AI-driven early detection framework for whitefly infestations in cucumber plants in Tharaka-Nithi County-Kenya.

Edna Chebet Too, Dennis K. Muriithi and Saif Kinyori
P. O. Box 109-60400, Chuka, Kenya, Center for Data Analytics and Modeling,
Faculty of Science and Technology, Chuka University
Email: echebet@chuka.ac.ke ; dkariuki@chuka.ac.ke ; skinyori@chuka.ac.ke

Objective:

To enhance pest management, reduce yield losses, and support sustainable farming practices in Kenya.

Key Project Components

1. AI & Computer Vision: Deep learning models (CNNs) to analyze leaf images for infestation signs.
2. Farmer-Focused Deployment: Mobile app for real-time field diagnostics.
3. IoT Integration: Environmental sensors (humidity, temperature, rainfall) to improve detection accuracy.
4. Scalable Impact: Potential integration with drones and smart sprayers for precision agriculture.

Project Focus:

Develop an AI intelligent model to detect Bemisia tabaci (whitefly) infestations in cucumber crops. This initiative addresses a critical agricultural challenge faced by smallholder farmers in the region and has the potential to deliver a transformative impact through the application of advanced AI technologies.

Collaborators:

1. Prof Po Yang,
   Department of Computer Science,
   Faculty of Engineering,
   The University of Sheffield.
2. Tim Li,
   Director,
   Mutus-Tech Ltd.