fairfolio
Saved Projects

AI Powered Plant Health Detector

CSEF · 2026 Plant Biology (Junior Division)

Manvi Karadigudda

Overview

Every year, up to 40% of crops are lost due to plant diseases and pests. The farmers whom society relies on face daily challenges in identifying plant diseases. In fact, many use their own eyes, which isn't a very reliable method. My Al invention gives these farmers a way to precisely analyze plant conditions through using computer vision, to see whether it's diseased or not. Accuracy, disease detection efficiency, and disease classification efficiency were all measured as percentages during testing. To design this invention, an Al model was trained using images from the PlantVillage Dataset, which contains both diseased and healthy pictures of tomato leaves. In order to test this model with completely new images, about 1000 leaf images from the Tomato Leaves Dataset were inputted into the model. After testing this program, results for the accuracy, disease detection efficiency, and disease classification efficiency, were calculated. The tool had an accuracy of 95.47% when tested with the PlantVillage Dataset, and 75.32% when tested with the Tomato Leaves Dataset. The disease detection efficiency was 94.97% and the overall disease classification efficiency was 89.57%. These results showed that while it could still be improved a lot further, this project offers strong potential for future plant disease detection in the real world.

Competition history

  • CSEF 2026 Plant Biology (Junior Division) · Entry J-18-11

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google