Special Issue on Machine Learning, Data Science, and Artificial Intelligence in Plasma Research
Bibliographic record
Abstract
This Special Issue of the IEEE Transactions on Plasma Science (TPS) follows the first American Physical Society Division of Plasma Physics (APS-DPP) mini-conference on Machine Learning, Data Science, and Artificial Intelligence in Plasma Research held during the 60th APS-DPP Meeting in Portland, OR, USA (November 5–9, 2018). It contains selected highlights from not only the mini-conference but also the broader plasma physics community. Although data science has a long and rich history in plasma physics, dating back at least three decades, it is experiencing a renaissance, thanks in large part to the advances outside of plasma physics. Novel algorithms, hardware, and analytic techniques (buoyed by the open source software ecosystem) have led plasma scientists to explore ways in which the data revolution could accelerate and inform scientific discovery. Emerging data-driven methods could have a transformative effect across the full spectrum of plasma research. For fusion energy research, some areas of opportunities [item 1) in the Appendix] include using machine learning (ML) or data methods for scientific discoveries, augmented instrumentation, accelerated model development and simulations, data-informed intelligent controls of the experiment, and data-enhanced predictions. The DPP mini-conference and the articles herein represent only a tiny cross section of contemporary research on data-driven plasma science. The 3rdInternational Conference on Data-Driven Plasma Science (ICDDPS-3) will be held in Okinawa, Japan, in April 2020 [item 2) in the Appendix], with expected presentations on fusion plasmas and low-temperature plasmas and beyond. Furthermore, Plasma Science is not unique in its exploration of Scientific Machine Learning: the Second Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019, Vancouver, BC, Canada, December 2019) and it illustrates a trend in cross disciplinary collaboration with contributions from plasma research.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.009 | 0.006 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.004 | 0.007 |
| Insufficient payload (model declined to judge) | 0.154 | 0.069 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".