Leveraging Machine Learning in Materials Science Challenges, Opportunities, and Solutions
Date
2025-10-25
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Electrical and Electronic Engineering (EEE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
Abstract
The discovery of new materials, particularly perovskites, plays a crucial role in
advancing technologies in energy and electronics. Traditional approaches to finding
new materials experimental synthesis and computer simulations can be time-
consuming and costly. This thesis specifically explores the application of machine
learning (ML) for a more effective additive material prediction, taking perovskite
materials classified for formability and stability properties as examples. We introduce
an advanced ML architecture employing complex algorithms that can predict material
properties and tackle issues such as class imbalance in materials databases. SMOTE
and Random Oversampling are two standard sampling methods that unfortunately do
not work well with materials science datasets, as they tend to be very noisy and
unbalanced. To address this issue, in this paper, we propose a novel hybrid sampling
approach named Difficulty-Directed Hybrid Sampling (DD-Hybrid). This weak
method utilizes oversampling of informative minority samples and pruning of majority
class instances already informed about redundancy. This approach has the advantage
of making ML models more robust and stronger in a situation of unbalanced data with
important but rare instances (i.e., stable structures are poorly represented). The
experimental results demonstrate that DD-Hybrid outperforms the existing methods of
SMOTE, Random Oversampling and improves classification accuracy and prediction
of material properties as well. This paper demonstrates how ML might transform
materials science, particularly through correcting any data imbalance and scaling
models using the proposed algorithm.
Description
Supervised by
Mr. Asif Newaz,
Lecturer,
Department of Electrical and Electronic Engineering (EEE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Electrical and Electronic Engineering, 2025
Keywords
Citation
1. M. U. Ahmad, A. A. Rahman Akib, M. M. Sarker Raihan, and A. B. Shams, "ABO₃ Perovskites’ Formability Prediction and Crystal Structure Classification using Machine Learning," arXiv preprint, vol. 2022, no. 10, pp. 1–16, 2022. [Online]. Available: https://arxiv.org/abs/2201.07831. 2. X. Zhai, F. Ding, Z. Zhao, A. Santomauro, F. Luo, and J. Tong, "Predicting the formation of fractionally doped perovskite oxides by a function-confined machine learning method," Commun. Mater., vol. 3, p. 42, 2022. [Online]. Available: https://doi.org/10.1038/s43246-022-00269-9. 3. D. Ni, W. Wu, Y. Guo, S. Gong, and Q. Wang, "Identifying key parameters for predicting materials with low defect generation efficiency by machine learning," Comput. Mater. Sci., vol. 191, p. 110306, 2021. [Online]. Available: https://doi.org/10.1016/j.commatsci.2021.110306. 4. S. Behara, T. Poonawala, and T. Thomas, "Crystal structure classification in ABO₃ perovskites via machine learning," Comput. Mater. Sci., vol. 188, p. 110191, 2020. [Online]. Available: https://doi.org/10.1016/j.commatsci.2020.110191. 5. G. S. Thoppil and A. Alankar, "Predicting the formation and stability of oxide perovskites by extracting underlying mechanisms using machine learning," arXiv preprint, vol. 2022, no. 10, pp. 1–20, 2022. [Online]. Available: https://arxiv.org/abs/2201.07831. 6. S. Bhattacharya and A. Roy, "Linking stability with molecular geometries of perovskites and lanthanide richness using machine learning methods," arXiv preprint, vol. 2024, no. 9, pp. 1–30, 2024. [Online]. Available: https://arxiv.org/abs/2409.13007. 