Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database

Abstract

We study the applicability of tools developed by the computer vision community for features learning and semantic image inpainting to perform data reconstruction of fluid turbulence configurations. The aim is twofold. First, we explore on a quantitative basis, the capability of Convolutional Neural Networks embedded in a Deep Generative Adversarial Model (Deep-GAN) to generate missing data in turbulence, a paradigmatic high dimensional chaotic system. In particular, we investigate their use in reconstructing two-dimensional damaged snapshots extracted from a large database of numerical configurations of 3d turbulence in the presence of rotation, a case with multi-scale random features where both large-scale organised structures and small-scale highly intermittent and non-Gaussian fluctuations are present. Second, following a reverse engineering approach, we aim to rank the input flow properties (features) in terms of their qualitative and quantitative importance to obtain a better set of reconstructed fields. We present two approaches both based on Context Encoders. The first one infers the missing data via a minimization of the L2 pixel-wise reconstruction loss, plus a small adversarial penalisation. The second searches for the closest encoding of the corrupted flow configuration from a previously trained generator. Finally, we present a comparison with a different data assimilation tool, based on Nudging, an equation-informed unbiased protocol, well known in the numerical weather prediction community. The TURB-Rot database, http://smart-turb.roma2.infn.it, of roughly 300K 2d turbulent images is released and details on how to download it are given.

References in corpus (9)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Coherent structures and extreme events in rotating multiphase turbulent flows
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
• Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
• Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
• Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs
• Data recovery in computational fluid dynamics through deep image priors
• TURB-Rot. A large database of 3d and 2d snapshots from turbulent rotating flows

Cited by in corpus (18)

• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
• Interpreted machine learning in fluid dynamics: Explaining relaminarisation events in wall-bounded shear flows
• Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models
• Quantum support vector machines for aerodynamic classification
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Generative Adversarial Networks to infer velocity components in rotating turbulent flows
• Reconstructing unsteady flows from sparse, noisy measurements with a physics-constrained convolutional neural network
• Mesh-Free Interpolant Observables for Continuous Data Assimilation
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• Neural Network Complexity of Chaos and Turbulence
• Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Correlation and decomposition framework for identifying and disentangling flow structures: canonical examples and application to isotropic turbulence
• Reconstruction of three-dimensional turbulent flows from sparse and noisy planar measurements: A weight-sharing neural network approach