# Solver Recommendation For Transport Problems in Slabs Using Machine Learning

## TL;DR

This paper explores using machine learning algorithms to automatically select the most suitable solver for transport problems in slabs, comparing five algorithms and identifying the most effective ones.

## Contribution

It introduces a machine learning-based approach to auto-select solvers for transport problems, demonstrating the effectiveness of random forest and K-nearest neighbors.

## Key findings

- Random forest and K-nearest neighbors perform best for solver classification.
- Machine learning can effectively automate solver selection in transport problems.
- Support vector machine, neural networks, and linear discriminant analysis are less effective.

## 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.