variables are sampled from a Gaussian distribution conditioned on the inputs.
• Consequently, the overall formulation sets up a procedure to predict the hyperparameters of this distribution which are then used to compute an objective function given training data.
• We demonstrate that this framework has the ability to provide for prediction confidence intervals based on the assumption of a probabilistic posterior, given an appropriate model architecture and adequate training data.