Skillful joint probabilistic weather forecasting from marginals
Machine learning (ML)-based weather models have rapidly risen to prominence due to their greater accuracy and speed than traditional forecasts based on numerical weather prediction (NWP), recently outperforming traditional ensembles in global probabilistic weather forecasting. This paper presents FGN, a simple, scalable and flexible modeling approach which significantly outperforms the current state-of-the-art models. FGN generates ensembles via learned model-perturbations with an ensemble of appropriately constrained models. It is trained directly to minimize the continuous rank probability score (CRPS) of per-location forecasts. It produces state-of-the-art ensemble forecasts as measured by a range of deterministic and probabilistic metrics, makes skillful ensemble tropical cyclone track predictions, and captures joint spatial structure despite being trained only on marginals.
Code (0)
등록된 구현이 없습니다.
Tasks
Weather ForecastingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
Accurate weather forecasting across time scales is critical for anticipating and mitigating the impacts of climate change. Recent data-driven methods based on deep learning have achieved significant success in the medium…
Weather ForecastingContinuous Ensemble Weather Forecasting with Diffusion models
Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produ…
Weather ForecastingCRPS-LAM: Probabilistic Regional Weather Forecasting with Continuous Ranked Probability Score
Limited-Area Models (LAMs) enable weather forecasting over regional domains at higher resolutions than what is computationally feasible for global models. At such high resolutions, machine learning approaches for weather…
Weather ForecastingEfficient Generative AI Boosts Probabilistic Forecasting of Sudden Stratospheric Warmings
Sudden Stratospheric Warmings (SSWs) are key sources of subseasonal predictability and major drivers of extreme weather in winter. Accurate and efficient probabilistic forecasting of these events remains a persistent cha…
Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting
Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for subseasonal-to-seasonal (S2S…
Weather Forecasting