TinyML Earthquake Vibration Logger Kit with ESP32 + MPU6050
Open this project in the Soldr app → What is Soldr.ai → wiring, code and test steps for exactly these parts
TinyML Earthquake Vibration Logger Kit with ESP32 + MPU6050 — a beginner-level kit.
TinyML Earthquake Vibration Logger Kit with ESP32 + MPU6050 — AI-Powered Seismology with ESP32
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-7 days.
Ever wondered how seismologists detect earthquakes? With this kit, you’ll build your own vibration logger that uses machine learning to distinguish tremor patterns, then streams them live via MQTT. It’s a hands-on dive into AI at the edge, turning raw accelerometer data into labeled seismic events on a tiny screen and a remote dashboard.
What You'll Build
A compact, self-contained seismograph that samples MPU6050 accelerometer data, runs a TensorFlow Lite Micro model to classify vibrations, and displays results on a 0.96-inch OLED. It simultaneously publishes classification labels to an MQTT broker, so you can monitor earthquake-like gestures from anywhere—perfect for school IoT labs and hackathon demos.
What You'll Learn
- Deploy a TFLite Micro gesture classifier on an ESP32 microcontroller
- Interface an MPU6050 IMU to capture high-resolution vibration signals
- Integrate a pre-trained TinyML model that distinguishes tap, shake, and tremor patterns
- Publish real-time earthquake classification labels to an MQTT server
- Visualize detection outcomes on a 0.96-inch OLED and build a live monitoring dashboard
Kit Contents
| Component | Quantity |
|---|---|
| ESP32-S3 dev board | 1 |
| MPU6050 | 1 |
| microSD module | 1 |
| 32GB microSD card | 1 |
| 0.96in OLED | 1 |
| USB-C cable | 1 |
| Breadboard (830 + 400) | 1 |
| Jumper wires (20) | 1 |
Who This Kit Is For
Ideal for CBSE students tackling AI and IoT projects, B.Tech ECE/EEE undergraduates exploring embedded ML, and enthusiasts preparing for Smart India Hackathon challenges on disaster monitoring. It’s also a fit for ATL Tinkering Labs introducing sensor fusion and edge AI, and for anyone at IIT, NIT, or VIT looking to prototype a low-cost seismograph with machine learning.
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.
What if I get stuck during the build?
Scan the QR code to chat with the AI companion for real-time guidance, or message us on WhatsApp for human support.
Do I need to train the machine learning model myself?
No, the kit includes a pre-trained TFLite Micro model for common vibration gestures. We also provide a Google Colab notebook if you want to train custom patterns like real earthquake signatures.
How do I view the earthquake detection data remotely?
The ESP32 publishes classification labels to an MQTT broker; use any MQTT client like Node-RED, a phone dashboard, or a web interface to see live events.
Can this kit detect real earthquakes?
It’s an educational tool that classifies vibration patterns—tapping, shaking, simulated tremors—not a calibrated seismometer. Use it to understand the principles of AI-driven seismic detection.
Seismology — TFLite Micro gesture classifier on ESP32 reads MPU6050 accelerometer data and publishes gesture labels to MQTT broker.
What's in this kit
Shipping Information
- Prepaid Orders: ₹45 for orders up to ₹1,999, FREE shipping above ₹1,999
- COD Orders: ₹45 shipping for orders up to ₹1,999, FREE shipping above ₹1,999. COD available.
- Delivery Timeline: Dispatch in 3-7 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items