7. Q. Tao, P. Xu, M. Li, and W. Lu, "Machine learning for perovskite materials design and discovery," npj Comput. Mater., vol. 7, no. 23, 2021. [Online]. Available: https://doi.org/10.1038/s41524-021-00495-8. 8. M. Chen, Z. Yin, Z. Shan, X. Zheng, L. Liu, Z. Dai, J. Zhang, S. (F.) Liu, and Z. Xu, "Application of machine learning in perovskite materials and devices: A review," J. Energy Chem., vol. 94, pp. 254–272, 2024. [Online]. Available: 53 https://doi.org/10.1016/j.jechem.2024.02.035. 9. Y. Zhang and X. Xu, "Predicting lattice parameters for orthorhombic distorted- perovskite oxides via machine learning," Solid State Sci., vol. 113, p. 106541, 2021. [Online]. Available: https://doi.org/10.1016/j.solidstatesciences.2021.106541. 10. A. Talapatra, B. P. Uberuaga, C. R. Stanek, and G. Pilania, "A machine learning approach for the prediction of formability and thermodynamic stability of single and double perovskite oxides," Chem. Mater., vol. 33, pp. 845–858, 2021. [Online]. Available: https://doi.org/10.1021/acs.chemmater.0c03402. 11. N. Gupta, R. Kumar, A. Alankar, et al., "Machine learning-based discovery of novel oxide and halide perovskites for energy storage," J. Alloys Compd., vol. 1010, p. 177470, 2025. [Online]. Available: https://doi.org/10.1016/j.jallcom.2024.177470. 12. E. T. Chenebuah and D. T. Chenebuah, "An inorganic ABX3 perovskite materials dataset for target property prediction and classification using machine learning," arXiv preprint, vol. 2023, no. 7, pp. 1–15, https://github.com/chenebuah/ML_abx3_dataset. 2023. [Online]. Available: 13. A. Newaz, A. U. R. Adib, and T. Jabid, "iCost: A novel instance complexity-based cost-sensitive learning framework," arXiv preprint, vol. 2024, no. 10, pp. 1–20, 2024. [Online]. Available: https://doi.org/10.1016/j.knosys.2024.108634. 14. M. S. Mohosheu, A. Al-Amin, M. A. al Noman, T. Jabid, and A. Newaz, "A comprehensive evaluation of sampling techniques in addressing class imbalance across diverse datasets," IEEE, vol. 6th International Conference on Electrical Engineering and Information & Communication Technology, Dhaka, Bangladesh, 2024. [Online]. Available: https://doi.org/10.1109/ICEEICT.2024.177470. 15. R. Zhao, B. Xing, H. Mu, Y. Fu, and L. Zhang, "Evaluation of performance of machine learning methods in mining structure–property data of halide perovskite materials," Chinese Phys. B, vol. 31, p. 056302, 2022. [Online]. Available: https://doi.org/10.1088/1674-1056/ac5d2d. 16. D. Vijay Anand, Q. Xu, J. J. Wee, K. Xia, and T. C. Sum, "Topological feature engineering for machine learning based halide perovskite materials design," npj Computational Materials, vol. 8, p. 203, 2022. [Online]. Available: https://doi.org/10.1038/s41524-022-00883-8. 17. B. Deng, P. Zhong, K. Jun, J. Riebesell, K. Han, C. J. Bartel, and G. Ceder, "CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling," Nature Machine Intelligence, vol. 5, pp. 1031-1041, 2023. [Online]. 54 Available: https://doi.org/10.1038/s42256-023-00716-3. 18. K. T. Butler, J. M. Frost, J. M. Skelton, K. L. Svanea, and A. Walsh, "Computational materials design of crystalline solids," Chem. Soc. Rev., vol. 45, pp. 1826-1854, 2016. [Online]. Available: https://doi.org/10.1039/c5cs00841g. 19. X. Cai, Y. Zhang, Z. Shi, Y. Chen, Y. Xia, A. Yu, F. Xie, H. Shao, H. Zhu, D. Fu, Y. Zhan, and H. Zhang, "Discovery of lead-free perovskites for high-performance solar cells via machine learning: Ultrabroadband absorption, low radiative recombination, and enhanced thermal conductivities," Adv. Sci., vol. 9, p. 2103648, 2022. [Online]. Available: https://doi.org/10.1002/advs.202103648. 20. V. Gladkikh, D. Y. Kim, A. Hajibabaei, A. Jana, C. W. Myung, and K. S. Kim, "Machine learning for predicting the band gaps of ABX3 perovskites from elemental properties," J. Phys. Chem. C, vol. 124, pp. 8905-8918, 2020. [Online]. Available: https://doi.org/10.1021/acs.jpcc.9b11768. 