Machine Learning Tools for Predicting Solar Energetic Particle Hazards

Solar Energetic Particles (SEPs) are among the most hazardous transient phenomena of the solar activity. Accelerated during solar flares or in shock wave fronts of coronal mass ejections (CMEs), SEPs propagate through the heliosphere and interact with the space environment. Representing hazardous radiation, SEPs may affect health of astronauts in the open space and create difficulties for the future space exploration. Therefore, improvement of the SPE forecasts using machine-learning technologies is a very timely task. In order to discover relationships among precursors and properties of the SPEs, and associated observational data, the incoming data and metadata need to be processed and integrated into a comprehensive database. This database will enable the development of targeted applications of modern machine learning and data analysis techniques to enhance reliability of the SEP forecasts, proposed in this investigation. The primary objective of the research is to enhance predictions of solar energetic particles (SEP) by implementing automatic data characterization and machine-learning tools. The project pursuits two main goals: 1) development of an online-accessible automatically-updated database that integrates the solar and heliospheric data, metadata, and descriptors related to SPEs; 2) development of robust all-clear forecasts of SPEs with low false-alarm rates, and adapted to operational data availability. Using the developed data resources, tools and methodologies, the team will achieve a transformative change from the current low Technology Readiness Level (TRL) to high-TRL in these tasks.

This project provides robust “all-clear” forecasts enabling possibilities for safe space exploration and advanced mission planning, while providing the availability of the prepared and integrated data for the heliophysics community. There are data discovery possibilities for the broader community and will replace the current operational forecasting techniques by machine learning-based approaches.

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.