Good Morning,
The Department of Energy has released a solicitation entitled
Machine Learning, Artificial Intelligence, and Data Resources for Fusion Energy Sciences, which limits the number of pre-applications that can be submitted from an institution. A synopsis and information on how to secure the Harvard nomination can be found below:
DOE Machine Learning, Artificial Intelligence, and Data Resources for Fusion Energy Sciences
Harvard Expression of Interest Deadline: January 16, 2023 by 5PM
Sponsor Pre-Application Deadline: January 31, 2023
FAS/SEAS/OSP Deadline: March 8, 2023
Sponsor Full Proposal Deadline (if invited): March 15, 2023
Award Amount: AI/ML award sizes for an individual institution may range from $80,000 per year to $1,500,000 per year, with a median award size between $200,000 per year and $500,000 per year. Award sizes for multi-institutional teams may range from $750,000 to $2,500,000 per year. Anticipated award sizes for activities under the Data Resource area are expected to support procurement and operation of data servers.DOE anticipates making awards with a project period of 3 years.
The DOE SC program in Fusion Energy Sciences (FES) has announced its interest in applications in the areas of Machine Learning, Artificial Intelligence, and Data Resources for fusion energy and plasma sciences. The goal of this FOA is to support multidisciplinary teams aiming to apply advanced and autonomous algorithms to address high-priority research opportunities across the FES program. Applicants are encouraged to propose research in new systems for managing, formatting, curating, and accessing experimental and simulation data, provided in publicly available databases. Of high programmatic importance are approaches that support the realization of a fusion pilot plant on a decadal timescale.
The priority research directions encouraged under this FOA are well described by the research opportunities identified in the 2019 Report on Advancing Fusion with Machine Learning. They include activities in three broad areas: accelerating science, enabling fusion, and R&D to provide enabling computational and data resources. Applicants are encouraged to pursue the following key research directions:
- Science Discovery with Machine Learning includes approaches to bridge gaps in theoretical understanding through identification of missing effects using large datasets, accelerating hypothesis generation and testing, and optimizing experimental planning to help speed up progress in gaining new knowledge;
- Machine Learning Boosted Diagnostics involves application of methods to maximize the information extracted from measurements, enhancing interpretability with data-driven models, fusing multiple data sources, and generating synthetic diagnostics that enable the inference of quantities that are not directly measured;
- Model Extraction and Reduction includes construction of models of fusion systems and plasmas for purposes of both enhancing our understanding of complex processes and accelerating computational algorithms;
- Control Augmentation with Machine Learning involves plasma control research using control-level models improved through data-driven methods, real-time data analysis algorithms designed and optimized for control, and optimization of plasma discharge trajectories using algorithms derived from large databases;
- Extreme Data Algorithms includes methods for in-situ, in-memory analysis and reduction of extreme scale simulation data, and methods for efficient ingestion and analysis of extreme-scale fusion experimental data;
- Data-Enhanced Prediction involves algorithms for prediction of key plasma phenomena and plant system states, especially in a manner that enables real-time system state prediction, health monitoring, and fault prediction; and
- Fusion Data Machine Learning Platform includes development of systems for managing, formatting, curating, and enabling access to fusion experimental and simulation data for optimal usability in applying AI/ML algorithms.
Harvard is limited to submitting three pre-applications for this opportunity as the lead institution. To be considered for the Harvard nomination, potential applicants must submit a brief expression of interest to Erin Hale at erin_hale@fas.harvard.edu by January 16, 2023 by 5PM. Expressions of interest should be no more than one page and should include:
- Name and affiliation of PI and any Co-PIs.
- A brief description of the objectives and technical approach of the proposed research.