The rapid advancement of nanotechnology has enabled the development of materials with unique properties that differ significantly from their bulk counterparts. Understanding and predicting the properties of nanomaterials, such as their electronic, optical, and mechanical characteristics, is crucial for their application in fields like electronics, energy storage, and catalysis. However, the computational methods used to predict these properties, particularly through quantum mechanical simulations such as Density Functional Theory (DFT), are computationally expensive and time-consuming, especially when applied to large datasets of nanomaterials. This paper proposes a novel approach that integrates machine learning (ML) techniques with DFT simulations to predict the structural and optical properties of nanomaterials. By utilizing a dataset derived from DFT calculations, we train and evaluate multiple machine learning models, including Random Forest, Support Vector Machine (SVM), and Deep Neural Networks (DNN), to predict key properties such as band gap, conductivity, and optical absorption. The goal is to develop a model that reduces the computational burden of traditional simulation methods while maintaining high accuracy and generalizability. The models were trained on a synthetic dataset that simulates the composition, size, and crystal structure of nanomaterials, with target properties generated based on these features. We evaluated the performance of the models using standard regression metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R2. Results show that the DNN model provides the best predictive accuracy, closely followed by the Random Forest model, while the SVM model demonstrated lower performance in this context. Additionally, feature importance analysis revealed that material composition, particle size, and crystal structure were the most influential factors in determining the predicted properties of the nanomaterials. This research demonstrates the potential of machine learning to accelerate the discovery of new nanomaterials by providing a fast and scalable way to predict their properties. By combining the predictive power of ML with quantum mechanical simulations, this study offers an efficient framework for material discovery that can be applied to a wide range of nanomaterial systems.
| Published in | International Journal of Materials Science and Applications (Volume 14, Issue 3) |
| DOI | 10.11648/j.ijmsa.20251403.11 |
| Page(s) | 60-66 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Nanomaterials, MachineLearning, DensityFunctionalTheory(DFT),MaterialPropertiesPrediction, DeepNeural Networks (DNN)
| [1] | H. Mohammed, F. Mia, J. Wiggins and S. Desai, “Nanomaterials for Energy Storage: A Review,” Molecules, vol. 30, no. 4, 883, 2025. |
| [2] | W. Kohn and L.J. Sham, “Self-consistent equations including exchange and correlation effects,” Physical Review, vol. 140, pp. A1133-A1138, 1965. |
| [3] | R. Jones and O. Gunnarsson, “The density functional formalism, its applications and prospects,” Reviews of Modern Physics, vol. 61, pp. 689-746, 1989. |
| [4] | X. Zhong, B. Gallagher, S. Liu et al., “Explainable machine learning in materials science,” npj Comput Mater, vol. 8, 204, 2022. |
| [5] | L. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5-32, 2001. |
| [6] | C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273-297, 1995. |
| [7] | Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436-444, 2015. |
| [8] | I. Jolliffe, Principal Component Analysis, 2nd ed. Springer, 2002. |
| [9] | S. Lundberg and S. Lee, “A unified approach to interpreting model predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 4768-4777. |
| [10] | T. C. Egemonye and T. O. Unimuke, “Machine learningassisted DFT-prediction of pristine and endohedral doped Ge12C12 and Si12C12 nanostructures as anode materials for lithium-ion batteries,” Scientific Reports, vol. 14, 26244, 2024. |
| [11] | B. Huang, G. F. von Rudorff, A. Lilienfeld, “The central role of density functional theory in the AI age,” Science, vol. 381, no. 6654, pp. 170-175, 2023. |
| [12] | A. Rana, D. Gautam, et al., “A comprehensive review of machine learning applications for the Internet of Nano Things: challenges and future directions,” Artificial Intelligence Review, vol. 58, 200, 2025. |
| [13] | M. F. Matus and H. Hakkinen, “Rational Design of Targeted Gold Nanoclusters with High Affinity to Integrin avb3 for Combination Cancer Therapy,” Bioconjugate Chemistry, vol. 35, no. 10, pp. 1481-1490, 2024. |
| [14] | H. Wang, J. Sun et al., “Machine learning and DFT database for C-H dissociation on single-atom alloy surfaces in methane decomposition,” Sci Data, vol. 12, 648, 2025. |
| [15] | M. F. Matus, S. Malola, et al., “GraphBNC: Machine Learning Aided Prediction of Interactions Between Metal Nanoclusters and Blood Proteins,” Advanced Materials, vol. 36, no. 47, pp. 1-9, 2024. |
| [16] | J. Liang, D. Wang, et al., “Combination of Density Functional Theory and Machine Learning Provides Deeper Insight of the Underlying Mechanism in the Ultraviolet/Persulfate System,” Environmental Science & Technology, vol. 59, no. 13, pp. 6891-6899, 2025. |
APA Style
Khushalani, B. (2025). Development of a Machine Learning Model for Predicting the Structural and Optical Properties of Nanomaterials Based on Quantum-Mechanical Simulations. International Journal of Materials Science and Applications, 14(3), 60-66. https://doi.org/10.11648/j.ijmsa.20251403.11
ACS Style
Khushalani, B. Development of a Machine Learning Model for Predicting the Structural and Optical Properties of Nanomaterials Based on Quantum-Mechanical Simulations. Int. J. Mater. Sci. Appl. 2025, 14(3), 60-66. doi: 10.11648/j.ijmsa.20251403.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijmsa.20251403.11,
author = {Bharat Khushalani},
