EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Impact of Internal Variability on Benchmarking Deep Learning Climate Emulators

Björn Lütjens, Raffaele Ferrari, Duncan Watson‐Parris, Noelle E. Selin

Journal of Advances in Modeling Earth Systems · 2025-08 · 17 (8)

DOI: 10.1029/2024ms004619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advances in Modeling Earth Systems, online erschienen am 26.08.2025. Verfasst von Björn Lütjens und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Full‐complexity Earth system models (ESMs) are computationally very expensive, limiting their use in exploring the climate outcomes of multiple emission pathways. More efficient emulators that approximate ESMs can directly map emissions onto climate outcomes, and benchmarks are being used to evaluate their accuracy on standardized tasks and data sets. We investigate a popular benchmark in data‐driven climate emulation, ClimateBench, on which deep learning‐based emulators are currently achieving the best performance. We compare these deep learning emulators with a linear regression‐based emulator, akin to pattern scaling, and show that it outperforms the incumbent 100M‐parameter deep learning foundation model, ClimaX, on 3 out of 4 regionally resolved climate variables, notably surface temperature and precipitation. While emulating surface temperature is expected to be predominantly linear, this result is surprising for emulating precipitation. Precipitation is a much more noisy variable, and we show that deep learning emulators can overfit to internal variability noise at low frequencies, degrading their performance in comparison to a linear emulator. We address the issue of overfitting by increasing the number of climate simulations per emission pathway (from 3 to 50) and updating the benchmark targets with the respective ensemble averages from the MPI‐ESM1.2‐LR model. Using the new targets, we show that linear pattern scaling continues to be more accurate on temperature, but can be outperformed by a deep learning‐based technique for emulating precipitation. We publish our code and data at https://github.com/blutjens/climate‐emulator .

Zitieren

APA

Lütjens, B., Ferrari, R., Watson‐Parris, D., & Selin, N. E. (2025). The Impact of Internal Variability on Benchmarking Deep Learning Climate Emulators. Journal of Advances in Modeling Earth Systems, 17(8). https://doi.org/10.1029/2024ms004619

Vancouver

Lütjens B, Ferrari R, Watson‐Parris D, Selin NE. The Impact of Internal Variability on Benchmarking Deep Learning Climate Emulators. Journal of Advances in Modeling Earth Systems. 2025;17(8). doi:10.1029/2024ms004619

BibTeX
@article{Ltjens2025,
  author = {Lütjens, Björn and Ferrari, Raffaele and Watson‐Parris, Duncan and Selin, Noelle E.},
  title = {The Impact of Internal Variability on Benchmarking Deep Learning Climate Emulators},
  journal = {Journal of Advances in Modeling Earth Systems},
  year = {2025},
  volume = {17},
  number = {8},
  doi = {10.1029/2024ms004619}
}
Kostenlos starten →