Integrated classical/quantum–classical neural networks, DFT, and experiments for predicting bandgap and color of CrxSbxTi1−2xO2 yellow-orange pigments
Abstract
The accurate prediction of the bandgap ( Eg ) and color of ceramic pigments is of considerable importance in materials science research. In this work, we investigate the Eg and color of Cr x Sb x Ti 1−2x O 2 rutile pigments by combining experimental, density functional theory (DFT and DFT+ U ) calculations, and neural network approaches. The main novelty of this study is the application of classical/hybrid quantum–classical neural networks to the prediction of pigment color and Eg . Cr/Sb co-doped rutile pigment was synthesized and characterized, and the electronic structures of undoped and doped TiO2 were analyzed using first-principles calculations. In parallel, classical and hybrid quantum–classical neural network models were developed and trained on datasets compiled from the Materials Project database and literature-reported rutile-based pigments. The models successfully captured the trends in Eg and chromaticity, with the hybrid architectures providing slightly improved predictive performance and more consistent agreement with experiment. Overall, this work demonstrates an effective framework that links experiment, first-principles calculations, and classical/quantum–classical neural networks for predicting key properties of ceramic pigments, and it points toward the future use of fully quantum machine learning models for materials design.
Related
- A reversible indole-based colorimetric chemosensor for Cu²⁺: implications for smartphone-integrated sensing, logic gate experiments, environmental and biological applications.
- Predicting Thermal Conductivity of Foamed Concrete via Physics-Informed Neural Networks Coupled with the Maxwell-Eucken Model.
- Predicting Adsorbate-Solvent Interaction Energies in Zeolite Pores Using Convolutional Neural Networks with Attention Mechanisms.
- Enhanced Azo Dye Removal via Alginate-Immobilized Ganoderma lucidum: From Batch Experiments to Continuous Column Studies
- Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments
BibTeX
@article{vaselnia2026integrated,
title = {{Integrated classical/quantum–classical neural networks, DFT, and experiments for predicting bandgap and color of CrxSbxTi1−2xO2 yellow-orange pigments}},
author = {S. Y. Vaselnia and M. Khajeh Aminian and R. Dehghan Banadaki},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-73340-x},
url = {https://www.nature.com/articles/s41598-026-73340-x},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Integrated classical/quantum–classical neural networks, DFT, and experiments for predicting bandgap and color of CrxSbxTi1−2xO2 yellow-orange pigments
AU - S. Y. Vaselnia
AU - M. Khajeh Aminian
AU - R. Dehghan Banadaki
PY - 2026
DA - 2026/10/01
JO - Scientific Reports
DO - 10.1038/s41598-026-73340-x
UR - https://www.nature.com/articles/s41598-026-73340-x
AB - The accurate prediction of the bandgap ( E_g ) and color of ceramic pigments is of considerable importance in materials science research. In this work, we investigate the E_g and color of Cr _x Sb _x Ti _1−2x O _2 rutile pigments by combining experimental, density functional theory (DFT and DFT+ U ) calculations, and neural network approaches. The main novelty of this study is the application of classical/hybrid quantum–classical neural networks to the prediction of pigment color and E_g . Cr/Sb co-doped rutile pigment was synthesized and characterized, and the electronic structures of undoped and doped TiO_2 were analyzed using first-principles calculations. In parallel, classical and hybrid quantum–classical neural network models were developed and trained on datasets compiled from the Materials Project database and literature-reported rutile-based pigments. The models successfully captured the trends in E_g and chromaticity, with the hybrid architectures providing slightly improved predictive performance and more consistent agreement with experiment. Overall, this work demonstrates an effective framework that links experiment, first-principles calculations, and classical/quantum–classical neural networks for predicting key properties of ceramic pigments, and it points toward the future use of fully quantum machine learning models for materials design.
SN - 2045-2322
ER -