AGS-PRF: Advancing Heliophysics with Automated Machine Learning and Open-Source Integration

The field of heliophysics is crucial for understanding solar phenomena and their impacts on Earth. Yet, existing datasets and tools for solar image analysis are typically semi-automated or demand intensive manual intervention, which limits research scope and speed. Moreover, there is a notable lack of artificial intelligence and machine learning-ready (AI/ML) datasets for near real time space weather forecasting. This project develops an automated, open-source pipeline utilizing AI/ML techniques to enhance the detection, segmentation, classification, and extraction of physical parameters from images captured by NASA’s Solar Dynamics Observatory (SDO). The first objective focuses on constructing ML-ready datasets through automated data processing. The second objective progresses to extracting and validating physical parameters, integrating these efforts into robust models. Finally, the third objective expands access to these advancements by establishing a comprehensive platform that disseminates these tools and data to a wider scientific community, including academic researchers and citizen scientists. The project supports an early career PI who will engage in outreach within the Atlanta community and through broader engagement such as media appearance on National Public Radio’s Weekend Science Edition.

This project creates a fully automated pipeline that leverages advanced computer vision techniques for image segmentation, feature extraction, and derivation of physical parameters from solar images. This innovation aims to enhance the efficiency, accuracy, and scalability of analyzing solar imaging data, thereby establishing new standards in the field. By automating processes that were predominantly manual or semi-automated, the project addresses a critical gap in the availability of specialized open-source ML tools for heliophysics. This accessibility empowers researchers to conduct more sophisticated analyses and fosters the development of new scientific hypotheses, democratizing access to cutting-edge technology. The implementation of state-of-the-art AI/ML technologies in this context promises to catalyze innovations across various domains of science, illustrating the profound, transformative potential of integrating modern computational techniques with conventional scientific investigation.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Award Number: 2444918
Principal Investigator: India Jackson
Funds Obligated: $202,000
State: GA