Uncertainty Quantification with Normalizing Flows: A Seismic Data Interpolation Example

Normalizing Flows are a type of neural network that allow us to map one probability distribution into another.  The advantage of such a technique is that they allow us to relate a simple distribution, like a Gaussian, to a more complicated distribution that may be more difficult to estimate and sample from.  In uncertainty quantification for inverse problems, we are trying to estimate one of these more complicated distributions, thus normalizing flows can help to speed up this process and improve our ability to use and analyze our results.  This will be an applied talk, giving an introduction to normalizing flows, discussing how we chose the particular machine learning method and explaining how it improves our understanding of seismic data processing and the associated uncertainties.