Landing page
Login page
User dashboard
Farm Updates
Updates 2
Adding farm using geographical location
Alerts if soil need irrigation
Specific farm
Alert mail to user
Ai Advisory

Inspiration

We were inspired by the increasing problem of water wastage in agriculture and the difficulty farmers face in deciding when and how much to irrigate. We wanted to build a system that uses real-time soil moisture and weather data to support smarter irrigation decisions.

What it does

Precision Irrigation Advisory (PIAS) collects soil moisture data using ESP32 sensors and combines it with live weather information. It analyzes these inputs and provides irrigation recommendations to help reduce unnecessary water usage and prevent crop stress.

How we built it

We developed PIAS using Spring Boot 3 microservices, ESP32 with capacitive soil moisture sensors, Open-Meteo weather data, and Google Gemini AI. The sensor and weather data are processed by the backend, while the AI generates practical agronomic recommendations. Automated notifications help deliver important alerts to users.

Challenges we ran into

Our main challenges were connecting the ESP32 hardware with the software system, handling real-time sensor data, integrating multiple APIs and microservices, and ensuring that AI-generated recommendations were relevant and understandable.

Accomplishments that we're proud of

We successfully integrated IoT, real-time weather data, AI, and backend microservices into a single working precision-agriculture solution. We are especially proud of converting raw sensor data into actionable irrigation recommendations.

What we learned

We learned how to build and integrate an end-to-end IoT and AI system. We gained practical experience with ESP32 hardware, REST APIs, Spring Boot microservices, AI integration, real-time data processing, and system debugging.

What's next for Precision Irrigation Advisory Using Soil Moisture & weather

We plan to improve PIAS by adding more sensors, supporting more crops and soil types, improving AI-based crop and yield predictions, adding mobile notifications, and developing more personalized irrigation recommendations based on historical field data.