dc.contributor.author | De Armas Morejón, Carlos Manuel | |
dc.contributor.author | Montero Cabrera, Luis A. | |
dc.contributor.author | Rubio Secades, Angel | |
dc.contributor.author | Jornet Somoza, Joaquim | |
dc.date.accessioned | 2023-04-26T17:06:56Z | |
dc.date.available | 2023-04-26T17:06:56Z | |
dc.date.issued | 2023-03 | |
dc.identifier.citation | Journal of Chemical Theory and Computation 19(6) : 1818-1826 (2023) | es_ES |
dc.identifier.issn | 1549-9618 | |
dc.identifier.issn | 1549-9626 | |
dc.identifier.uri | http://hdl.handle.net/10810/60939 | |
dc.description.abstract | Spectroscopic properties of molecules hold great importance for the description of the molecular response under the effect of UV/vis electromagnetic radiation. Computationally expensive ab initio (e.g., MultiConfigurational SCF, Coupled Cluster) or TDDFT methods are commonly used by the quantum chemistry community to compute these properties. In this work, we propose a (supervised) Machine Learning approach to model the absorption spectra of organic molecules. Several supervised ML methods have been tested such as Kernel Ridge Regression (KRR), Multiperceptron Neural Networs (MLP), and Convolutional Neural Networks. [Ramakrishnan et al. J. Chem. Phys. 2015, 143, 084111.Ghosh et al. Adv. Sci. 2019, 6, 1801367.] The use of only geometrical-atomic number descriptors (e.g., Coulomb Matrix) proved to be insufficient for an accurate training. [Ramakrishnan et al. J. Chem. Phys. 2015, 143, 084111.] Inspired by the TDDFT theory, we propose to use a set of electronic descriptors obtained from low-cost DFT methods: orbital energy differences (Δϵia = ϵa – ϵi), transition dipole moment between occupied and unoccupied Kohn–Sham orbitals (⟨ϕi|r|ϕa⟩), and when relevant, charge-transfer character of monoexcitations (Ria). We demonstrate that with these electronic descriptors and the use of Neural Networks we can predict not only a density of excited states but also get a very good estimation of the absorption spectrum and charge-transfer character of the electronic excited states, reaching results close to chemical accuracy (∼2 kcal/mol or ∼0.1 eV). | es_ES |
dc.description.sponsorship | This work was supported by the European Research Council (ERC-2015-AdG694097), the Cluster of Excellence ‘CUI: Advanced Imaging of Matter’ of the Deutsche Forschungsgemeinschaft (DFG) - EXC 2056 - project ID 390715994, Grupos Consolidados (IT1249-19), and the SFB925 “Light induced dynamics and control of correlated quantum systems”. We kindly recognize the partial support of the project ID PN223LH010-002 “Inteligencia Artificial Aplicada, Espectroscopía y Bioactividad” of the Cuban Ministry of Science, Technology and Environment as well as the overall support given to L.A.M.C. by the Universidad de La Habana and the Donostia International Physics Center.
Open access funded by Max Planck Society. | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | American Chemical Society | es_ES |
dc.relation | info:eu-repo/grantAgreement/EC/ERC/694097 | es_ES |
dc.rights | info:eu-repo/semantics/openAccess | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | * |
dc.title | Electronic Descriptors for Supervised Spectroscopic Predictions | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
dc.rights.holder | © 2023 The Authors. Published by American Chemical Society. Attribution 4.0 International (CC BY 4.0) | es_ES |
dc.rights.holder | Atribución 3.0 España | * |
dc.relation.publisherversion | https://pubs.acs.org/doi/10.1021/acs.jctc.2c01039 | es_ES |
dc.identifier.doi | 10.1021/acs.jctc.2c01039 | |
dc.contributor.funder | European Commission | |
dc.departamentoes | Polímeros y Materiales Avanzados: Física, Química y Tecnología | es_ES |
dc.departamentoeu | Polimero eta Material Aurreratuak: Fisika, Kimika eta Teknologia | es_ES |