Skip to content
DraconiticResearch
Search Sources API
181,713 studies31 sourcesUpdated 22 min ago
Peer-reviewedCC BYJournal of computational chemistry

Physics‐Based AI‐Augmented Workflows Discovering Candidate Graphene Quantum Dot Near‐Infrared Chromophores

  • Naga Mani Gajula1
  • Muhammad Hammad Ali2
  • Md Masud Rana1
  • Benjamin G Janesko2
  1. 1Department of Computer Science, Lamar University, Beaumont, Texas, USA.
  2. 2Department of Chemistry & Biochemistry, Texas Christian University, Fort Worth, Texas, USA.
Read full textPDFDOICite

Abstract

Graphene quantum dots (GQDs) exhibit optical properties that depend strongly on their size, edge structure, and surface functionalization, but identifying the molecular structures responsible for near-infrared (NIR) emission remains challenging because of their structural complexity and disorder. In this work, we developed a computational framework combining rule-based molecular generation, semi-empirical quantum chemistry calculations, machine learning, and time-dependent density functional theory (TD-DFT) to predict possible chemically realistic candidate GQDs with NIR-emitting optical properties. A fusion-based hexagonal lattice growth approach was used to generate 100,000 candidate graphitic structures. A random subset of 5000 structures was selected for semiempirical calculations. Computed band gaps were used to train and evaluate five machine learning models (Random Forest, XGBoost, LightGBM, CatBoost, and Neural Network). LightGBM predicted bandgaps were used to pre-screen the remaining 95,000 structures. 11,000 structures with low predicted gaps were selected for semiempirical calculations, and 50 top candidates with low gap and low SA score were selected for TD-DFT calculations employing LC-ωPBE functional. All 50 structures were predicted to exhibit NIR emission, offering a computed database of candidate NIR-emitting GQDs for future validation against experiment.

Related

  1. Exploration the influence of electron donor engineering on frequency-dependent nonlinear optical properties of anthraquinone-based chromophores: a DFT-ML approach
    Muhammad Adnan Asghar, Hafsa Sadiq, Muhammad Usman Khan +3
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMaterials & polymersCrossref
  2. A Visual Understanding of Circular Dichroism Spectroscopy: The Case of Interacting Chromophores
    Braden M. Weight, Aaron Forde, Sergei Tretiak
    arXivPreprintCC BY 4.0Full textPhysical chemistryarXiv
  3. A core–shell spectroscopic perspective on solution phase charge transfer in photoexcited push–pull chromophores
    Mate Kurucz, Marc-Oliver Winghart, Debkumar Rana +10
    Chemical sciencePeer-reviewedCC BY-NCFull textPhysical chemistryEurope PMCPMCEurope PMC
  4. Hybrid Organosilicon Polymers Integrating Latent Si–Si Chromophores and Orthogonal Si–O–C Reactivity
    Bercis Pektas, Cuong Minh Quoc Le, Kenshiro Hitoshio +3
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv
  5. Globally Aromatic 10-Boratetraoxacorroles: Boron-Doped Macrocyclic Chromophores with Intense Red-to-Near-Infrared Emission
    Jonas Fehler, Lukas Swoboda, Alexandra Friedrich +2
    ChemRxivPreprintCC BY-NC-NDFull textMaterials & polymersChemRxiv

Cite

BibTeXRIS
BibTeX
@article{gajula2026physicsbased,
  title = {{Physics‐Based AI‐Augmented Workflows Discovering Candidate Graphene Quantum Dot Near‐Infrared Chromophores}},
  author = {Naga Mani Gajula and Muhammad Hammad Ali and Md Masud Rana and Benjamin G Janesko},
  journal = {Journal of computational chemistry},
  year = {2026},
  month = nov,
  doi = {10.1002/jcc.70522},
  url = {https://europepmc.org/article/PMC/PMC13726809},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Physics‐Based AI‐Augmented Workflows Discovering Candidate Graphene Quantum Dot Near‐Infrared Chromophores
AU  - Naga Mani Gajula
AU  - Muhammad Hammad Ali
AU  - Md Masud Rana
AU  - Benjamin G Janesko
PY  - 2026
DA  - 2026/11/01
JO  - Journal of computational chemistry
DO  - 10.1002/jcc.70522
UR  - https://europepmc.org/article/PMC/PMC13726809
AB  - Graphene quantum dots (GQDs) exhibit optical properties that depend strongly on their size, edge structure, and surface functionalization, but identifying the molecular structures responsible for near-infrared (NIR) emission remains challenging because of their structural complexity and disorder. In this work, we developed a computational framework combining rule-based molecular generation, semi-empirical quantum chemistry calculations, machine learning, and time-dependent density functional theory (TD-DFT) to predict possible chemically realistic candidate GQDs with NIR-emitting optical properties. A fusion-based hexagonal lattice growth approach was used to generate 100,000 candidate graphitic structures. A random subset of 5000 structures was selected for semiempirical calculations. Computed band gaps were used to train and evaluate five machine learning models (Random Forest, XGBoost, LightGBM, CatBoost, and Neural Network). LightGBM predicted bandgaps were used to pre-screen the remaining 95,000 structures. 11,000 structures with low predicted gaps were selected for semiempirical calculations, and 50 top candidates with low gap and low SA score were selected for TD-DFT calculations employing LC-ωPBE functional. All 50 structures were predicted to exhibit NIR emission, offering a computed database of candidate NIR-emitting GQDs for future validation against experiment.
SN  - 0192-8651
SN  - 1096-987X
ER  -