Physics-informed deep learning framework to model intense precipitation events at super resolution

Par Conseil national de recherches du Canada

Téléchargement	Voir la version finale : Physics-informed deep learning framework to model intense precipitation events at super resolution (PDF, 3.7 Mio)
DOI	Trouver le DOI : https://doi.org/10.1186/s40562-023-00272-z
Auteur	Rechercher : Teufel, B.Identifiant ORCID : https://orcid.org/0000-0003-1331-2030; Rechercher : Carmo, F.; Rechercher : Sushama, L.; Rechercher : Sun, L.; Rechercher : Khaliq, M. N.¹; Rechercher : Bélair, S.; Rechercher : Shamseldin, A.; Rechercher : Kumar, D. Nagesh; Rechercher : Vaze, J.
Affiliation	Conseil national de recherches du Canada. Génie océanique, côtier et fluvial
Bailleur de fonds	Rechercher : National Research Council of Canada; Rechercher : Canadian Space Agency; Rechercher : Natural Sciences and Engineering Research Council of Canada
Format	Texte, Article
Sujet	deep learning; regional climate model; convection permitting model; intense precipitation; engineering scale
Résumé	Physical modeling of precipitation at fine (sub-kilometer) spatial scales is computationally very expensive. This study develops a highly efficient framework for this task by coupling deep learning (DL) and physical modeling. This framework is developed and tested using regional climate simulations performed over a domain covering Montreal and adjoining regions, for the summers of 2015–2020, at 2.5 km and 250 m resolutions. The DL framework uses a recurrent approach and considers atmospheric physical processes, such as advection, to generate high-resolution information from low-resolution data, which enables it to recreate fine details and produce temporally consistent fields. The DL framework generates realistic high-resolution precipitation estimates, including intense short-duration precipitation events, which allows it to be applied in engineering problems, such as evaluating the climate resiliency of urban storm drainage systems. The results portray the value of the proposed DL framework, which can be extended to other resolutions, periods, and regions.
Date de publication	2023-04-18
Maison d’édition	Springer
Licence	Creative Commons, Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/deed.fr
Dans	Geoscience Letters 10, nº 1, 19 (18 avril 2023).
Langue	anglais
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	02a7a5ec-7d48-4648-a5b7-8c46354f6808
Enregistrement créé	2023-08-17
Enregistrement modifié	2023-08-17

Date de modification :: 2024-06-29