Dynamic Lag Encoding and Multi-Head Attention Improve Deep Learning Flood Forecasting
A deep learning model combining dynamic lag encoding and temporal multi-head attention significantly reduces peak flow forecasting errors across multi-hour ...
A deep learning model combining dynamic lag encoding and temporal multi-head attention significantly reduces peak flow forecasting errors across multi-hour ...
A two-year citizen monitoring network across seven Ugandan highland watersheds revealed that local convective rainfall and farming practices drive flash ...
HazMiner applied multilingual natural language processing to over six million global news articles from 2017 through 2024, extracting 24,407 geo-hydrological ...
High-resolution numerical simulations reveal how the steep Apennine terrain anchored a catastrophic convective storm over central Italy in September 2022 ...
A new study of Uttarakhand's Pranmati watershed finds 73 major landslides, high susceptibility along stream channels and disaster preparedness among ...
A study combines expert opinion with five large language models to produce cloudburst susceptibility mapping of Pakistan, identifying the Hindukush-Himalaya ...
An AHP-GIS study of Sunamganj district in Bangladesh finds that roughly 37 percent of the area falls within high or ...
A hybrid fuzzy–machine learning framework classifies UAV takeoff safety into Safe, Caution and Unsafe categories for Saudi date palm farms, ...
A process-informed framework combining 0.2-meter UAV topography, hydrological modeling, and interpretable machine learning classified 31 flood-prone mountainous regions in China's ...
Long-term rain-gauge observations show stronger autumn daily extremes in southern France, contrasting with northern declines, while hourly changes are more ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine