[P24] Solver recommendation for transport problems in slabs using machine learning


Conference paper


Jinzhao Chen, Japan K. Patel, Richard Vasques
Proceedings of International Conference on Mathematics & Computational Methods Applied to Nuclear Science & Engineering, Portland, OR, 2019 Aug

View PDF
Cite

Cite

APA   Click to copy
Chen, J., Patel, J. K., & Vasques, R. (2019). [P24] Solver recommendation for transport problems in slabs using machine learning. In Proceedings of International Conference on Mathematics & Computational Methods Applied to Nuclear Science & Engineering. Portland, OR.


Chicago/Turabian   Click to copy
Chen, Jinzhao, Japan K. Patel, and Richard Vasques. “[P24] Solver Recommendation for Transport Problems in Slabs Using Machine Learning.” In Proceedings of International Conference on Mathematics &Amp; Computational Methods Applied to Nuclear Science &Amp; Engineering. Portland, OR, 2019.


MLA   Click to copy
Chen, Jinzhao, et al. “[P24] Solver Recommendation for Transport Problems in Slabs Using Machine Learning.” Proceedings of International Conference on Mathematics &Amp; Computational Methods Applied to Nuclear Science &Amp; Engineering, 2019.


BibTeX   Click to copy

@inproceedings{jinzhao2019a,
  title = {[P24] Solver recommendation for transport problems in slabs using machine learning},
  year = {2019},
  month = aug,
  address = {Portland, OR},
  journal = {Proceedings of International Conference on Mathematics & Computational Methods Applied to Nuclear Science & Engineering},
  author = {Chen, Jinzhao and Patel, Japan K. and Vasques, Richard},
  month_numeric = {8}
}

ABSTRACT: The use of machine learning algorithms to address classification problems is on the rise in many research areas. The current study is aimed at testing the potential of using such algorithms to auto-select the best solvers for transport problems in uniform slabs. Three solvers are used in this work: Richardson, diffusion synthetic acceleration, and nonlinear diffusion acceleration. Three parameters are manipulated to create different transport problem scenarios. Five machine learning algorithms are applied: linear discriminant analysis, K-nearest neighbors, support vector machine, random forest, and neural networks. We present and analyze the results of these algorithms for the test problems, showing that random forest and K-nearest neighbors are potentially the best suited candidates for this type of classification problem.

Share

Tools
Translate to