21. G. H. Gu, J. Jang, J. Noh, A. Walsh, and Y. Jung, "Perovskite synthesizability using graph neural networks," npj Computational Materials, vol. 8, p. 71, 2022. [Online]. Available: https://doi.org/10.1038/s41524-022-00757-z. 22. J. Im, S. Lee, T.-W. Ko, H. W. Kim, Y. Hyon, and H. Chang, "Identifying Pb-free perovskites for solar cells by machine learning," npj Computational Materials, vol. 5, p. 37, 2019. [Online]. Available: https://doi.org/10.1038/s41524-019-0177-0. 23. I. Kuzmanovski, S. Dimitrovska-Lazova, and S. Aleksovska, "Examination of the influence of different variables on prediction of unit cell parameters in perovskites using counter-propagation artificial neural networks," Chem. Soc. Rev., vol. 45, pp. 1826-1854, 2012. 24. W. Li, R. Jacobs, and D. Morgan, "Data and supplemental information for predicting the thermodynamic stability of perovskite oxides using machine learning models," Data in Brief, vol. 19, pp. https://doi.org/10.1016/j.dib.2018.05.007. 261-263, 2018. [Online]. Available: 25. W. Li, R. Jacobs, and D. Morgan, "Predicting the thermodynamic stability of perovskite oxides using machine learning models," Comput. Mater. Sci., vol. 150, pp. 454-463, 2018. [Online]. Available: https://doi.org/10.1016/j.commatsci.2018.04.033. 26. S. Liu, J. Wang, Z. Duan, K. Wang, W. Zhang, R. Guo, F. Xie, "Simple Structural Descriptor Obtained from Symbolic Classification for Predicting the Oxygen Vacancy Defect Formation of Perovskites," ACS Appl. Mater. Interfaces, vol. 14, pp. 11758- 11767, 2022. [Online]. Available: https://doi.org/10.1021/acsami.1c24003. 27. Y. Priya, "Machine learning aided design of perovskite oxide materials for photocatalytic water splitting," J. Energy Chem., vol. 60, pp. 351-359, 2021. [Online]. Available: https://doi.org/10.1016/j.jechem.2021.01.035. 55 28. S. Rath, S. P. G., N. N., and T. Thomas, "Discovery of direct band gap perovskites for light harvesting by using machine learning," Comput. Mater. Sci., vol. 210, p. 111476, 2022. [Online]. Available: https://doi.org/10.1016/j.commatsci.2022.111476. 29. K. Takahashi, L. Takahashi, I. Miyazato, and Y. Tanaka, "Searching for hidden perovskite materials for photovoltaic systems by combining data science and first principle calculations," ACS Photonics, vol. 7, pp. 1571-1580, 2021. [Online]. Available: https://doi.org/10.1021/acsphotonics.7b01479. 30. W. Lu, Q. Tao, Y. Sheng, L. Li, and M. Li, "Machine learning aided design of perovskite oxide materials for photocatalytic water splitting," J. Energy Chem., vol. 60, pp. 351-359, 2021. https://doi.org/10.1016/j.jechem.2021.01.035. [Online]. Available: 31. J. Williams, A. Mukherjee, and K. Rajan, "Deep learning based prediction of perovskite lattice parameters from Hirshfeld surface fingerprints," J. Phys. Chem. Lett., vol. 11, pp. https://doi.org/10.1021/jcc.21707. 7462-7468, 2020. [Online]. Available: 32. C. W. Yap, "PaDEL-Descriptor: An open source software to calculate molecular descriptors and fingerprints," J. Comput. Chem., vol. 32, pp. 1466-1474, 2011. [Online]. Available: https://doi.org/10.1002/jcc.21707. 33. T. Xie and J. C. Grossman, "Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties," Phys. Rev. Lett., vol. 120, p. 145301, 2018. https://doi.org/10.1103/PhysRevLett.120.145301. [Online]. Available: 34. G. Cheng, X.-G. Gong, and W.-J. Yin, "Crystal structure prediction by combining graph network and optimization algorithm," Nature Communications, vol. 13, p. 1492, 2022. [Online]. Available: https://doi.org/10.1038/s41467-022-29241-4. 35. Z. Li, Q. Xu, Q. Sun, Z. Hou, and W.-J. Yin, "Thermodynamic Stability Landscape of Halide Double Perovskites via High‐Throughput Computing and Machine Learning," Adv. Funct. Mater., vol. 29, p. 1807280, 2019. [Online]. Available: https://doi.org/10.1002/adfm.201807280. 