Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations
This work addresses flow reconstruction for fluid dynamics applications, but it is incremental as it builds on existing CVAE methods with a specific architectural modification.
The authors tackled the problem of reconstructing nonlinear flow fields from sparse observations by introducing a Semi-Conditional Variational Autoencoder (SCVAE), which enables probabilistic reconstruction and uncertainty quantification, and demonstrated its application on 2D cylinder flow and ocean model data with comparisons to GPOD.
We present a new data-driven model to reconstruct nonlinear flow from spatially sparse observations. The model is a version of a conditional variational auto-encoder (CVAE), which allows for probabilistic reconstruction and thus uncertainty quantification of the prediction. We show that in our model, conditioning on the measurements from the complete flow data leads to a CVAE where only the decoder depends on the measurements. For this reason we call the model as Semi-Conditional Variational Autoencoder (SCVAE). The method, reconstructions and associated uncertainty estimates are illustrated on the velocity data from simulations of 2D flow around a cylinder and bottom currents from the Bergen Ocean Model. The reconstruction errors are compared to those of the Gappy Proper Orthogonal Decomposition (GPOD) method.