Nuclear Fusion
Nuclear fusion reactors have the potential to produce safe and carbon-free electricity using a virtually limitless hydrogen fuel supply, but currently consume more energy than they produce.[1] While considerable scientific and engineering research is still needed, machine learning can help accelerate this work by guiding experimental design and monitoring physical processes. For instance, machine learning can help detect plasma disruptions during fusion experiments and prioritize which parameter configurations to explore.[2]
Background Readings
- "Nuclear fusion" in Nature Physics: A collection of articles on the state of nuclear fusion research. Available here.
Online Courses and Course Materials
Community
Libraries and Tools
Data
Future Directions
- "[S]peculatively, ML could help characterize this evolution and even help steer plasma into safe states through reactor control. ML models for such fusion applications would likely employ a combination of simulated and experimental data, and would need to account for the different physical characteristics, data volumes, and simulator speeds or accuracies associated with different reactor types."[2]
References
- ↑ Cowley, Steven C. (2016-05). "The quest for fusion power". Nature Physics. 12 (5): 384–386. doi:10.1038/nphys3719. ISSN 1745-2473. Check date values in:
|date=
(help) - ↑ 2.0 2.1 Rolnick, David, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross et al. "Tackling climate change with machine learning." arXiv preprint arXiv:1906.05433 (2019).