Evaluating Thermal Expansion in Fluorides and Oxides: Machine Learning Predictions with Connectivity Descriptors

The data related to the article "Evaluating Thermal Expansion in Fluorides and Oxides: Machine Learning Predictions with Connectivity Descriptors" was published in the journal of Chinese Physics B. It contains four CSV files, which are described below:We developed an algorithm for identifying and characterizing the connection patterns of structural units in open-framework structures and constructed a descriptor set for the thermal expansion properties of this system.

Our developed descriptor, aided by machine learning algorithms, can effectively learn the thermal expansion behavior in small sample datasets exhibiting complex symmetry.Table S1: The dataset of oxides and fluorides based on previous literature reports.Table S2: The feature set and labels for machine learning training on the thermal expansion behavior of oxides and fluorides.Table S3: The feature set of new binary compounds by substituting metal elements in initial binary fluorides and oxides with main group elements.Table S4: The prediction of thermal expansion behavior in new binary oxides and fluorides.