PARDIG is an AI framework that generates near‑real‑time global precipitation estimates using a spherical graph‑mesh transformer trained on dense multi‑modal inputs, including atmospheric analyses and satellite imagery. It produces high‑resolution (0.1° spatial, 15‑minute temporal) precipitation fields from 2016 to the present, with a historical extension back to 1999. Evaluations against multiple radar networks and surface stations show PARDIG outperforms existing products such as IMERG, MSWEP, ERA5, and HRES, especially for extreme precipitation events, and improves the skill of the WeatherNext 3 forecasting model.
Estimating precipitation at the global scale is vital for Earth system science and disaster response, yet observational coverage and measurement precision remain constrained. Existing solutions provid...
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.
The paper introduces PRISMA, a generative framework that separates precipitation prior training from sensor-specific constraints, allowing flexible composition of heterogeneous satellite observations without retraining the core model. By integrating FY‑4B/AGRI, GPM/GMI, F16‑F18 SSMIS, and GPM/DPR‑Ka data, PRISMA consistently improves precipitation‑estimation accuracy and outperforms IMERG Final in CRPS and RMSE while maintaining positive Brier skill across thresholds. The framework supports rapid, accurate ensemble precipitation estimates, enhancing satellite‑based monitoring for hydrometeorological hazards.
arXiv:2605. 16163v2 Announce Type: replace-cross Abstract: Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that global models cannot explicitly resolve at affordable cost.
arXiv:2609.39833v1 Announce Type: new Abstract: Extreme rainfall events are increasing in intensity and frequency as climate change accelerates. While kilometer-scale precipitation forecasts are crit...
The paper presents a graph-transformer AI weather model that is fine‑tuned with high‑resolution IMERG precipitation observations, moving beyond the traditional reliance on the ERA5 reanalysis dataset. This approach yields up to a 19% improvement in medium‑range continuous ranked probability scores and a 57% better Brier skill score for extreme rainfall compared to leading operational models, while also excelling in tropical storm and drizzle prediction. The study demonstrates that directly incorporating observation‑based precipitation data into AI training can markedly enhance forecast accuracy, though physics‑based models still outperform for the heaviest events.
WeatherNext 3 is a new AI‑driven global weather model that improves both spatial and temporal resolution by generating hourly forecasts at 0.1° resolution, matching the best physics‑based models. It incorporates low‑latency geostationary satellite data and learns to predict satellite‑derived precipitation, tropical cyclones, and station observations, enabling 2 m temperature and dewpoint predictions anywhere and anytime. By directly using raw observations instead of relying solely on analysis data, WeatherNext 3 sets a new state‑of‑the‑art for probabilistic medium‑range forecasting skill.
The paper introduces a plug‑and‑play framework called Dynamics‑Precipitation Decoupling that employs a diffusion generator to convert non‑precipitation forecasts from a frozen weather model into observation‑aligned daily precipitation. The generator is conditioned on atmospheric states and satellite‑gauge precipitation estimates, using a multi‑scale recurrent encoder and cross‑attention to capture heterogeneous rainfall distributions and align daily accumulations with evolving atmospheric signals. Experiments on global and regional datasets, including a heavy‑rainfall case study in China, show that the method improves daily precipitation accuracy, event detection, and localized accumulation patterns compared to several baseline weather models and ensemble forecasts.
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:2606. 18436v1 Announce Type: cross Abstract: Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts.
arXiv:2608.12685v2 Announce Type: replace-cross Abstract: An ``Attention Residual U-Net'' method is described for probabilistic quantitative precipitation forecasting (PQPF) that predicts the hourly...
We introduce a stretched-grid artificial intelligence (AI) weather forecasting model with 2-km resolution over the western United States and part of the Northeast Pacific and approximately 31-km resol...