Stacking Machine Learning Approach for Predicting Thermal Stability of Zinc–Metal Organic Frameworks (Zn-MOF)
- Ananta Surya Pratama Universitas Dian Nuswantoro, Semarang, Indonesia
- Muhammad Diva Irnanda Universitas Dian Nuswantoro, Semarang, Indonesia
- Taufiqul Umam Universitas Dian Nuswantoro, Semarang, Indonesia
- Dandy Prasetyo Nugroho Universitas Dian Nuswantoro, Semarang, Indonesia
-
Harun Al Azies
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
(*) Corresponding Author
Abstract
Thermal stability is a fundamental parameter that determines the feasibility of Metal Organic Frameworks (MOF) for high-temperature industrial applications, including catalysis, gas purification, and energy storage. Experimental evaluation of thermal stability, while accurate, is often costly and time-consuming, highlighting the need for computational prediction models that are both efficient and dependable. This study develops a Quantitative Structure Property Relationship (QSPR) model using a stacking ensemble regression framework to predict the thermal stability of Zn-MOFs. The stacking approach combines Linear Regression, Lasso Regression, and Huber Regression as base learners, with Linear Regression serving as the meta-model, thereby leveraging the complementary strengths of individual algorithms. Results demonstrate that the stacking ensemble consistently outperformed all single models, delivering highly reliable predictions that remained stable across multiple validation scenarios. Furthermore, external validation with experimental data confirmed the model’s robustness and its ability to generalize beyond the training dataset. These findings underline the reliability of stacking as not only a tool for improving accuracy but also for ensuring predictive stability and reproducibility. The study highlights the potential of machine learning, particularly ensemble methods, as a powerful and trustworthy predictive framework for the rational design of thermally stable MOFs, offering both scientific and industrial significance in sustainable energy applications.
Downloads
References
“CO2 Emissions – Global Energy Review 2025 – Analysis,” IEA. Accessed: Sept. 22, 2025. [Online]. Available: https://www.iea.org/reports/global-energy-review-2025/co2-emissions
N. Liang and Y. Zhao, “A review on thermal stability of nanostructured materials,” J. Alloys Compd., vol. 938, p. 168528, 2023, doi: https://doi.org/10.1016/j.jallcom.2022.168528.
G. Cai, P. Yan, L. Zhang, H.-C. Zhou, and H.-L. Jiang, “Metal–Organic Framework-Based Hierarchically Porous Materials: Synthesis and Applications,” Chem. Rev., vol. 121, no. 20, pp. 12278–12326, 2021, doi: 10.1021/acs.chemrev.1c00243.
G. Valdebenito, M. Gonzaléz-Carvajal, L. Santibañez, and P. Cancino, “Metal–Organic Frameworks (MOFs) and Materials Derived from MOFs as Catalysts for the Development of Green Processes,” Catalysts, vol. 12, no. 2, 2022, doi: 10.3390/catal12020136.
M. Yu et al., “Quantitative structure-property relationship (QSPR) framework assists in rapid mining of highly Thermostable polyimides,” Chem. Eng. J., vol. 465, p. 142768, 2023, doi: https://doi.org/10.1016/j.cej.2023.142768.
S. Datta, V. A. Dev, and M. R. Eden, “Developing Non-linear Rate Constant QSPR using Decision Trees and Multi-Gene Genetic Programming,” in 13th International Symposium on Process Systems Engineering (PSE 2018), vol. 44, M. R. Eden, M. G. Ierapetritou, and G. P. Towler, Eds., in Computer Aided Chemical Engineering, vol. 44. , Elsevier, 2018, pp. 2473–2478. doi: https://doi.org/10.1016/B978-0-444-64241-7.50407-9.
M. Akrom, S. Rustad, A. G. Saputro, A. Ramelan, F. Fathurrahman, and H. K. Dipojono, “A combination of machine learning model and density functional theory method to predict corrosion inhibition performance of new diazine derivative compounds,” Mater. Today Commun., vol. 35, p. 106402, June 2023, doi: 10.1016/j.mtcomm.2023.106402.
M. M. Hossain and K. Roy, “QSPR modeling of thermal stability of reactive and self-reactive chemicals using 2D descriptors: Predictions of heat of decomposition, Self-Accelerating decomposition temperature, and onset temperature,” Mater. Today Commun., vol. 46, p. 112751, 2025, doi: https://doi.org/10.1016/j.mtcomm.2025.112751.
