Digital Journal

Advances in deep learning assist with weather prediction

Accurate weather predictions are essential for modern economies, such as farming and shipping, as well as being required by governments (such as issuing flood warnings or alerting the populace to a ...
Nature

A deep learning-based land-atmosphere coupled model for heatwave prediction

Extreme heatwaves are intensifying under climate change, yet their prediction remains limited by inadequate representation of land–atmosphere (L–A) interactions. Most deep learning–based weather ...
WPLG Local 10

AI weather models changing the hurricane forecast game

The 2025 hurricane season was a coming-of-age story for AI weather models, which have been around in some capacity since ...
Nature

SIGMAformer: a spatiotemporal Gaussian mixture correlation transformer for global weather forecasting

SpatIotemporal Gaussian Mixture correlAtion transformer (SIGMAformer) is a spatiotemporal forecasting architecture that integrates a Gaussian mixture pattern extractor (GMPE) with a dynamic ...
Phys.org

Deep learning turns weather satellite thermal imagery into hourly ocean current maps

Scientists have developed a new method to measure ocean surface currents over large areas in greater detail than ever before. Called GOFLOW (Geostationary Ocean Flow), the approach applies deep ...
Frontiers

Hybrid Hydroinformatics: Integrating Machine Learning and Process-Based Modeling for Climate-Resilient Water Systems

The hydrologic system is subjected unprecedented stresses and increasing demands driven by climate variabilities, landuse changes, groundwater ...

AI model predicts wildfire risk a month out with greater accuracy

A new AI technology can predict wildfire risk up to a month in advance with greater accuracy than existing methods. The ...