“…In this way, the resulting hypothetical reticular structures will be combined with experimental structures (e.g., CoRE MOFs) and subjected to high-throughput calculations for property data prediction on the level of molecular dynamics (e.g., Monte Carlo simulations for gas sorption), 147,149,150 density functional theory (e.g., point charges and band structures), 148,151,152 ab initio calculations, [153][154][155] and machine-learned models. 154,155 These calculated property data can be further used for statistical analysis (e.g., linear or non-linear regression and principal-component analysis) 149,156 or machine-learning methods (e.g., support vector machine [SVM], 157,158 random forest [RF], 155,159,160 genetic algorithm [GA], 161,162 k-nearest neighbors [k-NNs], 163,164 artificial neural networks [ANNs], 154,165,166 and other higher-level models) to decipher the properties of materials (AI-assisted property studies in Figure 3).…”