CRPS-LAM: Regional ensemble weather forecasting from matching marginals

2025-10-10

AI Summary

To address the slow sampling speed and high computational cost of diffusion models in regional ensemble weather forecasting, this paper proposes a single-forward-pass generative method trained directly on the Continuous Ranked Probability Score (CRPS). Innovatively integrating CRPS optimization into the Limited-Area Modeling (LAM) framework, the approach employs a single latent-variable sampling strategy coupled with conditional injection, enabling high-fidelity ensemble generation in one forward pass. Evaluated on the MEPS dataset, it achieves a 39× speedup over diffusion-based methods while preserving competitive forecast accuracy and fine-grained spatial structure. The core contribution is the first end-to-end ensemble generation framework that jointly optimizes for probabilistic calibration (via CRPS), computational efficiency (single-forward inference), and physical consistency within LAM—establishing a novel paradigm for efficient regional probabilistic forecasting.

Technology Category

• Machine Learning: Ensemble Methods
• Natural Language Processing: Generation
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Machine learning for weather prediction increasingly relies on ensemble methods to provide probabilistic forecasts. Diffusion-based models have shown strong performance in Limited-Area Modeling (LAM) but remain computationally expensive at sampling time. Building on the success of global weather forecasting models trained based on Continuous Ranked Probability Score (CRPS), we introduce CRPS-LAM, a probabilistic LAM forecasting model trained with a CRPS-based objective. By sampling and injecting a single latent noise vector into the model, CRPS-LAM generates ensemble members in a single forward pass, achieving sampling speeds up to 39 times faster than a diffusion-based model. We evaluate the model on the MEPS regional dataset, where CRPS-LAM matches the low errors of diffusion models. By retaining also fine-scale forecast details, the method stands out as an effective approach for probabilistic regional weather forecasting

Problem

• Improving computational efficiency of ensemble weather forecasting
• Generating probabilistic regional forecasts with single forward pass
• Matching diffusion model accuracy while accelerating sampling speed

Innovation

• CRPS-LAM uses CRPS-based objective for training
• It injects single latent noise for ensemble generation
• Achieves 39x faster sampling than diffusion models