GreenIntuition is a smart plant health diagnostic assistant. Unlike traditional apps that use rigid "if/then" rules, this project uses a Discrete Bayesian Network to model the uncertainty of nature. It acts like an expert gardener's intuition, analyzing symptoms to find the most probable root cause of a plant's distress.
The main objective is to demonstrate how Probabilistic Graphical Models can be applied to everyday life. The AI handles ambiguous cases (e.g., yellow leaves can mean both over-watering or nutrient deficiency) by weighing multiple observations to provide a high-confidence diagnosis.
- Intelligent Inference: Calculates the probability of root causes (Over-watering, Under-watering, etc.) based on 5 independent observations.
- Uncertainty Management: Can provide a diagnosis even if some information is missing or contradictory.
- Modern Dashboard: A sleek, responsive interface with real-time probability bars and smooth animations.
- Expert Logic: Uses a refined Bayesian model with direct causal links between watering and soil texture for high precision.
| Layer | Technology |
|---|---|
| Frontend | React, TypeScript, Tailwind CSS |
| Animations | Framer Motion, Lucide Icons |
| Backend | Python, FastAPI |
| AI Engine | pgmpy (Probabilistic Graphical Models) |
-
Clone the repo
git clone https://github.com/ranto-dev/GreenIntuition.git
-
Run Backend
cd backend pip install -r requirements.txt uvicorn main:app --reload -
Run Frontend
cd frontend npm install npm start