<![CDATA[Metal-Organic Frameworks (MOFs) are a special class of organic-inorganic hybrid materials widely known for their regular and periodic crystal structures. MOFs are composed of metal ions or clusters connected by organic linkers that form a three-dimensional lattice-shaped series. The advantage of MOFs is their ability to capture guest molecules in their pores. Based on these capabilities, MOFs can be utilized in various applications such as gas absorption and separation processes, catalysts, and therapeutic compound delivery systems. Currently, in creating new materials, the MOFs synthesis process still applies a conventional trial-and-error approach that has the potential for high failure rates. The purpose of this study is to develop a machine learning model as an efficient tool design in creating new MOFs materials before the experimental process is carried out. This study implements the SMOTE and AdaBoost methods integrated with machine learning algorithms in classifying MOFs pores based on the pore limiting diameter (PLD) size. The results obtained from the CART-Gentle AdaBoost model provide the best performance with an accuracy of 72.82%; precision 71.32%; recall 73.53%; specificity 72.88%; and f1 score 72.39%. This model is quite suitable for use in identifying MOF structures that are accessible to guest molecules compared to other classification models.]]>
Copyrights © 2026
