Raspberry Pi 5 Water Network Leak Detection Kit: Train a GNN to Pinpoint Leaks

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

Water utilities lose up to 40% of water to leaks. This kit gives you everything to build a real-time monitoring system that deploys a graph neural network on Raspberry Pi 5. Four flow sensors and pressure modules feed data into a GNN model that learns pressure differential patterns—then instantly identifies the leaking pipe segment. Perfect for ECE, EEE students and Smart India Hackathon teams moving from theory to a working AI IoT solution.

What You'll Build

A complete IoT pipeline: four YF-S201 flow sensors and BMP280 pressure modules connect to your Raspberry Pi 5 over I2C. High‑speed sensor data streams onto an NVMe SSD via the M.2 HAT+. The trained GNN processes the network graph in real time, and you’ll visualise leak locations on a local dashboard or trigger remote alerts. It’s a real‑world leak detection prototype you can demo, extend, or even deploy in a campus water network simulation.

What You'll Learn

• Deploy a graph neural network on Raspberry Pi 5 for live sensor data inference
• Integrate YF-S201 flow sensors and BMP280 pressure sensors over I2C
• Build a multi‑node pipe network and collect pressure differential training data
• Train a GNN to classify leak location from pressure signature patterns

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

Ideal for B.Tech ECE/EEE students working on Smart India Hackathon or mini‑project demonstrations, CBSE Class 12 students building AI‑powered physics experiments, and makers hacking water conservation solutions at ATL Tinkering Labs. If you’re exploring graph neural networks at IITs, NITs, or VIT, this kit turns theory into a deployable system you can show off.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.