Measuring the Similarity between Materials with an Emphasis on the Materials Distinctiveness
This work addresses the challenge of choosing appropriate similarity measures for materials science applications, but it is incremental as it builds on existing methods and datasets.
The study tackled the problem of selecting similarity measures for machine learning in materials science by analyzing how well they preserve material distinctiveness, finding that measures minimizing distinctiveness loss improved prediction performance.
In this study, we establish a basis for selecting similarity measures when applying machine learning techniques to solve materials science problems. This selection is considered with an emphasis on the distinctiveness between materials that reflect their nature well. We perform a case study with a dataset of rare-earth transition metal crystalline compounds represented using the Orbital Field Matrix descriptor and the Coulomb Matrix descriptor. We perform predictions of the formation energies using k-nearest neighbors regression, ridge regression, and kernel ridge regression. Through detailed analyses of the yield prediction accuracy, we examine the relationship between the characteristics of the material representation and similarity measures, and the complexity of the energy function they can capture. Empirical experiments and theoretical analysis reveal that similarity measures and kernels that minimize the loss of materials distinctiveness improve the prediction performance.