Classifying superheavy elements by machine learning

Abstract

Among the 118 elements listed in the periodic table, there are nine superheavy elements (Mt, Ds, Mc, Rg, Nh, Fl, Lv, Ts, and Og) that have not yet been well studied experimentally because of their limited half-lives and production rates. How to classify these elements for further study remains an open question. For superheavy elements, although relativistic quantum-mechanical calculations for the single atoms are more accurate and reliable than those for their molecules and crystals, there is no study reported to classify elements solely based on atomic properties. By using cutting-edge machine learning techniques, we find the relationship between atomic data and classification of elements, and further identify that Mt, Ds, Mc, Rg, Lv, Ts, and Og should be metals, while Nh and Fl should be metalloids. These findings not only highlight the significance of machine learning for superheavy atoms but also challenge the conventional belief that one can determine the characteristics of an element only by looking at its position in the table.

Chemical Bonding and Bonding Models of Main-Group Compounds

“…The ELF clearly shows the shell structure for the heavier rare gases Xe and Rn, but for Og the density becomes smeared out over the whole atom. Moreover, Og has a positive electron affinity of 1.5 kcal/mol due to the very large relativistic 8s shell contraction, while all the other rare-gas elements do not bind an extra electron. , One might therefore speculate that solid Og has a small band gap and becomes semiconducting or even metallic due to relativistic effects . Further, the diffuse four 7p 3/2 electrons can easily be removed to form compounds like OgF 4 .…”

“…432,433 One might therefore speculate that solid Og has a small band gap and becomes semiconducting or even metallic due to relativistic effects. 434 Further, the diffuse four 7p 3/2 electrons can easily be removed to form compounds like OgF 4 . This structure, however, does not adopt the expected D 4h symmetry but becomes tetrahedral due to strong spin−orbit coupling.…”

Understanding Periodic and Non-periodic Chemistry in Periodic Tables

“…The elements below the metal-non-metal divide in Figure 2 -right are of a metallic character. The p-series in period 7 is mostly metallic, with astatine expected to be a metal (Hermann et al, 2013 ) and last member oganesson is either a semiconductor (Mewes et al, 2019a ) or a metalloid, depending on one's definition (Vernon, 2013 ), or a metal (Gong et al, 2019 ). Trombach et al ( 2019 ) has summarized the sparse chemical speculations, based on pronounced reluctant-pair and spin-orbit coupling effects.…”

Screening Topological Quantum Materials for Na-Ion Battery Cathode

“…Among the large amount of topological quantum materials, it is hard to carry out density functional theory (DFT) calculations to screen the candidates, especially for those with transition metal elements, where coupling among spin order, charge order, orbital order, and lattice order make the calculation more complicated. Currently, machine learning method is hotly pursued for material design. − As a representative of data-driven approaches, machine learning can discover complex rules and invisible relationships among multivariables and has faster speed and competitive accuracy compared with conventional theoretical computational simulations.…”