Infrared Spectroscopy of Chemically Diverse Carbon Clusters: A Data-Driven Approach

Abstract

Carbon clusters exhibit a broad diversity of topologies and shapes, encompassing fullerene-like cages, graphene-like flakes, and more disordered pretzel-like and branched structures. Here we examine computationally their infrared spectra in relation with these structures, from a statistical perspective. Individual spectra for broad samples of isomers were determined by means of the self-consistent charge density functional based tight-binding method, and an interpolation scheme is designed to reproduce the spectral features by regression on a much smaller subset of the sample.This interpolation proceeds by encoding the structures using appropriate descriptors and selecting them through a principal component analysis, Gaussian regression or inverse distance weighting providing the nonlinear weighting functions. Metric learning is employed to reduce the global error on a preselected testing set. The interpolated spectra satisfactorily reproduce the specific spectral features and their dependence on size and shape, enabling quantitative prediction away from the testing set. Finally, the classification of structures within the four proposed families is critically discussed through a statistical analysis of the sample based on iterative label spreading.

Unsupervised machine learning discovers classes in aluminium alloys

“…In this study, iterative label spreading (ILS) has been used because it requires no hyperparameter optimization and can predict the number and type of clusters in the dataset before clustering (something that is required in advance for other label-spreading approaches) [43]. ILS has successfully been used in materials science applications [21,[44][45][46]. ILS works better than other methods in clustering high-dimensional data with significant noise, is able to identify both concave and convex clusters, and can identify challenging cases such as the null case and the chain case where other methods fail [43].…”

Water Clusters in Interaction with Corannulene in a Rare Gas Matrix: Structures, Stability and IR Spectra

“…Alternatively, a "bottom-up" mechanism, consisting of the successive growth from smaller carbon chain building blocks, known as the closed network growth mechanism [31], would prevail in the hot, dense envelopes of evolved stars [30]. The need to characterize the structural diversity of carbon clusters, possibly hydrogenated and with amorphous character, that could play a role in the formation of buckminsterfullerene, motivated the development of dedicated experimental and theoretical approaches in order to obtain their spectral features in the UV-visible [32,33] and IR domains [34][35][36][37].…”

Predicting Binding Energies and Electronic Properties of Boron Nitride Fullerenes Using a Graph Convolutional Network

“…Alternatively, the emerging machine learning or deep learning (DL) techniques have provided a solution for rapid prediction of the energies of isomers for a molecule or cluster with precision comparable to DFT. − For instance, using a geom-C60 database with four symmetric cage isomers and 29 unique C–C bonds, Aghajamali and Karton examined the performance of 12 carbon force fields and found that a machine-learning-based Gaussian approximation potential, namely, GAP-20, outperforms the empirical force fields. In addition to binding energies, Calvo et al created a large database of 753,184 infrared spectra of C n clusters ( n = 24, 33, 42, 52, 60) with different shapes (including fullerene-like cages, graphene-like flakes, pretzel-like and branched structures) using density functional-based tight-binding calculations and developed an interpolation scheme to reproduce the spectral features by encoding the structures using appropriate descriptors and selecting them through principal component analysis and Gaussian regression. Turcani et al created a database of 63,472 hypothetical organic cage molecules and developed random forest models for predicting the shape persistence and cavity size of these molecules.…”