The fish is now being asked to count itself
the fish is now being asked to count itself: stereoscopic underwater cameras with computer vision estimate individual fish biomass and now dominate norwegian salmon pens, an edge system fuses sonar and optical feeds to detect schools at 0.88 map and forecast yield at 0.93 r squared on a gulf of maine dataset, and a noise robust yolov11 pipeline counts whole pond biomass from dynamic imaging sonar.
the school now files its own census.
Context
For stereo cameras, a 2024 Aquaculture paper begins from the point that salmon farming is a major part of the Norwegian food industry with welfare challenges, and earlier work covers stereo-imaging weight estimation for Atlantic salmon (a 2021 validation study and a 1996 stereo-imaging biomass paper). OptoScale, a Norwegian company, supplies camera sensor units for real-time biomass and welfare analysis at Grieg Seafood sites on Vancouver Island, per a 2022 report.
The pond sonar method is A method for noise-robust fish biomass estimation in pond aquaculture using dynamic imaging sonar (Acta Hydrobiologica Sinica, 2026), built on YOLOv11n with a frequency dynamic convolution module. It reports precision 0.886, F1 0.891 and mAP@0.5 of 0.897 on its test data, and an average per-frame detection accuracy of 86.02% in pond measurements, with a count pipeline of detection, tracking and region fusion.
The note says stereo systems now dominate Norwegian salmon pens. None of the sources read states a market share, so dominance is unsupported here, not refuted. The note's 0.88 mAP and 0.93 R squared for the Gulf of Maine edge system were not located: a Gulf of Maine result returned was a 2006 acoustic study of herring shoals, which is a different work. The sonar paper's mAP is 0.897 and is for a pond dataset, not the Gulf of Maine.
Watch next
- The paper behind the sonar and optical fusion system. A source for stereo camera adoption in Norway.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 09:06 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 →