Unsupervised learning methods for the identification of nanoparticles structures based on local atomic environments
Cesare Roncaglia and Riccardo Ferrando Physics Department, University of Genoa, Italy
We propose a scheme for the automatic separation of data sets composed of several nanoparticles (NPs) structures by means of Machine Learning techniques. These data sets originate from atomistic simulations, such as global optimizations and molecular dynamics (MD), which are well known to produce large outputs that are often difficult to inspect by hand. By combining a description of NPs based on their local atomic environment with unsupervised learning algorithms, such as K-Means and Gaussian mixture model, we are able to distinguish between different structural motifs (for example icosahedra, decahedra, polyicosahedra, fcc fragments and twins). We show that this method is able to improve over the results obtained in Ref. [1] thanks to the successful implementation of a more detailed description of NPs, especially for systems showing a large variety of structures, including disordered ones. References 1. C. Roncaglia, D. Rapetti and R. Ferrando, Phys. Chem. Chem. Phys., 2021, 23 , 23325-23335.
P15
© The Author(s), 2022
Made with FlippingBook Learn more on our blog