Multi-Scale Reconstruction of Turbulent Rotating Flows with Generative Diffusion Models
Atmosphere · 31.12.2023 · 15 (1) · 60
DOI: 10.3390/atmos15010060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Atmosphere, online erschienen am 31.12.2023. Verfasst von Tianyi Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council (ERC), ICSC—Centro Nazionale di Ricerca in High Performance Computing, Big Data, and Quantum Computing.
Abstract (Originalsprache)
We address the problem of data augmentation in a rotating turbulence set-up, a paradigmatic challenge in geophysical applications. The goal is to reconstruct information in two-dimensional (2D) cuts of the three-dimensional flow fields, imagining spatial gaps present within each 2D observed slice. We evaluate the effectiveness of different data-driven tools, based on diffusion models (DMs), a state-of-the-art generative machine learning protocol, and generative adversarial networks (GANs), previously considered as the best-performing method both in terms of point-wise reconstruction and the statistical properties of the inferred velocity fields. We focus on two different DMs recently proposed in the specialized literature: (i) RePaint, based on a heuristic strategy to guide an unconditional DM for flow generation by using partial measurements data, and (ii) Palette, a conditional DM trained for the reconstruction task with paired measured and missing data. Systematic comparison shows that (i) DMs outperform the GAN in terms of the mean squared error and/or the statistical accuracy; (ii) Palette DM emerges as the most promising tool in terms of both point-wise and statistical metrics. An important property of DMs is their capacity for probabilistic reconstructions, providing a range of predictions based on the same measurements, enabling uncertainty quantification and risk assessment.
Förderung
- European Research Council (ERC)
- ICSC—Centro Nazionale di Ricerca in High Performance Computing, Big Data, and Quantum Computing
Zitieren
APA
Li, T., Lanotte, A. S., Buzzicotti, M., Bonaccorso, F., & Biferale, L. (2023). Multi-Scale Reconstruction of Turbulent Rotating Flows with Generative Diffusion Models. Atmosphere, 15(1), 60. https://doi.org/10.3390/atmos15010060
Vancouver
Li T, Lanotte AS, Buzzicotti M, Bonaccorso F, Biferale L. Multi-Scale Reconstruction of Turbulent Rotating Flows with Generative Diffusion Models. Atmosphere. 2023;15(1):60. doi:10.3390/atmos15010060
BibTeX
@article{Li2023,
author = {Li, Tianyi and Lanotte, Alessandra S. and Buzzicotti, Michele and Bonaccorso, Fabio and Biferale, Luca},
title = {Multi-Scale Reconstruction of Turbulent Rotating Flows with Generative Diffusion Models},
journal = {Atmosphere},
year = {2023},
volume = {15},
number = {1},
pages = {60},
doi = {10.3390/atmos15010060}
}
EUVIMED