RF Event Detection from IQ Samples

About This Project

Collect short bursts of IQ samples (or RSSI based features) and classify events like interference, beacon presence, or modulation changes. Downlink only event metadata and a small sample window for verification.

Overview

The radio frequency spectrum in low Earth orbit is a complex and largely uncharacterized environment. Ground-based transmitters, other satellites, natural emissions, and interference sources all contribute to an RF landscape that varies with orbital position, time of day, and solar activity. An RF event detection payload captures short snapshots of the radio environment and uses an onboard classifier to categorize what it hears — known beacon signals, interference patterns, communication signals with identifiable modulation schemes, or anomalous events that do not match any expected pattern. Only the classification results and small representative samples are downlinked, keeping bandwidth requirements manageable while building a rich catalog of RF events correlated with time and orbital position. Over the course of a mission, this produces a unique dataset characterizing the electromagnetic environment that every satellite operates in. The project draws on signal processing, machine learning, embedded systems, and RF engineering — a challenging but highly relevant combination given the growing interest in spectrum awareness and RF intelligence from orbit.

Technical Details

Use PyCubed onboard radio (RFM9x) or add a small SDR front-end (e.g., MAX2769 for L-band or Si4463 for UHF) to capture short IQ bursts (1-10 ms windows) at scheduled intervals or triggered by RSSI threshold. Extract features: power spectral density, bandwidth, modulation type, signal duration. Classify using pre-trained random forest or small CNN on ESP32-S3. Event categories: interference, known beacon, LoRa signal, noise floor anomaly, unknown emitter. Downlink event metadata (time, position, class, confidence) plus a small raw IQ window for ground verification.

Research & Notes

Simplified version of what HawkEye 360 and Unseenlabs do commercially. IQ capture at CubeSat scale demonstrated by multiple university missions. Key constraint: PyCubed RFM9x has limited IQ capture capability — may need dedicated SDR front-end. Si4463 can output raw RSSI readings at high rate without full IQ capture for a simpler version. Feature extraction + classification is well-suited to Edge Impulse pipeline. Pairs with project 19 (GPS interference mapper) as a broader RF environment characterization experiment. Cost: $100-$500 for SDR front-end if needed. Complexity: advanced — RF signal processing + ML + embedded real-time constraints.

Required Disciplines

This project spans 3 disciplines, making it suitable for interdisciplinary student teams.

Next Steps

Ready to take on this project? Here's a general roadmap that applies to most CubeSat missions:

1. Build your foundation: Complete the core modules in the CubeSat Academy to understand spacecraft subsystems, mission design, and development workflows.
2. Form a team: Recruit students across the required disciplines and identify a faculty advisor. Plan for knowledge transfer between graduating and incoming members.
3. Write a mission concept: Draft a 1–2 page document outlining your objectives, target orbit, payload requirements, and success criteria.
4. Connect with a chapter: Join a Blackwing chapter for mentorship, shared resources, and access to the platform ecosystem.
5. Explore the developer tools: Visit the Developer Portal for platform documentation, SDKs, and hardware specs.
6. Plan your timeline: Map milestones to your academic calendar. Most projects align well with a 2–4 semester capstone or research sequence.
7. Reach out: Contact us to discuss your project goals, platform selection, and path to orbit.