Unsupervised meta-analysis on chemical elements and atomic energy prediction: case study on periodic table

Abstract

Abstract This paper presents an artificial classification and atomic energy correlation analysis of the periodic table. The choice of data mining method is due to its robustness, which can explore intrinsic or hidden relationships between chemical elements and their properties. The Mendeleev table is probably the earliest example of the data analysis technique in materials science. However, the classical periodic table represents the arrangement of chemical elements based on specific periodicities that have the problem of continuity of properties for some chemical elements. In this research, we used one of the unsupervised data mining methods (Principal Component Analysis) to investigate the chemical elements based on all the ready properties, some questions were raised before diving into this research. The main objective is to make a pseudo-classification of natural and synthetic chemical elements based on their physicochemical and energy-available properties. The results revealed the effectiveness of the data mining method in appreciating the relationships between the variables and properties that offer a new way of viewing a Mendeleev table. The last step of this work highlights the importance of predictive polynomial that allows the scientific community to make atomic total energy predictions for each natural periodic element, from helium to lawrencium.