Ragweed (Ambrosia) identification based on phenology, using high-resolution RGB drone aerial photos
CHALLENGE
Ragweed pollen is a common allergen causing yearly suffering for millions of people. A single ragweed plant can produce up to a billion pollen grains in a season, which are carried long distances by the wind. It is a major health concern in many parts of the world – also, various countries have laws imposing fines if too much ragweed is found on a property.
SOLUTION
Our partner turned to Proofminder to be able to recognize and identify ragweed on ragweed on thousands of hectares of land daily, based on plant phenology.
It only took a few weeks for visual AI development and deployment on the Proofminder platform to ensure scalability.
Ragweed detection and the calculation of infection metrics became accessible via a simple, browser-based map display, to take decisive actions.
DETAILS
- Orthomosaic is automatically created
- Multiple Machine Learning algorithms were evaluated by leveraging Proofminder’s MLOps quick iteration capabilities. SVM and Random Forest were deemed most applicable
- Infection metrics are accurately calculated according to local law
- Country-level deployment envisioned using Proofminder:
- 1st pass using satellite photos to identify potentially infected areas
- 2nd pass uses drone photos for detailed analysis and ragweed identification
- 3rd pass can focus on elimination – e.g. spraying
