2026-04-30T01:14:52Z https://archive.materialscloud.org/oai2d

oai:materialscloud.org:j9ss5-v8y68 2026-02-11T04:17:58Z openaire_data community-mcarchive

Chen, Ziyong Yam, Vivian Wing-Wah Chen, Ziyong Lam, Jonathan Yam, Vivian Wing-Wah 2026-01-08 <p>Leveraging our recent development, which incorporates hole and particle information into the multi-channel molecular orbital image (MolOrbImage), to generate exceptional accuracy (mean absolute error, MAE < 0.1 eV) in predicting excited-state energies of practical photofunctional materials containing several hundred atoms, we have advanced the implementation of a new approach to overcome the high computational cost of mean-field ground-state calculations that limits its application in high-throughput materials discovery. In this work, low-cost approaches for generating approximate orbitals, including the superposition of atomic densities technique and the semi-empirical tight-binding method, have been employed to construct cost-effective multi-channel MolOrbImages. By connecting with a convolutional neural network, the performance of our model is evaluated for both small organic molecules (MAE < 0.1 eV) and practical photofunctional materials (MAE < 0.14 eV). Perturbation analysis of MolOrbImages highlights the importance of frontier orbital energies, which further motivates the adoption of transfer learning techniques to reduce prediction errors in excited-state energies.</p> application/vnd.snesdev-page-table application/zip application/zip text/plain text/x-python text/x-python text/x-python https://doi.org/10.24435/materialscloud:4v-ce oai:materialscloud.org:j9ss5-v8y68 mcid:2026.14 eng Materials Cloud https://doi.org/10.1021/acs.jctc.5c01721 https://archive.materialscloud.org/communities/mcarchive https://doi.org/10.24435/materialscloud:7j-kj info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode Excited state Machine learning Photofunctional materials Cost-effective multi-channel MolOrbImage for machine-learned excited-state properties of practical photofunctional materials info:eu-repo/semantics/other