Prediction of sodium binding energy on 2D VS machine learning: a robust accompanying method to random structure searching.

In this work, we employed the back-propagation neural network (BPNN) for predicting the energetics of different sodium adsorption phases on the VS monolayer generated random structure searching (AIRSS). Two key adsorption features were identified as inputs: the average Na-Na distance and a defined adsorption feature marker that indicates the number of nearest-neighbor pairs within a sodium cluster. Using the stoichiometric structure NaVS as the test system, we first generated 50 random sensible structures AIRSS and optimized them density functional theory (DFT) calculations to obtain the sodium binding energy per atom.