Pham Tien Lam, Nguyen Van Duy, Nguyen Tien Cuong

Main Article Content


We present machine learning models for fast estimating atomic forces. In our method, the total energy of a system is approximated as the summation of atomic energy which is the interaction energy with its surrounding chemical environment within a certain cutoff radius. Atomic energy is decomposed into two-body terms which are expressed as a linear combination of basis functions. For the force exerted on an atom, we employ a linear combination of a set of basis functions for representing pairwise force. We use least-square linear regression regularized by the l2-norm, known as Ridge regression, to estimate model parameters. We demonstrate that our model can accurately reproduce atomic forces and energies from density-functional-theory (DFT) calculations for crystalline and amorphous silicon. The machine learning force model is then applied to calculate the phonon dispersion of crystalline silicon. The result shows reasonable agreement with DFT calculations.

Keywords: Machine Learning, molecular dynamics, force field, materials informatics


[1] R. Car, M. Parrinello, Unified approach for molecular dynamics and density-functional theory, Phys. Rev. Lett. 55 (1985) 2471–2474.
[2] W. Kohn, L.J. Sham, Self-Consistent Equations Including Exchange and Correlation Effects, Phys. Rev. 140 (1965) 1133.
[3] P. Hohenberg, W. Kohn, Inhomogeneous Electron Gas, Phys. Rev. 136 (1964) 5188.
[4] C.M. Handley, J. Behler, Next generation interatomic potentials for condensed systems, Eur. Phys. J. B. 87 (2014) 152.
[5] A.P. Bartók, G. Csányi, Gaussian approximation potentials: A brief tutorial introduction, Int. J. Quantum Chem. 115 (2015) 1051–1057.
[6] S. De, A.P. Bartók, G. Csanyi, M. Ceriotti, Comparing molecules and solids across structural and alchemical space, Phys. Chem. Chem. Phys. 18 (2016) 13754–13769.
[7] A. Seko, et al., A sparse representation for potential energy surface, Phys. Rev. B. 90 (2014) 24101.
[8] M. Rupp, A. Tkatchenko, K.-R. Muller, O.A. von Lilienfeld, Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning, Phys. Rev. Lett. 108 (2012) 58301.
[9] T.L. Pham, H. Kino, K. Terakura, T. Miyake, H.C. Dam, Novel mixture model for the representation of potential energy surfaces, J. Chem. Phys. 145 (2016) 154103.
[10] J. Behler, M. Parrinello, Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces, Phys. Rev. Lett. 98 (2007) 146401.
[11] N. Artrith, J. Behler, High-dimensional neural network potentials for metal surfaces: A prototype study for copper, Phys. Rev. B. 85 (2012) 45439.
[12] J. Behler, Atom-centered symmetry functions for constructing high-dimensional neural network potentials, J. Phys. Chem. 134 (2011) 74106.
[13] T. Lam Pham, H. Kino, K. Terakura, T. Miyake, K. Tsuda, I. Takigawa, H. Chi Dam, Machine learning reveals orbital interaction in materials, Sci Technol Adv Mater. 18 (2017) 756–765.
[14] T.L. Pham, N.D. Nguyen, V.D. Nguyen, H. Kino, T. Miyake, H.C. Dam, Learning structure-property relationship in crystalline materials: A study of lanthanide-transition metal alloys, J. Chem. Phys. 148 (2018).
[15] V.-D. Nguyen, T.-L. Pham, H.-C. Dam, Application of materials informatics on crystalline materials for two-body terms approximation, Comput. Mater. Sci. 166 (2019) 155–161.
[16] K. Parlinski, Z.Q. Li, Y. Kawazoe, First-Principles Determination of the Soft Mode in Cubic ZrO 2, Phys. Rev. Lett. 78 (1997) 4063–4066.
[17] A. Togo, I. Tanaka, First principles phonon calculations in materials science, Scr. Mater. 108 (2015) 1–5.