Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles (2405.16297v3)

Published 25 May 2024 in cs.LG, physics.ao-ph, and physics.comp-ph

Abstract: We present a lightweight, easy-to-train, low-resolution, fully data-driven climate emulator, LUCIE, that can be trained on as low as $2$ years of $6$-hourly ERA5 data. Unlike most state-of-the-art AI weather models, LUCIE remains stable and physically consistent for $100$ years of autoregressive simulation with $100$ ensemble members. Long-term mean climatology from LUCIE's simulation of temperature, wind, precipitation, and humidity matches that of ERA5 data, along with the variability. We further demonstrate how well extreme weather events and their return periods can be estimated from a large ensemble of long-term simulations. We further discuss an improved training strategy with a hard-constrained first-order integrator to suppress autoregressive error growth, a novel spectral regularization strategy to better capture fine-scale dynamics, and finally an optimization algorithm that enables data-limited (as low as $2$ years of $6$-hourly data) training of the emulator without losing stability and physical consistency. Finally, we provide a scaling experiment to compare the long-term bias of LUCIE with respect to the number of training samples. Importantly, LUCIE is an easy to use model that can be trained in just $2.4$h on a single A-100 GPU, allowing for multiple experiments that can explore important scientific questions that could be answered with large ensembles of long-term simulations, e.g., the impact of different variables on the simulation, dynamic response to external forcing, and estimation of extreme weather events, amongst others.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. A hybrid approach to atmospheric modeling that combines machine learning with a physics-based numerical model. Journal of Advances in Modeling Earth Systems, 14(3):e2021MS002712, 2022. doi: https://doi.org/10.1029/2021MS002712.
  2. Accurate medium-range global weather forecasting with 3D neural networks. Nature, 619(7970):533–538, 2023.
  3. The green’s function model intercomparison project (gfmip) protocol. Journal of Advances in Modeling Earth Systems, 16(2):e2023MS003700, 2024.
  4. Bonavita, M. On the limitations of data-driven weather forecasting models. arXiv preprint arXiv:2309.08473, 2023.
  5. Spherical fourier neural operators: Learning stable dynamics on the sphere. In International conference on machine learning, pp. 2806–2823. PMLR, 2023.
  6. Long-term instabilities of deep learning-based digital twins of the climate system: The cause and a solution. arXiv preprint arXiv:2304.07029, 2023.
  7. Correcting a 200 km resolution climate model in multiple climates by machine learning from 25 km resolution simulations. Journal of Advances in Modeling Earth Systems, 14(9):e2022MS003219, 2024/05/24 2022. doi: https://doi.org/10.1029/2022MS003219. URL https://doi.org/10.1029/2022MS003219.
  8. Computing fourier transforms and convolutions on the 2-sphere. Advances in Applied Mathematics, 15(2):202–250, 1994. ISSN 0196-8858. doi: https://doi.org/10.1006/aama.1994.1008. URL https://www.sciencedirect.com/science/article/pii/S0196885884710086.
  9. Dynamical tests of a deep-learning weather prediction model. arXiv preprint arXiv:2309.10867, 2023.
  10. Keisler, R. Forecasting global weather with graph neural networks. arXiv preprint arXiv:2202.07575, 2022.
  11. Decadal interactions between the western tropical pacific and the north atlantic oscillation. Climate Dynamics, 26(1):79–91, 2006. ISSN 1432-0894.
  12. Fourcastnet: Accelerating global high-resolution weather forecasting using adaptive fourier neural operators. In Proceedings of the platform for advanced scientific computing conference, pp.  1–11, 2023.
  13. Learning skillful medium-range global weather forecasting. Science, 0(0):eadi2336, 2023. doi: 10.1126/science.adi2336. URL https://www.science.org/doi/abs/10.1126/science.adi2336.
  14. A simple baseline for bayesian uncertainty in deep learning. Advances in neural information processing systems, 32, 2019.
  15. Towards stability of autoregressive neural operators. arXiv preprint arXiv:2306.10619, 2023.
  16. Molteni, F. Atmospheric simulations using a GCM with simplified physical parametrizations. I: model climatology and variability in multi-decadal experiments. Climate Dynamics, 20(2):175–191, 2003. ISSN 1432-0894.
  17. Assessments of epistemic uncertainty using gaussian stochastic weight averaging for fluid-flow regression. Physica D: Nonlinear Phenomena, 440:133454, 2022.
  18. Scaling transformers for skillful and reliable medium-range weather forecasting. In ICLR 2024 Workshop on Tackling Climate Change with Machine Learning (Best Paper), 2024.
  19. FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators. arXiv preprint arXiv:2202.11214, 2022.
  20. Gencast: Diffusion-based ensemble forecasting for medium-range weather. arXiv preprint arXiv:2312.15796, 2023.
  21. Ace: A fast, skillful learned global atmospheric model for climate prediction. arXiv preprint arXiv:2310.02074, 2023.
Citations (8)

Summary

We haven't generated a summary for this paper yet.