MIT Receives Support from DoE to Accelerate Fusion Science and Promote Diversity
MIT’s Plasma Science and Fusion Center (PSFC) has been selected by the U.S. Department of Energy (DoE) to receive funding for a project aimed at advancing fusion science and increasing diversity in the field. The project, led by researcher Cristina Rea at the PSFC, will focus on integrating fusion data into a system compatible with AI-powered tools, with the goal of expediting progress in fusion energy research.
As concerns about climate change continue to rise, fusion energy is gaining attention as a promising source of clean and sustainable power. However, there are still considerable challenges that scientists must address in order to make fusion power a practical reality. To speed up this progress and work towards carbon neutrality by 2050, the DoE has allocated funds for the collaboration between MIT’s PSFC and four other institutions.
The three-year project aims to develop a comprehensive fusion data platform that provides unprecedented access to research data, particularly for underrepresented students. The collaboration will include scientists from William & Mary, the University of Wisconsin at Madison, Auburn University, and the nonprofit HDF Group. Significantly, the project’s co-investigators consist of four out of five women, highlighting the commitment to promoting diversity in both academia and the workforce.
The funding from the DoE will support the distribution of fusion data generated by devices such as MIT’s Alcator C-Mod, which uses powerful magnets to control fusion reactions. Alcator C-Mod, which operated from 1991 to 2016, has provided valuable data that continues to be studied. However, accessing and organizing data from various fusion devices has been challenging, with different databases requiring user agreements and inconsistent cataloging methods. The project’s data platform aims to overcome these barriers by utilizing machine learning techniques and adhering to the principles of openness and transparency in scientific research.
The platform will be built using MDSplusML, an upgraded version of the open-source software MDSplus, which was originally developed by PSFC researchers in the 1980s. MDSplus has been widely used by nearly 40 fusion research institutes for storing and sharing fusion data. The release of MDSplusML will further promote collaboration and knowledge exchange in the fusion community.
Besides addressing technical obstacles, the project also focuses on fostering inclusivity and expanding participation in fusion research. The collaboration plans to organize a subsidized summer school at William & Mary, focusing on fusion and machine learning, to provide educational opportunities for women and disadvantaged groups. By bringing together diverse perspectives and ideas, the project aims to accelerate scientific advancements in fusion.
According to Cristina Rea, the primary investigator of the project, Accessibility is absolutely essential in scientific collaboration, and we recognize that diverse communities lead to faster problem-solving. The collaboration’s efforts align with the AI for Fusion Coordinated Research Project by the International Atomic Energy Agency (IAEA). The IAEA has expressed its support for the project, stating that it will benefit not only their own initiatives but also the wider international fusion research community.
Dennis Whyte, the Director of the PSFC, commends the project’s integration of AI tools and the extraction of valuable data from experiments. He emphasizes the significance of improving the fusion ecosystem and making fusion energy a reality.
The funding and support provided by the DoE will drive MIT’s PSFC and its collaborators towards advancing fusion science while promoting diversity and accessibility. Through the integration of fusion data and AI tools, the project offers a pathway to expedite progress and achieve fusion energy’s potential as a clean energy solution for the future.
