mlsanityData to 7 Oct 2026

EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matching

arXiv 2610.09715 ↗First posted 7 Oct 2026cs.LG physics.ao-phcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

We introduce EC-EarthFlow, a generative flow matching model that emulates simulations from the physical climate model EC-Earth3. The model is trained on transient simulations from EC-Earth3 (1950-2166, SSP2-4.5) to predict the day ahead temperature field from the previous days temperature as well as annual mean temperature. Predictions are made auto-regressively with rollout periods of between a month and an extended season. Using only this variable of interest, we are able to reproduce the daily variability, spatial patterns, annual cycle and long-term trend from EC-Earth3 at a substantially lower computational cost than the physical model. We demonstrate that EC-EarthFlow is stable for long inference periods, and that it can learn the physical relationships as simulated in EC-Earth3.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 8 of its 38 references that are in the map. First posted on arXiv 7 Oct 2026.

Builds on

8 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Physics-Constrained Adaptive Flow Matching for Climate Downscaling3 Apr
  2. 2022Flow Matching for Generative Modeling6 Oct
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 5

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2024Probabilistic Forecasting with Stochastic Interpolants and F"ollmer Processescited by 61
  3. 2023ACE: A fast, skillful learned global atmospheric model for climate predictioncited by 53
  4. 2025PDE-Transformer: Efficient and Versatile Transformers for Physics Simulationscited by 29
  5. 2025A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecastingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models
  2. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulation
  3. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Models
  4. 2026Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching
  5. 2024Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models
  6. 2025Generating realistic global precipitation fields from modelled atmospheric circulation
  7. 2025Efficient Generative AI Boosts Probabilistic Forecasting of Sudden Stratospheric Warmings
  8. 2026EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting