The wave is now being asked to file its own warning
the wave is now being asked to file its own warning: nasa's guardian network caught tsunami disturbances in satellite navigation signals within eight minutes of the earthquake, a physics informed network assimilates offshore pressure data to map coastal waves before they arrive, and neural surrogates trained on thousands of tsunami simulations estimate wave heights on standard cpus.
the ocean now files its own evacuation note.
Context
NASA describes GUARDIAN (GNSS Upper Atmospheric Real-time Disaster Information and Alert Network) as experimental software that detects slight distortions in satellite navigation signals. For the magnitude 8.8 earthquake off Russia on 29 July 2025, NASA says its AI-powered detection algorithms spotted the disturbances as soon as eight minutes after the quake, and flagged an incoming wave west of Hawaii some 32 minutes before it made landfall and was detected by tide gauges.
For neural surrogates, the nearest match is a 2026 preprint on a factorized Fourier neural operator surrogate for basin-scale tsunami propagation (egusphere). It reports timing errors of about 8 to 12 minutes and run times of 8.5 to 12 seconds per scenario on a single GPU, against 87.9 to 95.7 seconds for the COMCOT simulator.
The eight minutes matches NASA's page, where it is the earliest detection of disturbances in the signals, not a tsunami warning issued to the public. The note says wave heights on standard CPUs. The surrogate found runs on a GPU, so the CPU claim is unsupported here, not refuted. The physics informed network assimilating offshore pressure data was not located: the PINN results returned were for ocean waves and for a Valparaiso tsunami model, and neither was confirmed as the one meant.
Watch next
- The paper behind the offshore pressure PINN. Whether a CPU surrogate with thousands of simulations is published.
Sources
- See NASA's GUARDIAN Catch a Tsunami (NASA)nasa.gov
- See NASA's GUARDIAN Catch a Tsunami (JPL)jpl.nasa.gov
- A Factorized Fourier Neural Operator Surrogate for Basin-Scale Tsunami Propagationexa.ai
- Modeling Tsunami Waves at the Coastline of Valparaiso Area of Chile with Physics Informed Neural Networks (ICCS 2024)iccs-meeting.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 11:03 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →