The sea is now being asked to file its own rise notice
the sea is now being asked to file its own rise notice: a lightweight cnn called caspian v2 predicts high resolution coastal flooding under different sea level scenarios for abu dhabi and san francisco faster than hydrodynamic models, a deep model called hidra d turns sparse altimetry and tide gauges into dense sea level forecasts, and a surge surrogate trained on global tide simulations maps extreme storms around new york city.
the coastline now files its own exposure map.
Context
The coastal flood CNN is described in Scientific Reports, Deep vision-based framework for coastal flood prediction under sea level rise and shoreline adaptation (January 2026), with code at CaspianNet/CASPIAN-v2 on GitHub. The repository says the model predicts coastal flooding under sea-level rise scenarios and shoreline adaptation strategies and generalizes across regions including Abu Dhabi and San Francisco. The paper frames data-driven surrogates as orders of magnitude faster than physics-based models.
HIDRA-D is a Geoscientific Model Development paper (2026), a deep-learning model for basin scale dense (gridded) sea level prediction from sparse satellite altimetry and tide gauge data. The surge model is A Deep Learning Framework for Extreme Storm Surge Modeling Under Future Climate Scenarios (Earth's Future, 2026), trained against the Global Tide and Surge Model with reanalysis and CMIP6 HighResMIP projections, with New York City as the testbed.
The note's name is written as caspian v2, and the repository is CASPIAN-v2. Its speed claim is the authors' general statement about surrogates and the excerpts read give no timing against a specific hydrodynamic model, so no speedup figure is claimed here. The note says a surge surrogate trained on global tide simulations maps extreme storms around New York City, which matches a framework using the Global Tide and Surge Model with New York City as a testbed. HIDRA-D forecasts sea level in a basin and is not a flood map.
Watch next
- Speedup figures for CASPIAN-v2 against its hydrodynamic baseline. HIDRA-D skill numbers by region.
Sources
- Deep vision-based framework for coastal flood prediction under sea level rise and shoreline adaptation (Scientific Reports)nature.com
- CaspianNet/CASPIAN-v2 (GitHub)github.com
- HIDRA-D: deep-learning model for dense sea level forecasting using sparse altimetry and tide gauge data (GMD)gmd.copernicus.org
- A Deep Learning Framework for Extreme Storm Surge Modeling Under Future Climate Scenarios (Earth's Future)agupubs.onlinelibrary.wiley.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 10:48 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 →