Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations

Abstract

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.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Variational Inference: A Review for Statisticians
• An Introduction to Variational Autoencoders
• DRAW: A Recurrent Neural Network For Image Generation
• Data-Driven Sparse Sensor Placement for Reconstruction
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
• Robust flow field reconstruction from limited measurements via sparse representation
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
• Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observation

Cited by in corpus (6)

• Experimental velocity data estimation for imperfect particle images using machine learning
• Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models
• Low-Order Flow Reconstruction and Uncertainty Quantification in Disturbed Aerodynamics Using Sparse Pressure Measurements
• Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings
• Gappy AE: A Nonlinear Approach for Gappy Data Reconstruction using Auto-Encoder
• Image features of a splashing drop on a solid surface extracted using a feedforward neural network