The lake is now being asked to file its own bloom forecast
the lake is now being asked to file its own bloom forecast: a multi horizon system called bloomnet predicts hourly algal density for the next 72 hours with uncertainty and driver indicators, a self supervised framework fuses five satellite instruments plus fluorescence data to map bloom severity and species, and a nasa tool combines multiple satellites to spot harmful blooms off florida and california.
the water now files its own bloom schedule.
Context
BloomNet is described by EurekAlert and Newswise (29 July 2026) as an interpretable deep-learning framework that forecasts harmful algal blooms at hourly resolution up to 72 hours ahead while showing how risk changes over time. The paper's abstract says earlier deep-learning approaches mostly work at daily resolution, give point predictions and rely on post-hoc explanations, and that BloomNet is aimed at hourly, uncertainty-aware and interpretable forecasts for freshwater lakes.
The self-supervised framework is SIT-FUSE. Its arXiv abstract says it fuses reflectance data from VIIRS, MODIS, Sentinel-3 and PACE with TROPOMI solar-induced fluorescence to produce bloom severity and species products without labelled data for each instrument, validated against in-situ data from the Gulf of Mexico and Southern California for 2018 to 2025. The NASA tool is the same line of work: NASA and JPL say a study in AGU Earth and Space Science reported an AI tool that fused data from five space missions or instruments and detected blooms in western Florida and Southern California.
The note joins three separate projects. BloomNet forecasts lake blooms from lake data. SIT-FUSE and the NASA tool map coastal and ocean blooms from satellites. The note's wording that the NASA tool combines multiple satellites to spot blooms off Florida and California matches the NASA release, which names K. brevis in Florida and Pseudo-nitzschia off California. The five instruments in the note's second item are the arXiv abstract's VIIRS, MODIS, Sentinel-3, PACE and TROPOMI fluorescence. The note says the framework uses fluorescence data, which matches TROPOMI solar-induced fluorescence. Whether the NASA tool and SIT-FUSE are one system is not stated in the sources read, so the note should not be read as saying so.
Related work
- the river is now being asked to file its own quality report ↗A companion note on water quality and algae monitoring from satellites.
- the kelp forest is now being asked to keep its own canopy log ↗A companion note on satellite mapping of kelp and floating algae.
Watch next
- BloomNet's performance numbers, which the sources read here did not give in comparable terms. Whether SIT-FUSE products are available for public use.
Sources
- BloomNet turns lake data into early algal bloom warnings (EurekAlert)eurekalert.org
- BloomNet turns lake data into early algal bloom warnings (Newswise)newswise.com
- Deep learning decodes multi-horizon dynamics and probabilistic risks of harmful algal blooms (paper PDF)newswise.com
- Self-supervised multi-sensor satellite framework for harmful algal bloom severity and speciation, SIT-FUSE (arXiv 2510.02763)arxiv.org
- NASA-developed AI Could Help Track Harmful Algae (NASA)nasa.gov
- NASA-developed AI Could Help Track Harmful Algae (JPL)jpl.nasa.gov
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 13:50 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 →