Kwon, Hee Young Yoon, Han Gyu Park, Sung Min Lee, Doo Bong Choi, Jun Woo Won, Changyeon 2024-01-19T14:32:37Z 2024-01-19T14:32:37Z 2021-09-05 2021-06 2198-3844 https://pubs.kist.re.kr/handle/201004/116927 Numerical generation of physical states is essential to all scientific research fields. The role of a numerical generator is not limited to understanding experimental results; it can also be employed to predict or investigate characteristics of uncharted systems. A variational autoencoder model is devised and applied to a magnetic system to generate energetically stable magnetic states with low local deformation. The spin structure stabilization is made possible by taking the explicit magnetic Hamiltonian into account to minimize energy in the training process. A significant advantage of the model is that the generator can create a long-range ordered ground state of spin configuration by increasing the role of stabilization even if the ground states are not necessarily included in the training process. It is expected that the proposed Hamiltonian-guided generative model can bring about great advances in numerical approaches used in various scientific research fields. English WILEY REAL-SPACE OBSERVATION DYNAMICS Magnetic State Generation using Hamiltonian Guided Variational Autoencoder with Spin Structure Stabilization Article 10.1002/advs.202004795 1 ADVANCED SCIENCE, v.8, no.11 ADVANCED SCIENCE 8 11 scie scopus 000631777700001 2-s2.0-85102940814 Chemistry, Multidisciplinary Nanoscience & Nanotechnology Materials Science, Multidisciplinary Chemistry Science & Technology - Other Topics Materials Science Article REAL-SPACE OBSERVATION DYNAMICS energy minimization generative model machine learning micromagnetism the ground state