analiza aiqbench
This research introduces CloudCast v2, a machine learning model that bridges the gap between short-term nowcasting and longer-range forecasting by leveraging reanalysis data to correct satellite initialization errors. By employing conditional flow matching, the system achieves a 10% reduction in mean absolute error for cloud-cover prediction up to 12 hours, offering improved accuracy for solar power operations and radiation modeling.
From Nowcasting to Forecasting: Adapting a Reanalysis-Trained
arXiv:2609.03763v1 Announce Type: new Abstract: Accurate cloud-cover forecasts are important for temperature prediction, radiation forecasting, and solar-power operations. Short-range forecasting methods can preserve observed cloud placement during the first forecast hours, but their skill decreases when cloud fields evolve through formation, dissipation and deformation. Longer lead times require accounting for atmospheric evolution, but operational numerical weather prediction (NWP) forecasts may not accurately represent the satellite-observed cloud state at initialization. We develop CloudCast v2, a machine-learning model for 12-hour cloud-cover forecasting from observation-based initial conditions. The model is first trained on the Copernicus European Regional Reanalysis (Ridal2024) to learn cloud-evolution dynamics, and is then adapted to satellite-derived cloud fields using conditional flow matching (Lipman2023), a generative method that transforms noise into cloud-cover forecasts conditioned on the observed initial cloud fields and NWP inputs. CloudCast v2 reduces mean absolute error by 10% relative to its predecessor, CloudCast v1 (Partio2025), over the 1-12 h range. It also overtakes CloudCast v1 in fractions skill score, a neighborhood-based measure of spatial agreement, after approximately 3-6 h, depending on the cloudiness category. These results show that observation-initialized machine-learning forecasts can extend beyond the usual 1-3-hour nowcasting range while retaining spatial detail from satellite cloud fields.
Abstract:Accurate cloud-cover forecasts are important for temperature prediction, radiation forecasting, and solar-power operations. Short-range forecasting methods can preserve observed cloud placement during the first forecast hours, but their skill decreases when cloud fields evolve through formation, dissipation and deformation. Longer lead times require accounting for atmospheric evolution, but operational numerical weather prediction (NWP) forecasts may not accurately represent the satellite-observed cloud state at initialization. We develop CloudCast v2, a machine-learning model for 12-hour cloud-cover forecasting from observation-based initial conditions. The model is first trained on the Copernicus European Regional Reanalysis (Ridal2024) to learn cloud-evolution dynamics, and is then adapted to satellite-derived cloud fields using conditional flow matching (Lipman2023), a generative method that transforms noise into cloud-cover forecasts conditioned on the observed initial cloud fields and NWP inputs. CloudCast v2 reduces mean absolute error by 10% relative to its predecessor, CloudCast v1 (Partio2025), over the 1-12 h range. It also overtakes CloudCast v1 in fractions skill score, a neighborhood-based measure of spatial agreement, after approximately 3-6 h, depending on the cloudiness category. These results show that observation-initialized machine-learning forecasts can extend beyond the usual 1-3-hour nowcasting range while retaining spatial detail from satellite cloud fields.
Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph)
arXiv:2609.03763 [cs.LG]
(or arXiv:2609.03763v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.03763 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 293 cuvinte
Subiecte conexe
ORBIT-2 based Weather and Climate Downscaling and Downscaled Global Forecasts on AMD Instinct
AMD · 8 iun. 2026
AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS
arXiv · 28 iul. 2026
Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion
arXiv · 9 oct. 2026
SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations
arXiv · 28 aug. 2026