A comparison between Recurrent Neural Networks and classical machine learning approaches In Laser induced breakdown spectroscopy

TL;DR

This study compares the effectiveness of various Recurrent Neural Network architectures and classical machine learning methods in analyzing laser-induced breakdown spectroscopy data for aluminum alloy composition prediction.

Contribution

It introduces a comprehensive comparison between advanced RNN architectures, including convolutional variants, and traditional machine learning techniques for LIBS data analysis.

Findings

Convolutional Recurrent Networks outperform classical methods in prediction accuracy.

RNN-based models show significant potential for LIBS quantitative analysis.

Classical machine learning methods are less effective than RNN architectures for this task.

Abstract

Recurrent Neural Networks are classes of Artificial Neural Networks that establish connections between different nodes form a directed or undirected graph for temporal dynamical analysis. In this research, the laser induced breakdown spectroscopy (LIBS) technique is used for quantitative analysis of aluminum alloys by different Recurrent Neural Network (RNN) architecture. The fundamental harmonic (1064 nm) of a nanosecond Nd:YAG laser pulse is employed to generate the LIBS plasma for the prediction of constituent concentrations of the aluminum standard samples. Here, Recurrent Neural Networks based on different networks, such as Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Simple Recurrent Neural Network (Simple RNN), and as well as Recurrent Convolutional Networks comprising of Conv-SimpleRNN, Conv-LSTM and Conv-GRU are utilized for concentration prediction. Then a comparison is performed among prediction by classical machine learning methods of support vector regressor (SVR), the Multi Layer Perceptron (MLP), Decision Tree algorithm, Gradient Boosting Regression (GBR), Random Forest Regression (RFR), Linear Regression, and k-Nearest Neighbor (KNN) algorithm. Results showed that the machine learning tools based on Convolutional Recurrent Networks had the best efficiencies in prediction of the most of the elements among other multivariate methods.