elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Barrierefreiheit | Kontakt | English
Schriftgröße: [-] Text [+]

Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model

Vahid Yousefnia, Kianusch und Metzl, Christoph und Bölle, Tobias (2025) Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model. Artificial Intelligence for the Earth Systems, 4 (3). American Meteorological Society. doi: 10.1175/AIES-D-24-0096.1. ISSN 2769-7525.

[img] PDF - Verlagsversion (veröffentlichte Fassung)
8MB

Offizielle URL: https://dx.doi.org/10.1175/AIES-D-24-0096.1

Kurzfassung

Thunderstorms have significant social and economic impacts due to heavy precipitation, hail, lightning, and strong winds, necessitating reliable forecasts. Thunderstorm forecasts based on numerical weather prediction (NWP) often rely on single-level surrogate predictors, like convective available potential energy and convective inhibition, derived from vertical profiles of three-dimensional atmospheric variables. In this study, we develop SALAMA 1D, a deep neural network which directly infers the probability of thunderstorm occurrence from vertical profiles of ten atmospheric variables, bypassing single-level predictors. By training the model on convection-permitting NWP forecasts, we allow SALAMA 1D to flexibly identify convective patterns, with the goal of enhancing forecast accuracy. The model's architecture is physically motivated: sparse connections encourage interactions at similar height levels while keeping model size and inference times computationally efficient, whereas a shuffling mechanism prevents the model from learning non-physical patterns tied to the vertical grid. SALAMA 1D is trained over Central Europe with lightning observations as the ground truth. Comparative analysis against a baseline machine learning model that uses single-level predictors shows SALAMA 1D's superior skill across various metrics and lead times of up to at least 11 hours. Moreover, expanding the archive of forecasts from which training examples are sampled improves skill, even when training set size remains constant. Finally, a sensitivity analysis using saliency maps indicates that our model relies on physically interpretable patterns consistent with established theoretical understanding, such as ice particle content near the tropopause, cloud cover, conditional instability, and low-level moisture.

elib-URL des Eintrags:https://elib.dlr.de/216616/
Dokumentart:Zeitschriftenbeitrag
Titel:Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Vahid Yousefnia, KianuschDLR, IPAhttps://orcid.org/0000-0003-2644-2539192716748
Metzl, ChristophDLR, IPANICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Bölle, TobiasDLR, IPAhttps://orcid.org/0000-0003-3714-6882NICHT SPEZIFIZIERT
Datum:11 August 2025
Erschienen in:Artificial Intelligence for the Earth Systems
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Band:4
DOI:10.1175/AIES-D-24-0096.1
Verlag:American Meteorological Society
ISSN:2769-7525
Status:veröffentlicht
Stichwörter:Deep convection, Thunderstorms, Numerical weather prediction, Forecasting, Postprocessing, Machine learning, Interpretability
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Luftfahrt
HGF - Programmthema:Luftverkehr und Auswirkungen
DLR - Schwerpunkt:Luftfahrt
DLR - Forschungsgebiet:L AI - Luftverkehr und Auswirkungen
DLR - Teilgebiet (Projekt, Vorhaben):L - Klima, Wetter und Umwelt
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Physik der Atmosphäre > Angewandte Meteorologie
Hinterlegt von: Vahid Yousefnia, Kianusch
Hinterlegt am:25 Sep 2025 13:10
Letzte Änderung:25 Sep 2025 13:10

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
OpenAIRE Validator logo electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.