Prediction of bonding energy by structural descriptors of metal nanoalloys
V.S. Myasnichenko1, P.V. Matrenin2, N.Yu. Sdobnyakov1
1 Tver State University
2 Novosibirsk State Technical University
Abstract: The problem of predicting the binding energy for ternary metal nanoparticles and the construction of learning models based on structural descriptors are discussed. Regression dependences of the specific interatomic bond energy were constructed for the ternary Au–Ag–Cu nanosystem. A number of five radial features were used, depending on the pairwise interatomic distance of the nanoparticle structure descriptors. For a more correct assessment of the accuracy, cross-validation was applied, then the results obtained on the validation parts of the sample were averaged. The resulting model limitedly predicts the value of the specific interatomic binding energy within a group of data for nanoparticles of the same composition. For the entire sample the average error in modulus is 14 %. In this case, the model almost accurately determines the composition of a nanoparticle of several variants. The largest value of the coefficient of determination in the entire sample was obtained using an ensemble random forest algorithm. A negative correlation was found between the binding energy of the nanoalloy and the position of the first peak of the radial distribution function for copper atoms.
Keywords: machine learning, radial distribution function, structural descriptor, bond energy, ternary alloy.
- Vladimir S. Myasnichenko – Researcher, General Physics Department, Tver State University
- Pavel V. Matrenin – Ph. D., Senior Lecturer, «Power Supply Systems of Enterprises» Department, Novosibirsk State Technical University
- Nickolay Yu. Sdobnyakov – Ph. D., Docent, General Physics Department, Tver State University
Myasnichenko, V.S. Prediction of bonding energy by structural descriptors of metal nanoalloys / V.S. Myasnichenko, P.V. Matrenin, N.Yu. Sdobnyakov // Physical and chemical aspects of the study of clusters, nanostructures and nanomaterials. – Tver: TSU, 2021. — I. 13. — P. 495-502. DOI: 10.26456/pcascnn/2021.13.495. (In Russian).
Full article (in Russian): download PDF file
1. Kolosov A.Yu., Myasnichenko V.S., Bogdanov S.S. et al. On the regularities of formation of mono- and bimetallic nanoparticles in the coalescence process, Fiziko-khimicheskie aspekty izucheniya klasterov, nanostruktur i nanomaterialov [Physical and chemical aspects of the study of clusters, nanostructures and nanomaterials], 2018, issue 10, pp. 359-367. DOI: 10.26456/pcascnn/2018.10.359. (In Russian).
2. Myasnichenko V.S., Sdobnyakov N.Yu., Bazulev A.N., Ershov P.M., Davydenkova E.M. Size dependences of linear expansion and volume elasticity of mono- and bimetallic nanoclusters, Fiziko-khimicheskie aspekty izucheniya klasterov, nanostruktur i nanomaterialov [Physical and chemical aspects of the study of clusters, nanostructures and nanomaterials], 2020, issue 12, pp. 260-273. DOI: 10.26456/pcascnn/2020.12.260. (In Russian).
3. Myasnichenko V., Sdobnyakov N., Kirilov L., Mikhov R., Fidanova S. Structural instability of gold and bimetallic nanowires using Monte Carlo simulation, Recent Advances in Computational Optimization. Studies in Computational Intelligence, ed. by S. Fidanova. Cham, Springer, 2020, vol. 838, pp. 133-145. DOI: 10.1007/978-3-030-22723-4_9.
4. Sdobnyakov N.Yu., Myasnichenko V.S., San C.-H. et al. Simulation of phase transformations in titanium nanoalloy at different cooling rates, Materials Chemistry and Physics, 2019, vol. 238, art. no. 121895, 9 p. DOI: 10.1016/j.matchemphys.2019.121895.
5. Hart G.L.W., Mueller T., Toher C., Curtarolo S. Machine learning for alloys, Nature Reviews Materials, 2021, vol. 6, pp. 730-755. DOI: 10.1038/s41578-021-00340-w.
6. Deringer V.L., Caro M.A., Csányi G. A general-purpose machine-learning force field for bulk and nanostructured phosphorus, Nature Communications, 2020, vol. 11, art. no. 5461, 11 p. DOI: 10.1038/s41467- 020-19168-z.
7. Kart H.H., Yildirim H., Kart S.O., Çağin T. Physical properties of Cu nanoparticles: A molecular dynamics study, Materials Chemistry and Physics, 2014, vol. 147, issue 1-2, pp. 204-212. DOI: 10.1016/j.matchemphys.2014.04.030.
8. Qi W.H., Wang M.P., Xu G.Y. The particle size dependence of cohesive energy of metallic nanoparticles, Chemical Physics Letters, 2003, vol. 372, issue 5-6, pp. 632-634. DOI: 10.1016/S0009-2614(03)00470-6.
9. Myasnichenko V.S., Razavi M., Outokesh M., Sdobnyakov N.Yu., Starostenkov M.D. Molecular dynamic investigation of size-dependent surface energy of icosahedral copper nanoparticles at different temperature, Letters on materials, 2016, vol. 6, issue 4, pp. 266-270. DOI: 10.22226/2410-3535-2016-4-266-270.
10. Samsonov V.M., Chernyshova A.A., Sdobnyakov N.Yu. Size dependence of the surface energy and surface tension of metal nanoparticles, Bulletin of the Russian Academy of Sciences. Physics, 2016, vol. 80, issue 6, pp. 698-701. DOI: 10.3103/S1062873816060290.
11. Chiavazzo E., Covino R., Coifman R.R. et al. Intrinsic map dynamics exploration for uncharted effective free-energy landscapes, PNAS, 2017, vol. 114, issue 28, pp. E5494-E5503. DOI: 10.1073/pnas.1621481114.
12. Musil F., De S., Yang J. et al. Machine learning for the structure-energy-property landscapes of molecular crystals, Chemical Science, 2018, vol. 9, issue 5, pp. 1289-1300. DOI: 10.1039/C7SC04665K.
13. Keith J.A., Vassilev-Galindo V., Cheng B. et al. Combining machine learning and computational chemistry for predictive insights into chemical systems, Chemical Reviews, 2021, vol. 121, issue 16, pp. 9816-9872. DOI: 10.1021/acs.chemrev.1c00107.
14. Pozdnyakov S.N., Willatt M.J., Bartók A.P. et al. Incompleteness of atomic structure representations / // Physical Review Letters, 2020, vol. 125, issue 16, pp. 166001-1-166001-6. DOI: 10.1103/PhysRevLett.125.166001.
15. Roncaglia C., Rapettia D., Ferrando R.Regression and clustering algorithms for AgCu nanoalloys: from mixing energy predictions to structure recognition, Physical Chemistry Chemical Physics, 2021, vol. 23, issue 40, pp. 23325-23335. DOI: 10.1039/D1CP02143E.
16. Scikit-Learn. Machine learning in Python. Available at: www.url: https://scikit-learn.org/stable/ (accessed 15.09.2021).