36. S. Zhang, T. Lu, P. Xu, Q. Tao, M. Li, and W. Lu, "Predicting the Formability of Hybrid Organic–Inorganic Perovskites via an Interpretable Machine Learning Strategy," J. Phys. Chem. Lett., vol. 12, pp. 7423−7430, 2021. [Online]. Available: https://doi.org/10.1021/acs.jpclett.1c02053. 37. Q. Zhang, J. Wang, G. Liu, "Auxiliary guidance manufacture and revealing potential mechanism of perovskite solar cell using machine learning," J. Energy Chem., vol. 77, pp. 200–208, 2023. [Online]. Available: https://doi.org/10.1016/j.jechem.2023. 38. J. Chen, W. Xu, and R. Zhang, "Δ-Machine learning-driven discovery of double hybrid organic–inorganic perovskites," J. Mater. Chem. A, vol. 10, pp. 1402−1413, 2022. 56 [Online]. Available: https://doi.org/10.1039/d1ta09911f. 39. P. Branco, L. Torgo, R. P. Ribeiro, "A survey of predictive modeling on imbalanced domains," ACM Computing Surveys (CSUR), vol. 49, no. 2, pp. 1–50, 2016. [Online]. Available: https://doi.org/10.1145/2899478. 40. G. Haixiang, L. Yijing, J. Shang, G. Mingyun, H. Yuanyue, G. Bing, "Learning from class-imbalanced data: Review of methods and applications," Expert Systems with Applications, vol. 73, pp. 220–239, https://doi.org/10.1016/j.eswa.2016.12.031. 2017. [Online]. Available: 41. A. Newaz, S. Muhtadi, F. S. Haq, "An intelligent decision support system for the accurate diagnosis of cervical cancer," Knowledge-Based Systems, vol. 245, p. 108634, 2022. [Online]. Available: https://doi.org/10.1016/j.knosys.2022.108634. 42. A. Fernández, S. García, M. Galar, R. C. Prati, B. Krawczyk, F. Herrera, Learning from imbalanced data sets, vol. 10, Springer, 2018. 43. S. Susan, A. Kumar, "The balancing trick: Optimized sampling of imbalanced datasets—a brief survey of the recent state of the art," Engineering Reports, vol. 3, no. 4, p. e12298, 2021. [Online]. Available: https://doi.org/10.1002/eng2.12298. 44. M. S. Santos, P. H. Abreu, N. Japkowicz, A. Fernández, J. Santos, "A unifying view of class overlap and imbalance: Key concepts, multi-view panorama, and open avenues for research," Information Fusion, vol. 89, pp. 228–253, 2023. [Online]. Available: https://doi.org/10.1016/j.inffus.2023.02.008. 45. C. Elkan, "The foundations of cost-sensitive learning," in International Joint Conference on Artificial Intelligence, vol. 17, Lawrence Erlbaum Associates Ltd, 2001, pp. 973–978. 46. N. Japkowicz and S. Stephen, "The class imbalance problem: A systematic study," Intelligent Data Analysis, vol. 6, no. 5, pp. 429-449, Jan. 2002. [Online]. Available: https://doi.org/10.3233/IDA-2002-6504. 47. A. Fernández, S. García, M. Galar, R. C. Prati, B. Krawczyk, and F. Herrera, Learning from Imbalanced Data Sets, Cham: Springer International Publishing, 2018. [Online]. Available: https://doi.org/10.1007/978-3-319-98074-4. 48. P. Branco, L. Torgo, and R. P. Ribeiro, "A Survey of Predictive Modeling on Imbalanced Domains," ACM Comput. Surv., vol. 49, no. 2, pp. 1–50, Jun. 2017. [Online]. Available: https://doi.org/10.1145/2907070. 49. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002. [Online]. Available: https://doi.org/10.1613/JAIR.953. 57 50. D. Elreedy and A. F. Atiya, "A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance," Inf. Sci. (N.Y.), vol. 505, pp. 32–64, Dec. 2019. [Online]. Available: https://doi.org/10.1016/j.ins.2019.07.070. 18, 51. L. Ma and S. Fan, "CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests," BMC Bioinformatics, vol. no. 1, p. 169, Dec. https://doi.org/10.1186/s12859-017-1578-z. 2017. [Online]. Available: 52. G. Douzas and F. Bacao, "Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE," Inf. Sci. (N.Y.), vol. 501, pp. 118–135, Oct. 2019. [Online]. Available: https://doi.org/10.1016/j.ins.2019.06.007.