2000 character limit reached
Machine Learning Interatomic Potentials with Keras API (2404.18393v1)
Published 29 Apr 2024 in physics.comp-ph and cond-mat.dis-nn
Abstract: A neural network is used to train, predict, and evaluate a model to calculate the energies of 3-dimensional systems composed of Ti and O atoms. Python classes are implemented to quantify atomic interactions through symmetry functions and to specify prediction algorithms. The hyperparameters of the model are optimised by minimising validation RMSE, which then produced a model that is accurate to within 100 eV. The model could be improved by proper testing of symmetry function calculations and addressing properties of features and targets.
- J.-L. Bretonnet, Basics of the density functional theory, AIMS Materials Science 4, 1372 (2017).
- W. Hu and M. Chen, Editorial: Advances in density functional theory and beyond for computational chemistry, Frontiers in Chemistry 9, 10.3389/fchem.2021.705762 (2021).
- J. Behler and M. Parrinello, Generalized neural-network representation of high-dimensional potential-energy surfaces, Phys. Rev. Lett. 98, 146401 (2007).
- N. Artrith and A. Urban, An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for tio2, Computational Materials Science 114, 135 (2016).
- J. P. Rili, Machine Learning Interatomic Potentials with Keras API.
- D. P. Kingma and J. Ba, Adam: A method for stochastic optimization (2017), arXiv:1412.6980 [cs.LG] .