Pith. sign in

REVIEW 7 cited by

ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.12971 v1 pith:W2VGJJXL submitted 2024-12-17 cs.LG

Guillaume Couairon , Renu Singh , Anastase Charantonis , Christian Lessig , Claire Monteleoni This is my paper · ORCID
classification cs.LG
keywords weathermodelsarchesweathergenarchesweatherdeterministicforecastingera5model
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Weather forecasting plays a vital role in today's society, from agriculture and logistics to predicting the output of renewable energies, and preparing for extreme weather events. Deep learning weather forecasting models trained with the next state prediction objective on ERA5 have shown great success compared to numerical global circulation models. However, for a wide range of applications, being able to provide representative samples from the distribution of possible future weather states is critical. In this paper, we propose a methodology to leverage deterministic weather models in the design of probabilistic weather models, leading to improved performance and reduced computing costs. We first introduce \textbf{ArchesWeather}, a transformer-based deterministic model that improves upon Pangu-Weather by removing overrestrictive inductive priors. We then design a probabilistic weather model called \textbf{ArchesWeatherGen} based on flow matching, a modern variant of diffusion models, that is trained to project ArchesWeather's predictions to the distribution of ERA5 weather states. ArchesWeatherGen is a true stochastic emulator of ERA5 and surpasses IFS ENS and NeuralGCM on all WeatherBench headline variables (except for NeuralGCM's geopotential). Our work also aims to democratize the use of deterministic and generative machine learning models in weather forecasting research, with academic computing resources. All models are trained at 1.5{\deg} resolution, with a training budget of $\sim$9 V100 days for ArchesWeather and $\sim$45 V100 days for ArchesWeatherGen. For inference, ArchesWeatherGen generates 15-day weather trajectories at a rate of 1 minute per ensemble member on a A100 GPU card. To make our work fully reproducible, our code and models are open source, including the complete pipeline for data preparation, training, and evaluation, at https://github.com/INRIA/geoarches .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Timestep-Conditioned Transformers for Global Weather Forecasting

    cs.LG 2026-08 conditional novelty 7.0 of 10

    A single weather transformer with inference-time timestep conditioning matches specialist models across 1 to 24 hour steps and improves rollout stability under mixed-timestep training.

  2. AI-boosted rare event sampling to characterize extreme weather

    physics.ao-ph 2025-10 conditional novelty 7.0 of 10

    AI+RES uses AI weather-forecast ensembles as a guide for rare-event simulation, yielding accurate return-period statistics for 1-in-50,000-year heatwaves at roughly 100× lower computational cost.

  3. Skillful joint probabilistic weather forecasting from marginals

    cs.LG 2025-06 conditional novelty 7.0 of 10

    FGN, a neural weather model trained only on per-location forecast scores, produces more accurate global ensemble forecasts than GenCast and captures realistic spatial correlations.

  4. Weather Emulators at the Frontier of Heat Extremes Predictability

    physics.ao-ph 2026-07 accept novelty 6.0 of 10

    At 10–15 day leads, AI weather emulators can match or beat dynamical models on global temperature skill but under-represent heat-extreme intensity and lose to IFS on recall.

  5. Scaling Laws of Global Weather Models

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Across five global weather models, validation loss follows power-law scaling, with wider architectures and larger training datasets outperforming deeper or smaller-data configurations.

  6. LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A latent diffusion model generates medium-range global weather ensembles at 1.5 degrees that match ECMWF IFS-ENS deterministic skill at lower compute, with weaker probabilistic spread and anecdotal cyclone advantages.

  7. Diffusion-LAM: Probabilistic Limited Area Weather Forecasting with Diffusion

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A diffusion-based limited area weather model that uses future boundary conditions from a global model improves short-lead forecast accuracy and boundary consistency.

Pith tools