Real-Time Space Weather Event Detection and Attribution Using FPGA-Based Machine Learning on CubeSats

Aug 4, 2026

Upload by Quinn

Utah State University develops FPGA hardware accelerators and machine learning algorithms for real-time detection and attribution of space weather events on small satellites. Funded under the Low-power Array for CubeSat Edge Computing Architecture, Algorithms, and Applications (LACEC3A) and supported by NASA STMD through USTP, the work implements an XGBoost model on a low-power flash-based FPGA. The approach enables onboard intelligent decision-making for now-casting and timestamped reporting of Equatorial Plasma Bubbles (EPBs), using Space Weather Probes (SWP) sensor data.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

ABSTRACT

Introduction

Background

Equatorial plasma bubble formation

Machine learning for space weather

SSC25-RAI-04 Real-Time Space Weather Event Detection and Attribution Using FPGA-Based Machine Learning on CubeSats Benjamin Lewis, Shawn Jones, Jonathan Phillips, Charles Swenson, Kade Howes Utah State University 4120 Old Main Hill Logan, UT 84322-4120; 435-557-1682 [benjamin.lewis@usu.edu](benjamin.lewis@usu.edu) ABSTRACT Utah State University has been developing hardware accelerators and machine learning algorithms for real-time detection and attribution of space weather events on small satellites. This research, funded under the Low-power Array for CubeSat Edge Computing Architecture, Algorithms, and Applications (LACEC3A), is a NASA STMD-funded effort as part of the University Smallsat Technology Partnerships (USTP) . In this paper, we present an FPGA implementation of an AI/ML algorithm for intelligent decision-making, enabling real-time space weather monitoring and now-casting of Equatorial Plasma Bubbles (EPBs) . EPBs are low-density plasma structures that form at low latitudes within the Earth’s ionosphere, rising along magnetic field lines after sunset and persisting throughout the night. These structures cause severe scintillation in radio signals, degrading the performance of GPS and other satellite communication systems. The objective of LACE-C3A is to develop an FPGA-based edge computing platform and AI/ML processing algorithms at the CubeSat scale for a variety of detection and attribution problems. Given the global reliance on GPS for navigation, aviation, and communications, real-time detection of plasma bubbles is critical for mitigating their impacts. To achieve real-time detection, data from in-situ sensors such as Langmuir probesand impedance probes onboard CubeSats can be used to identify EPBs. Utah State University developed a suite of plasma sensors, Space Weather Probes (SWP), which flew and collected data on EPBs during the Scintillation Prediction and Observation Research Task (SPORT) mission. An XGBoost machine learning model was trained on SPORT mission electron density data from SWP to detect plasma bubbles using a desktop computer. This paper presents our research extending that work by optimizing and implementing XGBoost on a low-power flash-based FPGA for real-time inference using a custom decision tree accelerator and FFT-based feature vector creation. The FPGA processes sensor data onboard in real time, generating timestamped plasma bubble detections and attributions, which can be reported via an inter-satellite link. This FPGA-accelerated machine learning implementation will be demonstrated on the upcoming ITA-SAT2 mission. As part of the ITA-SAT2 mission, the LACE-C3A hardware and algorithms will be integrated into a constellation of three 16U CubeSats. This presentation will focus on the implementation of XGBoost on FPGA hardware, the adaptation of machine learning for space-based detection of plasma bubbles, and the expected benefits of real-time, autonomous detection and attribution from CubeSat constellations. Introduction Space weather phenomena are of particular interest to systems dependent on space-based communication. For instance, a phenomenon known as equatorial plasma bubbles can cause scintillationson RF signals passing through the ionosphere, degrading the performance of systems that rely on those signals. Equatorial plasma bubbles are depletions in electron density that form at low altitudes in the thermosphere just after sunset along the equator. Throughout the night, these depletions rise and spread along magnetic field lines. When an RF signal passes through a plasma bubble, the bubble distorts the signal, adding scintillations—seemingly random alterations in the phase of the signal. The Space Weather Probes (SWP) sensor developed by Utah State University (USU) and flownon the Scintillation Prediction Observation Research Task (SPORT)—a joint Brazil–NASA mission—provided in-situ measurements of plasma parameters, including electron density. SPORT was a

FAQs

What problem does the document address for CubeSat missions?

It targets real-time detection and attribution of space weather events, specifically equatorial plasma bubbles, using on-board AI/ML running on FPGA hardware.

What is the role of Equatorial Plasma Bubbles (EPBs) in this work?

EPBs are low-density plasma structures that cause scintillation in RF signals, degrading GPS and satellite communications; detecting them in real time is critical for mitigation.

How is the FPGA-based machine learning implemented and what model is used?

The document describes optimizing and implementing an XGBoost model on a low-power flash-based FPGA, including a custom decision tree accelerator and FFT-based feature vector creation for real-time inference.

Aug 4, 2026

Upload by Quinn