Extracting Knowledge of 2D‐Hybrid Halide Perovskite Materials: A Data Mining Approach

2D-hybrid halide perovskites are semiconductor materials with excellent optical properties that have been widely studied due to their potential as materials applicable to green energy production. Data mining techniques are powerful tools to recognize and extract relevant patterns from databases. In this study, data mining techniques are used to extract relationships among geometric characteristics, composition, and the bandgap of 2D-hybrid halide perovskites. Our analysis reveals patterns that connect the chemical properties of the organic spacer cation with the bandgap, like the distance between the halogen in the perovskite and the terminal nitrogen of the interlayer organic cation, and the relation among the type of organic interlayer cation, the interlayer distance, and the perovskite layer phase. Furthermore, it is found that aromatic cations lead to bandgaps between 2.2 and 2.4 eV. These results are consistent with previous experimental reports and provide insight into the structure-property relationships, thus illustrating the utility of data mining techniques for extracting valuable knowledge to optimize and design new materials with improved properties.