The kelp forest is now being asked to keep its own canopy log
the kelp forest is now being asked to keep its own canopy log: deep learning maps built from satellites now track california kelp through the 2014 to 2016 marine heatwave at a resolution old tools missed, an open source tool segments kelp from sentinel 2 imagery with a semantic segmentation model, and an ai analysis of 1.2 million satellite images found a massive algae boom across the world's oceans.
the seaweed now files its own census.
Context
The open source tool is skema, a Python command-line tool on GitHub that classifies kelp in Sentinel-2 imagery with a PyTorch deep learning segmentation model. The 1.2 million image analysis is a Nature Communications paper, Global floating algae blooms are expanding, which used 1.2 million satellite images and AI with imaging spectroscopy to quantify macroalgal mats and microalgal scums in global oceans from 2003 onward. The University of South Florida and NOAA describe it as led by USF and NOAA researchers and reporting that floating algae blooms are expanding across the ocean.
The note's California kelp item says deep learning maps track kelp through the 2014 to 2016 marine heatwave at a resolution old tools missed. The specific deep-learning study was not located. Related published work that was found is Kelpwatch, a PLOS ONE tool for exploring kelp canopy dynamics and recovery from marine heatwaves, and a Frontiers in Marine Science paper on giant kelp resistance and resilience in southern and Baja California during the 2014 to 2016 heatwave, which describes that event as unprecedented in the historical record for its duration and intensity on the west coast of North America. Neither source was confirmed as the one the note means, so the resolution claim is unsupported here, not refuted. The Nature Communications paper covers floating algae, which is a different thing from kelp forests, so the note's wording that the 1.2 million image analysis found a massive algae boom refers to floating mats and scums.
Related work
- the lake is now being asked to file its own bloom forecast ↗A companion note on satellite bloom mapping.
Watch next
- The deep-learning California kelp study the note refers to. Whether skema was trained on California data.
Sources
- skema: Satellite-based Kelp Mapping using Semantic Segmentation on Sentinel-2 imagery (GitHub)github.com
- Global floating algae blooms are expanding (Nature Communications)nature.com
- Scientists harness AI to discover a rise in floating algae across the global ocean (University of South Florida)usf.edu
- Kelpwatch: A new visualization and analysis tool to explore kelp canopy dynamics (PLOS ONE)journals.plos.org
- Spatial Variability in the Resistance and Resilience of Giant Kelp in Southern and Baja California to a Multiyear Heatwave (Frontiers in Marine Science)frontiersin.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 14:04 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 →