Weeding became the first farm job with a robot price tag
weeding became the first farm job with a robot price tag: carbon robotics’ laserweeder, trained on 150 million labeled plant images, kills about 5,000 weeds a minute across 100+ growers and cuts chemical use 70%, and john deere’s see and spray slashes herbicide 77%. one grower says the half-million-dollar machine cut his weeding bill from over a million to under $200,000 a year.
the row crop just became the app.
Context
Carbon Robotics' LaserWeeder page lists 5,000+ weeds a minute, 0.5 to 1.5 acres an hour and kills of up to 99 percent of weeds. Spudman (Apr 22, 2026) says its Large Plant Model is trained on 150 million labeled plant images from more than 175 LaserWeeder units across over 100 crops in 15 countries.
John Deere's See & Spray Select page cites 77 percent average herbicide savings; an Arkansas three-year field trial (Mar 10, 2025) found potential herbicide reductions of 43 to 59 percent.
The 150 million labeled images and 5,000 weeds a minute match Carbon Robotics. The 77 percent figure is Deere's average claim for See & Spray Select, and the Arkansas trial measured a lower 43 to 59 percent range. The 70 percent chemical cut, the 100-plus growers and the grower's half-million-dollar machine and bill figures were not seen in the sources read, so unsupported here, not refuted. Farm Progress (Oct 2023) quoted about $1.48 million for a 2024 unit, so the price in the post may be dated or a different model.
Related work
- Carbon Robotics: LaserWeeder ↗Product page.
- Spudman: laser weed control model trained on millions of images ↗Apr 22, 2026.
- University of Arkansas: See & Spray research ↗Mar 10, 2025.
Watch next
- Find the grower's cost figures and the 70 percent chemical reduction.
Sources
- Carbon Robotics: LaserWeedercarbonrobotics.com
- John Deere: See & Spray Selectdeere.com
- Farm Progress: machine fries weeds with lasersfarmprogress.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 23:48 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 →