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

Accelerating the Discovery of Steady‐States of Planetary Interior Dynamics With Machine Learning

Agarwal, Siddhant und Tosi, Nicola und Hüttig, Christian und Greenberg, David und Bekar, Ali (2025) Accelerating the Discovery of Steady‐States of Planetary Interior Dynamics With Machine Learning. Journal of Geophysical Research: Machine Learning and Computation, 2 (1). Wiley. doi: 10.1029/2024JH000438. ISSN 2993-5210.

[img] PDF - Verlagsversion (veröffentlichte Fassung)
1MB

Offizielle URL: https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2024JH000438

Kurzfassung

Simulating mantle convection often requires reaching a computationally expensive steady-state, crucial for deriving scaling laws for thermal and dynamical flow properties and benchmarking numerical solutions. The strong temperature dependence of the rheology of mantle rocks causes viscosity variations of several orders of magnitude, leading to a slow-evolving “stagnant lid” where heat conduction dominates, overlying a rapidly evolving and strongly convecting region. Time-stepping methods, while effective for fluids with constant viscosity, are hindered by the Courant criterion, which restricts the time step based on the system's maximum velocity and grid size. Consequently, achieving steady-state requires a large number of time steps due to the disparate time scales governing the stagnant and convecting regions. We present a concept for accelerating mantle convection simulations using machine learning. We generate a data set of 128 two-dimensional simulations with mixed basal and internal heating, and pressure- and temperature-dependent viscosity. We train a feedforward neural network on 97 simulations to predict steady-state temperature profiles. These can then be used to initialize numerical time-stepping methods for different simulation parameters. For an example application, the number of time steps required to reach steady-state is reduced by a factor of 2.8, compared to typically used initializations. The benefit of this method lies in requiring very few simulations to train on, providing a steady-state solution that is numerically accurate as we initialize a numerical method, and posing minimal computational overhead at inference time. We demonstrate the effectiveness of our approach and discuss its potential for advancing mantle convection research.

elib-URL des Eintrags:https://elib.dlr.de/215961/
Dokumentart:Zeitschriftenbeitrag
Titel:Accelerating the Discovery of Steady‐States of Planetary Interior Dynamics With Machine Learning
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Agarwal, Siddhantsiddhant.agarwal (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Tosi, Nicolanicola.tosi (at) dlr.dehttps://orcid.org/0000-0002-4912-2848NICHT SPEZIFIZIERT
Hüttig, ChristianChristian.Huettig (at) dlr.dehttps://orcid.org/0009-0006-3621-7000191482289
Greenberg, DavidModel-Driven Machine Learning, Institute of Coastal Systems - Analysis and Modeling, Hereon Center, Geestacht, GermanyNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Bekar, AliModel-Driven Machine Learning, Institute of Coastal Systems - Analysis and Modeling, Hereon Center, Geestacht, GermanyNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:2025
Erschienen in:Journal of Geophysical Research: Machine Learning and Computation
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Ja
In SCOPUS:Nein
In ISI Web of Science:Nein
Band:2
DOI:10.1029/2024JH000438
Verlag:Wiley
ISSN:2993-5210
Status:veröffentlicht
Stichwörter:neural networks; mantle convection; steady state; geophysical fluid dynamics; machine learning; planetary interiors
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erforschung des Weltraums
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EW - Erforschung des Weltraums
DLR - Teilgebiet (Projekt, Vorhaben):R - Exploration des Sonnensystems
Standort: Berlin-Adlershof
Institute & Einrichtungen:Institut für Planetenforschung > Planetenphysik
Hinterlegt von: Tosi, Dr. Nicola
Hinterlegt am:09 Sep 2025 13:56
Letzte Änderung:09 Sep 2025 13:56

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.