CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models
The article introduces the Common Task Framework (CTF) for Machine Learning in nuclear engineering, aimed at improving the evaluation of ML methods in this field. It highlights the challenges of designing nuclear systems and the potential of ML to create reliable surrogate models. The CTF seeks to standardize performance comparisons across various datasets, enhancing rigor and reproducibility in scientific ML applications for nuclear technologies.
- ▪The demand for clean energy is increasing, with nuclear technologies offering a complementary solution to renewables.
- ▪High-fidelity simulations in nuclear engineering are computationally expensive and often unsuitable for real-time applications.
- ▪The CTF evaluates ML methods on 12 established metrics and aims to replace ad hoc comparisons with standardized evaluations.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.15549 (cs) [Submitted on 15 May 2026] Title:CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models Authors:Stefano Riva, Carolina Introini, Antonio Cammi, Dean Price, Alexey Yermakov, Yue Zhao, Philippe M. Wyder, Judah Goldfeder, Jan Williams, Amy Sara Rude, Matteo Tomasetto, Joe Germany, Joseph Bakarji, Georg Maierhofer, Miles Cranmer, J. Nathan Kutz View a PDF of the paper titled CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models, by Stefano Riva and 15 other authors View PDF HTML (experimental) Abstract:The demand for clean energy is ever increasing, with new nuclear technologies presenting a complementary solution to renewable energies.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
