arXiv:2611.08255v1 Announce Type: new Abstract: High-resolution tropical cyclone surface wind speeds derived from synthetic aperture radar (SAR) observations can support storm structure and intensity...
arXiv:2607. 27152v1 Announce Type: new Abstract: Accurate intraday forecasts of offshore wind are becoming increasingly important for power system operation and the integration of growing shares of offshore wind energy.
arXiv:2607. 16080v1 Announce Type: new Abstract: Precipitation nowcasting over the immediate 10-90 min period is important for flood management and real-time decision-making in urban regions.
arXiv:2510. 16031v2 Announce Type: replace-cross Abstract: Machine learning-based precipitation nowcasting relies on high-fidelity radar reflectivity sequences to model the short-term evolution of convective storms.
The study evaluates machine learning techniques for detecting weather fronts using satellite data, comparing a model that relies solely on geostationary infrared observations with one that also incorporates 28 ERA5 reanalysis fields. The satellite-only model achieves a neighbourhood critical success index (CSI@150) of 0.402, while the combined satellite and reanalysis model improves this metric to 0.575, a gain of 0.173. The analysis indicates that low‑level winds are poorly predicted from satellite imagery alone (R² = 0.23) and that excluding wind or moisture variables from the model leads to the most significant drops in detection performance.
The paper presents Laxmi, a retrained version of the AIFS weather model that uses satellite-based precipitation observations instead of ERA5 reanalysis data. Laxmi achieves a 19% improvement in global probabilistic accuracy, reduces drizzle overprediction by 33%, and boosts the 95th percentile Brier skill score by 57%. In a case study of 10 Indian tropical storms, Laxmi accurately forecasted 150 mm event-total precipitation in 7 events, outperforming both the original AIFS and the leading physical model IFS.
TC-Next is a multimodal deep learning model that forecasts tropical cyclone track and intensity for 6‑24 hour lead times by combining atmospheric forecast fields from a foundation model with GridSat infrared satellite imagery. Trained solely on GraphCast forecasts for the Western Pacific, it reduces track error by 15‑44% and intensity error by a factor of 3‑6 compared to the rule‑based tracker TempestExtremes, and maintains superior performance when applied zero‑shot to other forecast systems such as Pangu‑Weather, IFS HRES, and WeatherNext Cyclones. Ablation studies confirm that incorporating the additional satellite modality consistently improves tracking accuracy at all lead times and enhances intensity predictions, especially at longer horizons.
The paper introduces Nested‑EAGLE, a 0.25° global weather model with a 6 km refinement over the contiguous United States, designed to merge short‑ and medium‑range forecasts into a single system. It shows lower mean‑squared error for near‑surface and low‑level variables over the U.S. compared to NOAA’s GFS and HRRR, while remaining competitive globally. Although precipitation forecasts are less skillful than HRRR’s deterministic training, Nested‑EAGLE delivers the most accurate storm‑location predictions at longer lead times, with blurred extrema.
Huayu-Global is a cross‑constellation deep‑learning system that fuses data from three geostationary sensor streams across five satellites to produce coherent quasi‑global precipitation fields every thirty minutes. By combining multiple satellite observations, it improves event detection and precipitation‑amount estimation compared to existing real‑time products, achieving skill levels comparable to delayed‑product releases. The system offers a scalable framework that can incorporate future geostationary missions into hydrological and weather‑prediction applications.
Satellite precipitation products face a persistent trade-off: real-time estimates are timely but less accurate, whereas the most reliable products are often released months after observation. This del...
arXiv:2602. 17683v3 Announce Type: replace Abstract: Short-term forecasting of vegetation dynamics is a key enabler for data-driven decision support in precision agriculture.
arXiv:2606. 08563v1 Announce Type: new Abstract: While global data-driven models excel at predicting continuous atmospheric variables, three-dimensional hydrometeor forecasting remains challenging due to the zero-inflated, long-tailed distributions of these variables.