Machine learning (ML) models can potentially accelerate the discovery of tailored materials by learning a function that maps chemical compounds into their respective target properties. In this realm, a crucial step is encoding the molecular systems into the ML model, in which the molecular representation plays a crucial role. Most of the representations are based on the use of atomic coordinates (structure); however, it can increase ML training and predictions' computational cost. Herein, we investigate the impact of choosing free-coordinate descriptors based on the Simplified Molecular Input Line Entry System (SMILES) representation, which can substantially reduce the ML predictions' computational cost. Therefore, we evaluate a feed-forward neural network (FNN) model's prediction performance over five feature selection methods and nine ground-state properties (including energetic, electronic, and thermodynamic properties) from a public data set composed of ∼130k organic molecules. Our best results reached a mean absolute error, close to chemical accuracy, of ∼0.05 eV for the atomization energies (internal energy at 0 K, internal energy at 298.15 K, enthalpy at 298.15 K, and free energy at 298.15 K). Moreover, for the atomization energies, the results obtained an out-of-sample error nine times less than the same FNN model trained with the Coulomb matrix, a traditional coordinate-based descriptor. Furthermore, our results showed how limited the model's accuracy is by employing such low computational cost representation that carries less information about the molecular structure than the most state-of-the-art methods.
Platinum-based nanoalloys can yield unique properties
due to synergistic
effects derived from the combination of Pt with one or more transition-metal
(TM) species, as well as from the chemical ordering within the particles
such as the formation of core–shell PtTM structures. Although
several studies have been reported, our atomistic understanding of
the key physical and chemical descriptors that lead to the formation
and stability of the core–shell structures are not completely
understood. Here, we discuss such descriptors to understand the formation
and stability of 11 platinum-based nanoalloys through ab initio density functional theory calculations employing 55-atom PtTM model
systems. Studying several properties and using the Spearman correlation
analysis, we found that the core–shell PtTM nanoalloys are
energetically more stable if the surface region is populated by the
chemical species with larger atomic radius and lower surface energy,
which helps to reduce strain and forms stable structures. For nanoalloys
of chemical species with large difference in the electronegativity,
the energetic stability is enhanced by the Coulomb attraction between
the cationic core and anionic surface derived from charge transfer,
which increases the strain on the core and contributes to increase
the segregation of large species to the surface region. Thus, the
atomic radii, surface energies, and charge transfer play a crucial
role in the formation and stability of core–shell PtTM nanoalloys.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.