AgriCuke.
A smart farming app for cucumber growers. It detects diseases from a leaf photo, recommends land using IoT soil and weather data, and predicts market prices to plan sales.
[ Role ]
Flutter developer, ML integration
[ Categories ]
- Mobile (Flutter & iOS)
- AI & Automation
- IoT & Hardware
[ Stack ]
- Flutter (Dart)
- TensorFlow (image models)
- Python (ML models)
- FastAPI
- Arduino (soil sensors)
- Firebase
- Weather API
Cucumber growers often spot disease too late and sell without knowing where prices are heading. AgriCuke puts four AI tools in one Flutter app. Teammates built the models: a TensorFlow image model for Belly Rot, Downy Mildew and Powdery Mildew, a land suitability model using soil pH and moisture from Arduino field sensors plus weather, and a market price predictor. I built the Flutter app and connected it to these models through FastAPI, so a farmer can scan a leaf or check land and prices in a few taps.
- 01One app, four models. I built the Flutter app that brings disease detection, land advice, price prediction and marketing tips together on a single home screen.
- 02Photo to diagnosis. I wired the camera flow to the team's TensorFlow disease model through FastAPI, so a leaf photo returns a clear disease name in seconds.
- 03Field data to advice. The app sends land requests to the recommendation model, which combines Arduino soil pH and moisture readings with weather data.
- 04Clean model integration. Every model sits behind FastAPI, so the app talks to one simple API and models can be updated without shipping a new app version.