CropCare AI

What inspired us?

Agriculture is essential to our country , but farmers face two major problems:

1. Detecting crop diseases early.
2. Managing crop waste after harvest without harming the environment. Many farmers do not have access to modern technology and scientific help. This gap inspired us to create an AI-powered assistant that offers straightforward , farmer-friendly solution.

What it does?

1. It detects crop health by analyzing images uploaded by the farmer.
2. It suggests remedies if diseases are found or fertilizers for further growth if the crop is healthy.
3. It recommends eco-friendly residue management tips after harvest based on the inputs crop , soil type , climate , location , fieldsize.
4. It supports English and Telugu for better accessibility.

How we built it?

1. Frontend: HTML, CSS, JavaScript; it has a clean, farmer-friendly UI.
2. Demo Logic: We used simulated AI logic to show the workflow because of time constraints.
3. Features: Language toggle (English <-->Telugu), image upload, solution cards.
4. Future Scope: CNN for detecting image-based diseases plus an ML model for managing residues.

Challenges we ran into

1. Having limited time to train and integrate a real AI model.
2. Designing a bilingual interface to make it farmer-friendly.
3. Balancing two workflows (crop health + residue management) in a single demo.

Accomplishments that we're proud of

1. Created a functional demo that demonstrates both workflows in a minimal UI.
2. Implemented language switch (English <-->Telugu) to enhance accessibility.
3. Completed AI output simulation to show real-world workflow.
4. Created a scalable concept that can scale up to be a full platform for farmers.

What we learned ?

1. How to design simple, accessible UIs for farmers.
2. Basics of simulating AI models during hackathons.
3. Importance of multi-language support in agricultural tools.
4. Practical challenges in building AI models for agriculture.

What's next for CropCare AI ?

1. Construct two independent modules: o Crop Health Detection (actual CNN model for disease detection using images). o Residue Management (ML model for sustainable practices).
2. Include fertilizer suggestions.
3. Deploy as a mobile-responsive web app for actual farmers.

Built With

• css
• html5
• javascript
• simulated-ai-logic