The invader is now being asked to file its own registry
the invader is now being asked to file its own registry: a deep learning system identifies 54 invasive species of management priority in china using a phone camera, a marine model updated monthly now covers 118,700 taxa, and an edge detector finds invasive crayfish underwater with 90 percent accuracy.
the ecosystem now files its own watchlist.
Context
An invasive species list is only useful if people can recognise the species. The first result puts that recognition in a phone camera: a deep learning system, described in the EyeInvaS paper, identifies 54 invasive species of management priority in China, so a member of the public can report one without a specialist.
The second result is about breadth. A marine model that is updated monthly and covers 118,700 taxa treats species coverage as something that keeps growing rather than a fixed list. The third works underwater: the UDEEP work runs computer vision on edge hardware to find invasive crayfish in place, without sending video to a server.
Phone identification relies on many volunteers, so quality depends on photos and on how well the training data covers local species. Edge detection in the water relies on a single instrument and a narrow target. One scales by people, the other by hardware, and a watchlist needs both.
Related work
- iNaturalist computer vision model updates ↗How a large public species model grows its coverage over time.
- AquaX: an enhanced AquaMaps framework to model marine species (PLOS ONE) ↗Related work on modelling marine species ranges.
Watch next
- Whether phone identification keeps its accuracy on look-alike native species, which decides false alarms.
- Field trials of edge crayfish detectors in murky or cluttered water.
Sources
- EyeInvaS: Lowering Barriers to Public Participation in Invasive Alien Species Monitoring (Animals, MDPI)mdpi.com
- Updated computer vision model and geomodel with over 1,300 new taxa (iNaturalist)inaturalist.org
- UDEEP: Edge-based Computer Vision for In-Situ Underwater Crayfish and Plastic Detection (arXiv)arxiv.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 4 October 2026 at 15:58 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 →