Tailoring hydrogen adsorption and desorption properties of Li-doped SV (single vacancy) monolayer h-BN systems using ab initio calculations

Abstract

This study uses DFT (Density Functional Theory) technique to examine the H2 storage on Li-decorated h-BN monolayer. The results of DFT proven that Li doped h-BN system can hold up to 9H2 with the adsorption energy lie in between -0.31eV to -0.24eV/H2 at ambient condition However, the calculated average adsorption energy for 9H2 is-0.240eV/H2 with hydrogen storage capacity of 5.96 wt. %, which is according to the United States Department of Energy (USDOE). Partial Density of State (PDOS) computed for each configuration to provide additional justifications for the H2 storage on Li-doped h-BN monolayer. The hybridization shows a significant interaction between hydrogen molecules (H2) and Li atom, and most of their hybrid peaks was observed in the energy range from -7.5 eV to -1 eV. Moreover, the H2 desorption simulations achieved via the ab initio molecular dynamics (MD). The computed desorption temperature TD is 306 °K which is a suitable operating temperature. Hence our research demonstrates that Li-doped h-BN is a thermally stable and viable hydrogen storage material for hydrogen storage systems.

Machine learning-based electricity theft detection using support vector machines

“…There are other validation parameters such as accuracy, Matthew's correlation coefficient (MCC), area under curve (AUC), area under receiver operating characteristic curve (ROC AUC), area under the precision recall curve (PR AUC), precision, recall and F1 score are used in this study. − Accuracy is defined as the percentage of correctly predicted data points among all the data points which is given in (6). It is a commonly used statistic in the data science profession for categorization issues.…”

“…In recent times, machine learning (ML) techniques have been investigated as a potential solution for automatically detecting the electricity theft and it has shown the promising results. Machine learning algorithms can analyze large data sets, which can also identify patterns that might be signs of electricity theft [5], [6]. One of the commonly used machine learning algorithm i.e., support vector machines (SVM) has been effectively used in a number of industries, including banking, healthcare, and cyber security and Electric theft detection [7].…”