Unsupervised Machine Learning to Classify the Confinement of Waves in Periodic Superstructures
This work addresses wave confinement analysis for researchers in physics or materials science, but it is incremental as it builds on a recently presented scaling method.
The researchers tackled the problem of analyzing wave confinement in periodic superstructures by enhancing a scaling method with unsupervised machine learning, finding that a model-based clustering algorithm outperformed standard k-means++ and that combining direct scaling with clustering yields the most accurate results.
We employ unsupervised machine learning to enhance the accuracy of our recently presented scaling method for wave confinement analysis [1]. We employ the standard k-means++ algorithm as well as our own model-based algorithm. We investigate cluster validity indices as a means to find the correct number of confinement dimensionalities to be used as an input to the clustering algorithms. Subsequently, we analyze the performance of the two clustering algorithms when compared to the direct application of the scaling method without clustering. We find that the clustering approach provides more physically meaningful results, but may struggle with identifying the correct set of confinement dimensionalities. We conclude that the most accurate outcome is obtained by first applying the direct scaling to find the correct set of confinement dimensionalities and subsequently employing clustering to refine the results. Moreover, our model-based algorithm outperforms the standard k-means++ clustering.