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.
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...
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:2510. 02605v2 Announce Type: replace Abstract: While many modern studies are dedicated to ML-based large-sample hydrologic modeling, these efforts have not necessarily translated into predictive improvements that are grounded in enhanced physical-conceptual understanding.
arXiv:2608. 03822v1 Announce Type: cross Abstract: Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation.
arXiv:2606. 28546v1 Announce Type: new Abstract: Recent advances in AI-driven weather and climate modeling have improved forecast skill while reducing computational cost.
arXiv:2506. 04281v2 Announce Type: replace Abstract: Compound flooding, driven by nonlinear interactions between multiple hydrometeorological factors, poses a significant challenge to hazard prevention.
The paper proposes a method for predicting future snow water equivalent (SWE) across the Western United States by first removing spatial correlations using a Gaussian Process-based linear transformation, then training a long short-term memory (LSTM) neural network on the decorrelated data. This separation of spatial and temporal components improves predictive accuracy compared to baseline models. Additionally, the authors incorporate conformal prediction to provide distribution‑free uncertainty estimates for SWE forecasts.
Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation. Although generative models provide a promising means of data augmentation, existing methods often yield implausible spatial layouts of flooded regions and distort scene structures.
arXiv:2603.25779v2 Announce Type: replace-cross Abstract: Groundwater represents a key element of the water cycle, yet it exhibits complex and context-dependent relationships that make its modeling c...
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.
MZ‑Rain is a moisture‑budget‑guided zero‑inflated sLSTM framework designed for station‑level precipitation nowcasting. It decomposes precipitation formation into moisture storage, transport, surface evaporation, and persistence pathways, each modeled by dedicated sLSTM branches, and employs an adaptive Tweedie strategy to handle the dataset’s severe zero inflation. Experiments across varied climates show MZ‑Rain outperforms strong baselines on metrics such as CSI, FAR, MSE, and MAE, especially for heavy precipitation events.
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.