Pith. sign in

REVIEW 9 cited by

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

Not yet reviewed by Pith; the record is open.

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

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). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. MotifGen: Spatiotemporal interpolation of misaligned satellite images via multi-source generative modeling, in an application to tropical cyclones

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    MotifGen is the first multi-source generative model for spatiotemporal interpolation of misaligned microwave cyclone images from heterogeneous instruments at irregular intervals, achieving lower CRPS via self-supervis...

  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. 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.

  4. Decision-Aware Training for Sample-Based Generative Models

    cs.LG 2026-07 unverdicted novelty 6.0 of 10

    Augments the energy score objective for sample-based generative models with a differentiable decision loss that is itself a proper scoring rule, yielding targeted improvements on cost-sensitive regions in synthetic an...

  5. Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Tyche achieves competitive probabilistic weather forecasting skill and calibration using a single-step flow model with JVP-regularized training and rollout finetuning.

  6. U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

    cs.LG 2026-04 conditional novelty 6.0 of 10

    A standard U-Net with MAE pre-training followed by short CRPS fine-tuning via Monte Carlo Dropout matches or exceeds GenCast and IFS ENS probabilistic skill at 1.5° resolution while cutting training compute and infere...

  7. 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.

  8. Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Otter Weather is a spatiotemporal model that outperforms NWP baselines by 9.6% at 24h lead with under 3.5 A100-days training and extends efficiency gains to probabilistic forecasting via CRPS.

  9. U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

    cs.LG 2026-04 conditional novelty 5.0 of 10

    A standard U-Net with MAE pre-training plus short CRPS fine-tuning and MC Dropout matches GenCast and IFS ENS probabilistic skill at 1.5° while cutting training and inference cost by over 10×.

Pith tools