Z. Zhang et al., “Machine learning aided high-throughput prediction of ionic liquid@MOF composites for membrane-based CO2 capture,” J. Membr. Sci., vol. 650, p. 120399, 2022, doi: https://doi.org/10.1016/j.memsci.2022.120399.
J. Usman, S. I. Abba, N. Baig, N. Abu-Zahra, S. W. Hasan, and I. H. Aljundi, “Design and Machine Learning Prediction of In Situ Grown PDA-Stabilized MOF (UiO-66-NH2 ) Membrane for Low-Pressure Separation of Emulsified Oily Wastewater,” ACS Appl. Mater. Interfaces, vol. 16, no. 13, pp. 16271–16289, Apr. 2024, doi: 10.1021/acsami.4c00752.
H. Daglar, S. Aydin, and S. Keskin, “MOF-based MMMs Breaking the Upper Bounds of Polymers for a Large Variety of Gas Separations,” Sep Purif Technol, vol. 281, p. 119811, 2022.
H. Liang, K. Jiang, T.-A. Yan, and G.-H. Chen, “XGBoost: An Optimal Machine Learning Model with Just Structural Features to Discover MOF Adsorbents of Xe/Kr,” ACS Omega, vol. 6, no. 13, pp. 9066–9076, 2021, doi: 10.1021/acsomega.1c00100.
V. C. Anadebe, V. I. Chukwuike, S. Ramanathan, and R. C. Barik, “Cerium-based metal organic framework (Ce-MOF) as corrosion inhibitor for API 5L X65 steel in CO2- saturated brine solution: XPS, DFT/MD-simulation, and machine learning model prediction,” Process Saf. Environ. Prot., vol. 168, pp. 499–512, 2022, doi: https://doi.org/10.1016/j.psep.2022.10.016.
H. A. Azies, M. Akrom, S. Rustad, and H. K. Dipojono, “Robust Machine Learning for Predicting Thermal Stability of Metal-Organic Framework,” Chem. Afr., vol. 7, no. 8, pp. 4669–4681, Oct. 2024, doi: 10.1007/s42250-024-01080-4.
M. Moharramnejad, L. Tayebi, A. R. Akbarzadeh, and A. Maleki, “A simple, robust, and efficient structural model to predict thermal stability of zinc metal-organic frameworks (Zn-MOFs): The QSPR approach,” Microporous Mesoporous Mater., vol. 336, p. 111815, May 2022, doi: 10.1016/j.micromeso.2022.111815.
C. Ghosh, “Data Pre-processing,” in Data Analysis with Machine Learning for Psychologists: Crash Course to Learn Python 3 and Machine Learning in 10 hours, Cham: Springer International Publishing, 2022, pp. 55–85. doi: 10.1007/978-3-031-14634-3_3.
K. Purohit, “Separation of Data Cleansing Concept from EDA,” Int. J. Data Sci. Anal., vol. 7, no. 3, p. 89, 2021, doi: 10.11648/j.ijdsa.20210703.16.
Y. Feng and Q. Wu, “A statistical learning assessment of Huber regression,” J. Approx. Theory, vol. 273, p. 105660, Jan. 2022, doi: 10.1016/j.jat.2021.105660.
J. O. Ogutu, T. Schulz-Streeck, and H.-P. Piepho, “Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions,” BMC Proc., vol. 6, no. 2, p. S10, May 2012, doi: 10.1186/1753-6561-6-S2-S10.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, July 2021, doi: 10.7717/peerj-cs.623.
T. A. Munshi, K. Popi, L. N. Jahan, M. F. Howladar, and M. Hashan, “Stacking modeling with genetic algorithm-based hyperparameter tuning for uniaxial compressive strength prediction,” Appl. Comput. Geosci., vol. 27, p. 100276, Sept. 2025, doi: 10.1016/j.acags.2025.100276.
X.-Q. Wang et al., “A water-stable zinc( II )–organic framework as a multiresponsive luminescent sensor for toxic heavy metal cations, oxyanions and organochlorine pesticides in aqueous solution,” Dalton Trans., vol. 48, no. 44, pp. 16776–16785, 2019, doi: 10.1039/C9DT03195B.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Stacking Machine Learning Approach for Predicting Thermal Stability of Zinc–Metal Organic Frameworks (Zn-MOF)
Pages: 1390-1399
Copyright (c) 2025 Ananta Surya Pratama, Muhammad Diva Irnanda, Taufiqul Umam, Dandy Prasetyo Nugroho, Harun Al Azies
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
