Harnessing Fusion Energy through Artificial Intelligence

The MIT Plasma Science and Fusion Center (PSFC) has secured support from the U.S. Department of Energy (DoE) to enhance fusion data accessibility and promote workforce diversity in fusion research. As the urgency to combat climate change grows, interest in fusion as a clean energy solution is on the rise. Fusion research has been ongoing since the 1930s, but numerous critical questions must be addressed to make fusion power a practical reality.

In pursuit of their goal to expedite fusion energy development and attain carbon neutrality by 2050, the DoE has announced funding for a collaborative project led by researchers from MIT’s PSFC and four partner institutions. Cristina Rea, a research scientist and group leader at PSFC, is the principal investigator for this three-year initiative aimed at integrating fusion data into a format readable by AI-driven tools.

The PSFC, in collaboration with scientists from William & Mary, the University of Wisconsin at Madison, Auburn University, and the nonprofit HDF Group, intends to create a comprehensive fusion data platform. This platform is poised to provide unprecedented access for researchers, particularly underrepresented students, fostering diverse participation in fusion and data science both in academia and the workforce. Notably, four out of five co-investigators on the project are women.

The DoE’s funding, part of a $29 million allocation for seven projects spanning 19 institutions, will facilitate the dissemination of data generated by fusion devices, such as the PSFC’s Alcator C-Mod, a toroidal “tokamak” that employs powerful magnets to control and confine fusion reactions. Alcator C-Mod operated from 1991 to 2016, and its data remain a subject of study, thanks to the PSFC’s commitment to open knowledge sharing.

Presently, access to historical and current data from the nearly 50 public magnetic confinement-type fusion devices is challenging, with some databases requiring user agreements and varying data organization. Leveraging machine learning for data analysis and scientific discovery is hindered by these obstacles, resulting in fewer scientists working on fusion, impeding discovery, and delaying the utilization of AI for progress.

To address these challenges, the project’s proposed data platform adheres to the FAIR (Findable, Interoperable, Accessible, Reusable) principles and UNESCO’s Open Science recommendations, enhancing the transparency and inclusivity of scientific research. All deliverables from the researchers will align with FAIR and Open Science principles as mandated by the DoE.

The platform’s databases will be constructed using MDSplusML, an upgraded version of the MDSplus open-source software developed by PSFC researchers in the 1980s to catalog Alcator C-Mod’s experimental results. Today, nearly 40 fusion research institutes employ MDSplus to store and provide external access to their fusion data. The release of MDSplusML aims to continue this tradition of open collaboration.

In addition to improving data accessibility, the researchers plan to address participation barriers for women and disadvantaged groups by offering a subsidized summer school focused on fusion and machine learning topics. This summer school will be hosted at William & Mary for the next three years.

Cristina Rea emphasizes the significance of their research, stating, “This project is about responding to the fusion community’s needs and setting ourselves up for success. Scientific advancements in fusion require multidisciplinary collaboration and diverse perspectives for faster problem-solving.”

This collaboration aligns with research priorities outlined in the International Atomic Energy Agency’s “AI for Fusion” Coordinated Research Project (CRP). Cristina Rea serves as the technical coordinator for the IAEA’s CRP, emphasizing community engagement and knowledge access to accelerate fusion research and development. In a letter of support, the IAEA acknowledges that the researchers’ work will benefit not only their CRP but also the global fusion community.

Dennis Whyte, the PSFC Director and Hitachi America Professor of Engineering, expresses his enthusiasm for the project, stating, “I am thrilled to see PSFC and our collaborators at the forefront of applying new AI tools while simultaneously enabling the extraction of critical data from our experiments.”

Cristina Rea concludes by emphasizing the importance of her role and the team’s motivation, stating, “Having the opportunity to lead such an important project is extremely meaningful, and I feel a responsibility to show that women can be leaders in STEM. We have an incredible team, strongly motivated to improve our fusion ecosystem and contribute to realizing fusion energy.”

Recommended Articles

Leave a Reply