High Dimension Neural Network Potential Implementation for FeS Optimization Muhammad Rizky Rahman (a*), Iqbal Lafifa Zulfa (a), Ari Sulistyowati (a), Dr. Atthar Luqman Ivansyah (a), Fahdzi Muttaqien, Ph.D (a)
a) Bandung Institute of Technology
Jalan Ganesha 10, Bandung 40132, Indonesia
* 20920305[at]mahasiswa.itb.ac.id
Abstract
Iron sulfide (FeS) is of interest due to their potential usage in a variety of industries, including energy storage, catalysis, and environmental remediation. FeS is a Metal-Insulator Transition (MIT) material in which its electronic properties can be modified as initial temperature treatment. FeS take a form P62c when it hit temperature below 416 K and change to P63/mmc when the temperature raise above it. Nevertheless, since a stoichiometric ratio is challenging to attain, multistep methods are needed to synthesize FeS. In this study, we employ artificial neural network (ANN) based on Behler-Parinello approach to investigate the phase changes of FeS at 300 - 550 K. Currently, we try to elucidate the best multilayer perceptron (MLP) ANN structure to construct adequate atomic interaction potential of FeS. The potentials are constructed from more than 4000 database structures, which include pristine and defected structures. We obtain that 2 hidden layers MLP with 20 nodes in each shows fine training and testing set error. We do force minimization of particular FeS structure using ANN atomic potential. We obtain excellent results as no overlapping Fe-S bond length in the final structure and no odd energy change.
