AIMIP Phase 1: systematic evaluations of AI weather and climate models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Henn, Brian, Bretherton, Christopher S., Koldunov, Nikolay, Lessig, Christian, Molina, Maria J., Arcomano, Troy, Watt-Meyer, Oliver, Couairon, Guillaume, Singh, Renu, Brunstein, Robert, Hasson, Yana, Jost, Antonia, Brenowitz, Noah, Manshausen, Peter, Cresswell-Clay, Nathaniel, Durran, Dale, Hall, Kyle Joseph Chen, Yuval, Janni, Kochkov, Dmitrii, Hoyer, Stephan, Lopez-Gomez, Ignacio
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917510854475776
author Henn, Brian
Bretherton, Christopher S.
Koldunov, Nikolay
Lessig, Christian
Molina, Maria J.
Arcomano, Troy
Watt-Meyer, Oliver
Couairon, Guillaume
Singh, Renu
Brunstein, Robert
Hasson, Yana
Jost, Antonia
Brenowitz, Noah
Manshausen, Peter
Cresswell-Clay, Nathaniel
Durran, Dale
Hall, Kyle Joseph Chen
Yuval, Janni
Kochkov, Dmitrii
Hoyer, Stephan
Lopez-Gomez, Ignacio
author_facet Henn, Brian
Bretherton, Christopher S.
Koldunov, Nikolay
Lessig, Christian
Molina, Maria J.
Arcomano, Troy
Watt-Meyer, Oliver
Couairon, Guillaume
Singh, Renu
Brunstein, Robert
Hasson, Yana
Jost, Antonia
Brenowitz, Noah
Manshausen, Peter
Cresswell-Clay, Nathaniel
Durran, Dale
Hall, Kyle Joseph Chen
Yuval, Janni
Kochkov, Dmitrii
Hoyer, Stephan
Lopez-Gomez, Ignacio
contents We present the AI weather and climate model intercomparison project (AIMIP), phase 1. Drawing from the rich tradition of intercomparisons in climate model development, we specify a common experiment, output data format, and training constraints (namely, training against historical reanalysis data) for AIMIP Phase 1 models. We aim to identify differences in modeling frameworks and AI architectural choices that influence model behavior, and build trust in AI weather and climate models through open data and evaluation. AIMIP Phase 1 models must simulate the atmosphere given specified historical sea surface temperatures over 1979-2024. We evaluate the models' performance using five major evaluation criteria: biases, trends, response to El Niño-related sea surface temperature anomalies, temporal variability, and out-of-sample generalization tests. We find that the AI models are able to simulate the historical climate and response to forcing as well as a conventional physically-based model, but some AI models underestimate historical warming trends, and their predictions diverge in the out-of-sample generalization tests. We describe the AIMIP Phase 1 dataset that is publicly available for additional evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06944
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AIMIP Phase 1: systematic evaluations of AI weather and climate models
Henn, Brian
Bretherton, Christopher S.
Koldunov, Nikolay
Lessig, Christian
Molina, Maria J.
Arcomano, Troy
Watt-Meyer, Oliver
Couairon, Guillaume
Singh, Renu
Brunstein, Robert
Hasson, Yana
Jost, Antonia
Brenowitz, Noah
Manshausen, Peter
Cresswell-Clay, Nathaniel
Durran, Dale
Hall, Kyle Joseph Chen
Yuval, Janni
Kochkov, Dmitrii
Hoyer, Stephan
Lopez-Gomez, Ignacio
Atmospheric and Oceanic Physics
We present the AI weather and climate model intercomparison project (AIMIP), phase 1. Drawing from the rich tradition of intercomparisons in climate model development, we specify a common experiment, output data format, and training constraints (namely, training against historical reanalysis data) for AIMIP Phase 1 models. We aim to identify differences in modeling frameworks and AI architectural choices that influence model behavior, and build trust in AI weather and climate models through open data and evaluation. AIMIP Phase 1 models must simulate the atmosphere given specified historical sea surface temperatures over 1979-2024. We evaluate the models' performance using five major evaluation criteria: biases, trends, response to El Niño-related sea surface temperature anomalies, temporal variability, and out-of-sample generalization tests. We find that the AI models are able to simulate the historical climate and response to forcing as well as a conventional physically-based model, but some AI models underestimate historical warming trends, and their predictions diverge in the out-of-sample generalization tests. We describe the AIMIP Phase 1 dataset that is publicly available for additional evaluations.
title AIMIP Phase 1: systematic evaluations of AI weather and climate models
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2605.06944