Solver Recommendation For Transport Problems in Slabs Using Machine Learning
This work addresses solver selection for transport problems in slabs, which is an incremental improvement in a domain-specific context.
The study tested machine learning algorithms to automatically select the best solvers for transport problems in uniform slabs, finding that random forest and K-nearest neighbors performed best for this classification task.
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.