AI Drop: Groundbreaking model for precision spraying aims to reduce herbicide use

Contact
  1. Danish Technological Institute
  2. Projects
  3. AI Drop: Groundbreaking model for precision spraying aims to reduce herbicide use
Alea Louise Scovill

Your Contact

Contact me

Indtast venligst et validt navn
Or your phone number
?
Thank you for your message
Vi beklager

På grund af en teknisk fejl kan din henvendelse desværre ikke modtages i øjeblikket. Du er velkommen til at skrive en mail til Send e-mail eller ringe til +45 72 20 28 91.

Præcisionssprøjtning på mark

AI Drop: Groundbreaking model for precision spraying aims to reduce herbicide use

Denmark In Danish

Project Period: 1 April 2025 – 30 September 2026
Supported by IF – Innomission 24-1 (2.56 – 1642)

By combining high-resolution drone imagery, AI-driven weed detection, and precise spraying maps, we will develop a model for precision spraying that can save both chemicals and costs in agriculture.

The primary objective of the ‘AI Drop’ project is to develop a groundbreaking model that can detect weeds in crops, with a particular focus on agricultural areas in Scandinavia and Northern Europe. The model uses high-resolution drone images to generate maps of weeds and crops at centimetre-level detail. These maps enable farmers to create accurate spraying plans for precision application, significantly reducing the use of herbicides, minimising environmental impact, and enhancing farmers’ competitiveness.

Præcisionssprøjtning på markThe red colouring indicates where the herbicide has landed in the field. In this way, it is possible to determine how many weeds and what area coverage has not received precision spraying.

Technical objectives

  • An average reduction of 85% in the use of crop protection agents through precise identification and targeted control of weed-infested areas.
  • Participating farmers maintain a yield level of 95–98%.
  • At least 10% of Danish farmers will have adopted the technology, covering at least 120,000 hectares by 2026.
  • The base model can identify weeds across different crops, including wheat, barley, grass, clover, beet, spinach, and maize.
  • 97% accuracy in weed detection at centimetre-level in the generated maps.
  • The base model is to be ready for rollout in 2026 or 2027.
  • As a new feature, ‘AI Drop’ will be platform-independent, usable across different crops and regions, and offer centimetre-level accuracy. Since it will be applicable across various crops, farmers will be able to scale up weed detection, especially for “green-on-green” scenarios (e.g., grass in clover).