arXiv:2606. 00281v1 Announce Type: cross Abstract: Generative machine learning is an increasingly important complement to dynamical downscaling for producing high-resolution precipitation projections, with diffusion models currently the leading approach.
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 study compares the Weather Research and Forecasting (WRF) dynamical model with an unpaired diffusion-based generative model for downscaling extreme precipitation events up to three weeks ahead. Both models outperform raw European Centre for Medium-Range Weather Forecasts forecasts when evaluated against Swiss rain gauge-radar observations, but their strengths differ by atmospheric regime: WRF excels in a multicell, non‑stationary event, while the diffusion model performs more consistently and better in a stationary supercell event.
PCSDiff is a diffusion-based framework designed to correct systematic biases and enhance spatial resolution in medium-term (10‑day) precipitation forecasts. It uses a Precipitation Intensity‑aware Multi‑branch Decoder to mitigate dynamic multi‑day errors and a two‑phase conditional diffusion super‑resolution module to restore fine‑scale rainfall patterns. Evaluated over China, PCSDiff reduces RMSE by 16.1% and increases ACC by 13.9% compared to raw ECMWF forecasts, outperforming mainstream deep‑learning baselines and enabling low‑latency rolling forecasts for operational use.
arXiv:2606. 14570v1 Announce Type: cross Abstract: Emulators provide a cost-effective alternative to regional climate models (RCMs) by capturing their dynamical downscaling function.
arXiv:2604. 03275v2 Announce Type: replace-cross Abstract: Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making.
arXiv:2602. 13416v2 Announce Type: replace Abstract: The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating exceptional skill in medium-range forecasting.
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.
The study evaluates how well wavelet-diffusion models (WDM) for precipitation downscaling generalize across different U.S. regions and precipitation regimes. A WDM trained only on Oklahoma data performs competitively in other regions, while a model trained on all six regions achieves the best overall image-domain and detection performance, though improvements vary with precipitation intensity. The analysis shows a strong correlation between spatial autocorrelation (Moran's I) and detection success, indicating that model performance is linked to the spatial organization of precipitation fields.
The study evaluates three conditioning strategies for a denoising diffusion probabilistic model to downscale daily precipitation for the Colorado River Basin. Channel concatenation of upsampled coarse predictors yields the lowest point‑wise CRPS and MSE but tends to over‑smooth high‑intensity events. Cross‑attention conditioning—both with a learned encoder and with the frozen encoder of the pretrained Prithvi‑WxC weather foundation model—provides better distributional realism, improved spectral fidelity, and stronger performance on extreme events, especially when data are limited.
arXiv:2609.37038v1 Announce Type: cross Abstract: Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling...
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.
The paper introduces RaiNet, a data‑driven model that jointly learns multiscale water‑quality dynamics and station‑specific rainfall effects. It uses LocTrend to capture irregular water‑quality patterns, constructs station‑oriented rainfall events from gridded precipitation, and applies XGateFusion for lag‑aware fusion across scales. Experiments on three new multimodal datasets show RaiNet surpasses existing time‑series, water‑quality, diffusion‑based, and spatiotemporal models by over 20%, with each module contributing uniquely to performance.