Interpretable model of dielectric constant for rational design of microwave dielectric materials: a machine learning study

Machine learning has advantages in studying fundamental properties of materials and comprehending structure-property correlations. In this study, we employed Sure Independence Screening and Sparsifying Operator (SISSO) method (machine learning technique) to explore the experimental dielectric constant, temperature coefficient of frequency resonator, and quality factor of inorganic oxide microwave dielectric materials. Among the constructed white-box models, the highest accuracy of R² = 0.8  for predicting the dielectric constants of the quaternary materials was observed. Additionally, we proposed a straightforward strategy to merge the ternary and quaternary datasets in a single training, aiming to address the issue of data scarcity in machine learning research. Although this strategy slightly compromises the model accuracy, it has the advantage of creating a more unified trained model for structural-property relationship understanding. Using the unified and interpretable model trained with the merged dataset, we derived a general rule governing the dielectric constant of materials. Our machine learning findings regarding the dielectric property provide fundamental insights for designing microwave dielectric materials with diverse dielectric constants.