PixelGust launched a public Model Context Protocol (MCP) server that gives AI assistants live weather, climate, terrain, and hazard data for any point on Earth, enabling tools like Claude and Cursor t…
A study using 134,376 hourly weather observations from Ioannina, Greece (2011-2026) found that hybrid CNN-GRU models outperform traditional recurrent networks in weather forecasting, achieving a Weigh…
Researchers introduced Sparse-Reslim, a plug-in routing module that reduces computational cost in ViT-based weather forecasting by processing only 25% of spatial tokens through expensive transformer b…
Researchers introduced ReMatch, a method that uses optimal transport in PCA space to align training and test-time residual distributions, reducing under-dispersion in probabilistic downscaling. In tes…
Researchers reconstructed GRACE-like terrestrial water storage anomalies back to 1940 using a spatio-temporal graph neural network (MTGNN) applied to South America. The model achieved high correlation…
Researchers developed an XGBoost model that predicts clear-air turbulence by incorporating aircraft-specific characteristics, using pilot reports (PIREPs) and ERA5 reanalysis data. The model outperfor…
Russian scientists at the Moscow Institute of Physics and Technology developed an AI algorithm that predicts extreme Arctic weather with five times higher effective resolution than global climate mode…