Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
Michele Buzzicotti, Fabio Bonaccorso, Patricio Clark Di Leoni, Luca Biferale
Abstract
Investigations show that convolutional neural networks (CNNs) are able to reconstruct missing data in turbulence. Different types of input information impact the performance of the algorithm. CNNs are able to reconstruct original data with errors comparable to equation-informed tools such as nudging, even in the presence of large gaps.
Topics & Concepts
InpaintingConvolutional neural networkGenerative grammarGenerative adversarial networkComputer scienceDeep learningArtificial intelligenceGenerative modelArtificial neural networkTurbulenceMissing dataNatural language processingData miningImage (mathematics)Machine learningGeographyMeteorologyGenerative Adversarial Networks and Image SynthesisFluid Dynamics and Turbulent FlowsModel Reduction and Neural Networks