Tag
This paper introduces SpatioTemporal Causal Network Diagnostics (ST-CND), a framework that uses data-driven causal networks and dynamic mode decomposition to provide localized early warning of geographic tipping points, outperforming classical spatial indicators on synthetic and observational benchmarks.
This paper identifies a powerful space-based GNSS interference source over Europe, Greenland, and Canada as a constellation of Russian early warning satellites in Molniya orbits, based on data from 2019 to 2026.
Applies graph spectral analysis (Fiedler value) and Scheffer critical slowing down indicators to predict grokking in neural networks, detecting it 21,000 steps before the loss function changes, across five reproducible experiments.
Google DeepMind's WeatherNext AI model accurately predicted the intensification of 2025's Hurricane 'Melissa' into a Category 5 hurricane and its landfall in Jamaica three days in advance, issuing early warnings that likely saved many lives.