Next-Generation Earth System Models: Towards Reliable Hybrid Models for Weather and Climate Applications

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Beucler, Tom, Koch, Erwan, Kotlarski, Sven, Leutwyler, David, Michel, Adrien, Koh, Jonathan
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929225136603136
author Beucler, Tom
Koch, Erwan
Kotlarski, Sven
Leutwyler, David
Michel, Adrien
Koh, Jonathan
author_facet Beucler, Tom
Koch, Erwan
Kotlarski, Sven
Leutwyler, David
Michel, Adrien
Koh, Jonathan
contents We review how machine learning has transformed our ability to model the Earth system, and how we expect recent breakthroughs to benefit end-users in Switzerland in the near future. Drawing from our review, we identify three recommendations. Recommendation 1: Develop Hybrid AI-Physical Models: Emphasize the integration of AI and physical modeling for improved reliability, especially for longer prediction horizons, acknowledging the delicate balance between knowledge-based and data-driven components required for optimal performance. Recommendation 2: Emphasize Robustness in AI Downscaling Approaches, favoring techniques that respect physical laws, preserve inter-variable dependencies and spatial structures, and accurately represent extremes at the local scale. Recommendation 3: Promote Inclusive Model Development: Ensure Earth System Model development is open and accessible to diverse stakeholders, enabling forecasters, the public, and AI/statistics experts to use, develop, and engage with the model and its predictions/projections.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13691
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Next-Generation Earth System Models: Towards Reliable Hybrid Models for Weather and Climate Applications
Beucler, Tom
Koch, Erwan
Kotlarski, Sven
Leutwyler, David
Michel, Adrien
Koh, Jonathan
Atmospheric and Oceanic Physics
Artificial Intelligence
Computational Physics
We review how machine learning has transformed our ability to model the Earth system, and how we expect recent breakthroughs to benefit end-users in Switzerland in the near future. Drawing from our review, we identify three recommendations. Recommendation 1: Develop Hybrid AI-Physical Models: Emphasize the integration of AI and physical modeling for improved reliability, especially for longer prediction horizons, acknowledging the delicate balance between knowledge-based and data-driven components required for optimal performance. Recommendation 2: Emphasize Robustness in AI Downscaling Approaches, favoring techniques that respect physical laws, preserve inter-variable dependencies and spatial structures, and accurately represent extremes at the local scale. Recommendation 3: Promote Inclusive Model Development: Ensure Earth System Model development is open and accessible to diverse stakeholders, enabling forecasters, the public, and AI/statistics experts to use, develop, and engage with the model and its predictions/projections.
title Next-Generation Earth System Models: Towards Reliable Hybrid Models for Weather and Climate Applications
topic Atmospheric and Oceanic Physics
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2311.13691