title = {Development of a Machine Learning Model for Predicting the Structural and Optical Properties of Nanomaterials Based on Quantum-Mechanical Simulations},
journal = {International Journal of Materials Science and Applications},
volume = {14},
number = {3},
pages = {60-66},
doi = {10.11648/j.ijmsa.20251403.11},
url = {https://doi.org/10.11648/j.ijmsa.20251403.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijmsa.20251403.11},
abstract = {The rapid advancement of nanotechnology has enabled the development of materials with unique properties that differ significantly from their bulk counterparts. Understanding and predicting the properties of nanomaterials, such as their electronic, optical, and mechanical characteristics, is crucial for their application in fields like electronics, energy storage, and catalysis. However, the computational methods used to predict these properties, particularly through quantum mechanical simulations such as Density Functional Theory (DFT), are computationally expensive and time-consuming, especially when applied to large datasets of nanomaterials. This paper proposes a novel approach that integrates machine learning (ML) techniques with DFT simulations to predict the structural and optical properties of nanomaterials. By utilizing a dataset derived from DFT calculations, we train and evaluate multiple machine learning models, including Random Forest, Support Vector Machine (SVM), and Deep Neural Networks (DNN), to predict key properties such as band gap, conductivity, and optical absorption. The goal is to develop a model that reduces the computational burden of traditional simulation methods while maintaining high accuracy and generalizability. The models were trained on a synthetic dataset that simulates the composition, size, and crystal structure of nanomaterials, with target properties generated based on these features. We evaluated the performance of the models using standard regression metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R2. Results show that the DNN model provides the best predictive accuracy, closely followed by the Random Forest model, while the SVM model demonstrated lower performance in this context. Additionally, feature importance analysis revealed that material composition, particle size, and crystal structure were the most influential factors in determining the predicted properties of the nanomaterials. This research demonstrates the potential of machine learning to accelerate the discovery of new nanomaterials by providing a fast and scalable way to predict their properties. By combining the predictive power of ML with quantum mechanical simulations, this study offers an efficient framework for material discovery that can be applied to a wide range of nanomaterial systems.},
year = {2025}
}
TY - JOUR T1 - Development of a Machine Learning Model for Predicting the Structural and Optical Properties of Nanomaterials Based on Quantum-Mechanical Simulations AU - Bharat Khushalani Y1 - 2025/06/03 PY - 2025 N1 - https://doi.org/10.11648/j.ijmsa.20251403.11 DO - 10.11648/j.ijmsa.20251403.11 T2 - International Journal of Materials Science and Applications JF - International Journal of Materials Science and Applications JO - International Journal of Materials Science and Applications SP - 60 EP - 66 PB - Science Publishing Group SN - 2327-2643 UR - https://doi.org/10.11648/j.ijmsa.20251403.11 AB - The rapid advancement of nanotechnology has enabled the development of materials with unique properties that differ significantly from their bulk counterparts. Understanding and predicting the properties of nanomaterials, such as their electronic, optical, and mechanical characteristics, is crucial for their application in fields like electronics, energy storage, and catalysis. However, the computational methods used to predict these properties, particularly through quantum mechanical simulations such as Density Functional Theory (DFT), are computationally expensive and time-consuming, especially when applied to large datasets of nanomaterials. This paper proposes a novel approach that integrates machine learning (ML) techniques with DFT simulations to predict the structural and optical properties of nanomaterials. By utilizing a dataset derived from DFT calculations, we train and evaluate multiple machine learning models, including Random Forest, Support Vector Machine (SVM), and Deep Neural Networks (DNN), to predict key properties such as band gap, conductivity, and optical absorption. The goal is to develop a model that reduces the computational burden of traditional simulation methods while maintaining high accuracy and generalizability. The models were trained on a synthetic dataset that simulates the composition, size, and crystal structure of nanomaterials, with target properties generated based on these features. We evaluated the performance of the models using standard regression metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R2. Results show that the DNN model provides the best predictive accuracy, closely followed by the Random Forest model, while the SVM model demonstrated lower performance in this context. Additionally, feature importance analysis revealed that material composition, particle size, and crystal structure were the most influential factors in determining the predicted properties of the nanomaterials. This research demonstrates the potential of machine learning to accelerate the discovery of new nanomaterials by providing a fast and scalable way to predict their properties. By combining the predictive power of ML with quantum mechanical simulations, this study offers an efficient framework for material discovery that can be applied to a wide range of nanomaterial systems. VL - 14 IS - 3 ER -
Department of Artificial Intelligence, Shri Vishnu Engineering College for Women, Bhimavaram, India
Information