Is this project an undergraduate, graduate, or faculty project?
Undergraduate
Project Type
group
Campus
Daytona Beach
Authors' Class Standing
Kylie Nager, Junior
Lead Presenter's Name
Kylie Nager
Lead Presenter's College
DB College of Engineering
Faculty Mentor Name
Dr. Cagri Kilic
Abstract
HELIO: Heliophysics Enhanced Learning for Intelligent Orbits Satellite constellations operating in near-Earth space are increasingly vulnerable to space weather disturbances, such as solar flares, coronal mass ejections (CMEs), and high-speed solar wind streams, which degrade communications, destabilize attitude control, and accelerate orbital decay. These disturbances directly threaten mission continuity, constellation availability, and space asset survivability. Current protective approaches rely primarily on ground-based alerts and lack integration with broader space domain awareness, which results in programmed reactive protocols that are often initiated too late to prevent performance degradation and asset loss. The HELIO project addresses this gap by turning space-weather forecasts into real-time operational decisions for Small Satellite swarms. Using an artificial intelligence (AI) heliophysics foundation model to produce solar weather forecasts of these incoming disturbances, our decision-action intelligence layer will interpret the predictive outputs and converts them into spacecraft-level operational modes. Forecast indicators of solar wind velocity, flare probability, and coronal activity will map to three operational condition categories (Normal, Moderate, and Severe), each linked to a swarm mode (Nominal, Harden, Safe). This chain lets Small Satellites switch modes before geomagnetic disturbances occur thereby increasing their resilience. Current work involves evaluating our heliophysics AI model against existing ground-based solar weather prediction systems such as NOAA and CelesTrak. This evaluation will quantify predictive accuracy and assess our model's potential for complementing current capabilities while reducing response latency. From testing, we expect to prove that the AI heliophysics model is capable of efficient and reliable forecasts for future use in our decision intelligence system.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Included in
Artificial Intelligence and Robotics Commons, Multi-Vehicle Systems and Air Traffic Control Commons, The Sun and the Solar System Commons
HELIO: Heliophysics Enhanced Learning for Intelligent Orbits
HELIO: Heliophysics Enhanced Learning for Intelligent Orbits Satellite constellations operating in near-Earth space are increasingly vulnerable to space weather disturbances, such as solar flares, coronal mass ejections (CMEs), and high-speed solar wind streams, which degrade communications, destabilize attitude control, and accelerate orbital decay. These disturbances directly threaten mission continuity, constellation availability, and space asset survivability. Current protective approaches rely primarily on ground-based alerts and lack integration with broader space domain awareness, which results in programmed reactive protocols that are often initiated too late to prevent performance degradation and asset loss. The HELIO project addresses this gap by turning space-weather forecasts into real-time operational decisions for Small Satellite swarms. Using an artificial intelligence (AI) heliophysics foundation model to produce solar weather forecasts of these incoming disturbances, our decision-action intelligence layer will interpret the predictive outputs and converts them into spacecraft-level operational modes. Forecast indicators of solar wind velocity, flare probability, and coronal activity will map to three operational condition categories (Normal, Moderate, and Severe), each linked to a swarm mode (Nominal, Harden, Safe). This chain lets Small Satellites switch modes before geomagnetic disturbances occur thereby increasing their resilience. Current work involves evaluating our heliophysics AI model against existing ground-based solar weather prediction systems such as NOAA and CelesTrak. This evaluation will quantify predictive accuracy and assess our model's potential for complementing current capabilities while reducing response latency. From testing, we expect to prove that the AI heliophysics model is capable of efficient and reliable forecasts for future use in our decision intelligence system.