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.
<p><strong>Abstract.</strong> The monitoring of agricultural activities at a regular basis is crucial to assure that the food production meets the world population demands, which is increasing yearly. Such information can be derived from remote sensing data. In spite of topic’s relevance, not enough efforts have been invested to exploit modern pattern recognition and machine learning methods for agricultural land-cover mapping from multi-temporal, multi-sensor earth observation data. Furthermore, only a small proportion of the works published on this topic relates to tropical/subtropical regions, where crop dynamics is more complicated and difficult to model than in temperate regions. A major hindrance has been the lack of accurate public databases for the comparison of different classification methods. In this context, the aim of the present paper is to share a multi-temporal and multi-sensor benchmark database that can be used by the remote sensing community for agricultural land-cover mapping. Information about crops in situ was collected in Luís Eduardo Magalhães (LEM) municipality, which is an important Brazilian agricultural area, to create field reference data including information about first and second crop harvests. Moreover, a series of remote sensing images was acquired and pre-processed, from both active and passive orbital sensors (Sentinel-1, Sentinel-2/MSI, Landsat-8/OLI), correspondent to the LEM area, along the development of the main annual crops. In this paper, we describe the LEM database (crop field boundaries, land use reference data and pre-processed images) and present the results of an experiment conducted using the Sentinel-1 and Sentinel-2 data.</p>
In this work, we report an ab initio investigation based on density functional theory calculations within van der Waals D3 corrections to investigate the adsorption properties and activation of CO2 on transition-metal (TM) 13-atom clusters (TM = Ru, Rh, Pd, Ag), which is a key step for the development of subnano catalysts for the conversion of CO2 to high-value products. From our analyses, which include calculations of several properties and the Spearman correlation analysis, we found that CO2 adopts two distinct structures on the selected TM13 clusters, namely, a bent CO2 configuration in which the OCO angle is about 125 to 150° (chemisorption), which is the lowest energy CO2/TM13 configuration for TM = Ru, Rh, Pd. As in the gas phase, the linear CO2 structure yields the lowest energy for CO2/Ag13 and several higher energy configurations for TM = Ru, Rh, Pd. The bent CO2 (activated) is driven by a chemisorption CO2–TM13 interaction due to the charge transfer from the TM13 clusters toward CO2, while a weak physisorption interaction is obtained for the linear CO2 on the TM13 clusters. Thus, the CO2 activation occurs only in the first case and it is driven by charge transfer from the TM13 clusters to the CO2 molecule (i.e., CO2 –δ), which is confirmed by our Bader charge analysis and vibrational frequencies.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.