Pith. sign in

REVIEW 14 cited by

AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score

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 2412.15832 v1 pith:UE2F3S5H submitted 2024-12-20 physics.ao-ph

classification physics.ao-ph
keywords ensembleforecastingforecastsaifs-crpsmodelscorecrpsloss
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as they permit to estimate the probability of weather events by representing the sources of uncertainties and accounting for the day-to-day variability of error growth in the atmosphere. This paper presents a novel approach to obtain a weather forecast model for ensemble forecasting with machine-learning. AIFS-CRPS is a variant of the Artificial Intelligence Forecasting System (AIFS) developed at ECMWF. Its loss function is based on a proper score, the Continuous Ranked Probability Score (CRPS). For the loss, the almost fair CRPS is introduced because it approximately removes the bias in the score due to finite ensemble size yet avoids a degeneracy of the fair CRPS. The trained model is stochastic and can generate as many exchangeable members as desired and computationally feasible in inference. For medium-range forecasts AIFS-CRPS outperforms the physics-based Integrated Forecasting System (IFS) ensemble for the majority of variables and lead times. For subseasonal forecasts, AIFS-CRPS outperforms the IFS ensemble before calibration and is competitive with the IFS ensemble when forecasts are evaluated as anomalies to remove the influence of model biases.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

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

  1. 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.

  2. Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction

    physics.ao-ph 2025-08 conditional novelty 7.0 of 10

    A fully observation-driven ensemble weather forecasting system, Huracan, reports CRPS skill comparable to ECMWF ENS on 75.4% of variable and lead-time combinations.

  3. FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale

    cs.LG 2025-07 conditional novelty 7.0 of 10

    A purely convolutional, spherical-geometry weather model trained with a combined spatial and spectral CRPS loss delivers GenCast-level skill, IFS-beating accuracy, and stable spectra out to 60 days.

  4. 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.

  5. MoWE : A Mixture of Weather Experts

    cs.LG 2025-09 conditional novelty 6.0 of 10

    MoWE, a ViT-based gating network, combines forecasts from Pangu, Aurora, and FCN3 with per-grid-point weights and beats each expert and the simple mean in RMSE.

  6. HRRRCast: a data-driven emulator for regional weather forecasting at convection allowing scales

    physics.ao-ph 2025-07 conditional novelty 6.0 of 10

    A diffusion-based neural network trained on HRRR analysis beats HRRR forecast skill on 20 dBZ composite reflectivity across CONUS and is competitive at 30 dBZ.

  7. Fair Box ordinate transform for forecasts following a multivariate Gaussian law

    stat.ME 2025-06 accept novelty 6.0 of 10

    A new 'fair' Box ordinate transform for multivariate Gaussian forecasts is exactly uniform whenever the forecast is calibrated, regardless of ensemble size.

  8. DEF: Diffusion-augmented Ensemble Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A conditional diffusion model that generates perturbed initial states can turn any deterministic neural weather forecast model into an ensemble, with measured error reduction on a single ERA5 case study.

  9. Evaluating Extreme Precipitation Forecasts: A Threshold-Weighted, Spatial Verification Approach for Comparing an AI Weather Prediction Model Against a High-Resolution NWP Model

    physics.ao-ph 2025-10 conditional novelty 5.0 of 10

    Combining HiRA neighborhood verification with threshold-weighted CRPS shows that AI-vs-NWP rankings for extreme precipitation depend strongly on neighborhood size.

  10. CRPS-LAM: Probabilistic Regional Weather Forecasting with Continuous Ranked Probability Score

    cs.LG 2025-10 conditional novelty 5.0 of 10

    CRPS-LAM produces 57-hour probabilistic limited-area forecasts on MEPS at diffusion-comparable accuracy with single-forward-pass sampling, roughly 39x faster than Diffusion-LAM.

  11. Statistical post-processing of operational dual-resolution wind-speed ensemble forecasts

    stat.AP 2025-06 conditional novelty 5.0 of 10

    For ECMWF wind-speed ensembles, high resolution beats large ensemble size, calibration shrinks the differences between configurations, and injecting high-resolution members into low-resolution forecasts improves skill.

  12. Probabilistic measures afford fair comparisons of AIWP and NWP model output

    stat.AP 2025-06 conditional novelty 5.0 of 10

    PC, the mean CRPS of isotonic distributional regression fitted post hoc to deterministic model output, offers a loss-function-independent way to compare AI and physics-based weather forecasts.

  13. The Rise of AI in Weather and Climate Information and its Impact on Global Inequality

    physics.ao-ph 2026-03 conditional novelty 4.0 of 10

    AI weather and climate tools inherit Northern-controlled data and compute, risking worse forecasts and maladaptation for the Global South rather than democratizing climate information.

  14. Post-processing of ensemble photovoltaic power forecasts with distributional and quantile regression methods

    stat.AP 2025-08 unverdicted novelty 4.0 of 10

    On Hungarian PV data, every tested post-processing method improves raw ensemble forecasts, and nonlinear quantile regression performs best.

Pith tools