Film · simulated scene · real drone imagery

Finding cocoa swollen shoot before it spreads

DEMO-13, a cocoa farm at Asuopri Forest Edge in Western North: a farmer's voice note, two drones, an AI first look, a check on the ground, a lab test, and a replanted farm.

Simulated scene · real drone imagery · 2:15 · captions on screen, with voice-over
Short on time?

The 60-second cut

The same story, shortened: the survey, the AI's first look, the check on the ground and the replanting.

Simulated scene · real drone imagery · 1:00 · captions on screen, with voice-over
Step by step

What happens in the film

  1. Ama sees red veins on new cocoa leaves and sends a voice note to her hub.
  2. The hub turns it into a case and books a drone survey and a technician visit the same day.
  3. Two drones go up: one maps the farm, the other carries a hyperspectral camera, in a trial with CRIG, the Cocoa Research Institute of Ghana.
  4. The AI compares every crown with healthy ones and flags the suspect trees. A flag is a first look, not a diagnosis.
  5. A technician walks to each flagged tree: red vein banding, swollen branches, mealybugs, the insects that carry the virus.
  6. A rapid test confirms it in under an hour, a sample goes to CRIG's laboratory, and every step is sealed in the farm's passport.
  7. Under COCOBOD's programme, and with the farmer's agreement, the infected trees and the trees around them are cut and the stumps treated.
  8. Tolerant hybrid seedlings go in with plantain for shade and income. Each season the drones fly again.
Honest about it

What the film shows, and what it doesn't

The farm is a real place, drawn from a real drone survey. The trees, people, drones, the disease and the numbers on screen are simulated, and every frame says so.

Finding swollen shoot with a hyperspectral drone is not proven yet: we found no published drone study with ground truth. The pilot plans a trial with CRIG, and the film labels that step "Trial with CRIG · not yet proven".

Nothing is cut on the strength of an image. A technician and a test confirm first, and the farmer decides.

How crop disease detection works · The same steps in the app · Every video

Contact

Put the engine to work with us

For partners, investors, government programmes and operators that want to run a pilot. Your message goes straight to the Aionautics team.

Partner with us

Privacy

The contact form stores your name, email, organisation, topic, message and the time you sent it in Aionautics' own database. We use it to reply to you and don't share it.

We measure visits on our own server with no cookies and nothing sent to analytics or ad companies: pages, where you came from, country and city, device, clicks, scrolling, films watched, form fields reached (never what you type) and a masked replay of the page, kept 90 days. Opt out on this browser with this link; details on the privacy page. Fonts load from Google Fonts. To have your message deleted, write to us through the same form.

Film credits

Drone imagery: OpenAerialMap, North East Region survey flown 5 October 2021, CC BY 4.0. Earth imagery: NASA Visible Earth, Blue Marble (public domain). Borders: Natural Earth (public domain). Plants, soil, terrain and the field scenes are generated procedurally and rendered in Blender.

ModelAuthorLicence
Harvester Near Completion (modified)webbsketchesCC BY 4.0
Low Poly Combine HarvestorsiedaltonCC BY 4.0
1975 FUSO Canter T200jinjinjinCC BY 4.0
Isuzu Elf seriesRomanov_13CC BY 4.0
Mado_Ricebags (modified)Korea Heritage ServiceCC BY 4.0
Warehouse FBX Model FreeNicholas-3DCC BY 4.0
Wooden PalletsYadroGamesCC BY 4.0
Microsoft Rocketbox avatars and motion capture (clothing re-dyed)© 2020 MicrosoftMIT