Explainable AI (XAI)-driven experimental and predictive analysis of thermophysical properties in hybrid nanofluids
Shaiza Salahuddin, Zafar Said
Abstract: Hybrid nanofluids are chosen over regular heat transfer fluids because of improved thermophysical properties. Fluid behavior is accurately predicted by machine learning. AI’s contribution to this segment is a rising and valuable research area. But Explainable AI (XAI) integration is explicitly evolving. XAI applications require a robust AI model, and this base is well set. Several researchers used Machine Learning (ML) and traditional AI models for exactness, but XAI is the new area now. Some common AI/ML techniques that researchers have used are Artificial Neural Networks (ANNs); a predominantly used tool for capturing complex, non-linear relationships between input parameters and output properties, Support Vector Machines (SVM); implied for smaller datasets, Random Forest & Gradient Boosting Algorithms (XGBoost, etc.); prevalent for their high accuracy and built-in feature importance metrics, which are a primitive form of (XAI), Genetic Algorithms (GA); Often used for optimization alongside other models. This review proves that AI is remarkably capable of exhibiting nanofluid behavior, but research in explicit Explainable AI (XAI) has a lot of room for improvement. The fundamental purpose of XAI is to transform from a black box (prediction) to a glass box (insight). The techniques that are increasingly being used are SHAP (Shapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations). XAI can identify complex interactions, and it also links data-driven models and physical principles. Researchers can use XAI-guided models to reverse-engineer the problem. Yet there are several challenges in this area. Such as data quality and quantity, model complexity, and standardization. Whereas the gap in the research is to focus on developing XAI-specific frameworks for hybrid nanofluid property prediction, using XAI for the discovery of new nanofluids with tailored properties, and integrating domain knowledge (physics-based rules) directly into XAI models to make them more accurate and trustworthy (often called Physics-Informed ML).
Keywords
XAI, Explainable AI, Hybrid Nano Fluids, Machine Learning (ML), Predictive Accuracy
Published online 6/20/2026, 7 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Shaiza Salahuddin, Zafar Said, Explainable AI (XAI)-driven experimental and predictive analysis of thermophysical properties in hybrid nanofluids, Materials Research Proceedings, Vol. 67, pp 578-584, 2026
DOI: https://doi.org/10.21741/9781644904176-77
The article was published as article 77 of the book Climate Action and Sustainability
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] M. Muneeshwaran, G. Srinivasan, P. Muthukumar, and C.-C. Wang, “Role of hybrid-nanofluid in heat transfer enhancement – A review,” International Communications in Heat and Mass Transfer, vol. 125, p. 105341, 2021. https://doi.org/10.1016/J.ICHEATMASSTRANSFER.2021.105341.
[2] L. Yang, W. Ji, M. Mao, and J.-N. Huang, “An updated review on the properties, fabrication and application of hybrid-nanofluids along with their environmental effects,” J Clean Prod, vol. 257, p. 120408, 2020. https://doi.org/10.1016/j.jclepro.2020.120408.
[3] P. Sharma et al., “Recent Advances in Machine Learning Research for Nanofluid-Based Heat Transfer in Renewable Energy System,” Energy & Fuels, p., 2022. https://doi.org/10.1021/acs.energyfuels.2c01006.
[4] S. Giwa, K. Adegoke, M. Sharifpur, and J. Meyer, “Research trends in nanofluid and its applications: a bibliometric analysis,” Journal of Nanoparticle Research, vol. 24, p., 2022. https://doi.org/10.1007/s11051-022-05453-z.
[5] Z. Said and M. A. Sohail, “10 – Challenges and difficulties in developing hybrid nanofluids and way forward,” in Hybrid Nanofluids, Z. Said, Ed., in Micro and Nano Technologies. , Elsevier, 2022, pp. 233–259. https://doi.org/https://doi.org/10.1016/B978-0-323-85836-6.00010-7.
[6] H. Bacha, N. Ullah, A. Hamid, and N. A. Shah, “A comprehensive review on nanofluids: Synthesis, cutting-edge applications, and future prospects,” International Journal of Thermofluids, p., 2024. https://doi.org/10.1016/j.ijft.2024.100595.
[7] O. Mahian et al., “Recent advances in modeling and simulation of nanofluid flows—Part II: Applications,” Phys Rep, p., 2019. https://doi.org/10.1016/J.PHYSREP.2018.11.003.
[8] L. Longo et al., “Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions,” ArXiv, vol. abs/2310.19775, p., 2023. https://doi.org/10.1016/j.inffus.2024.102301.
[9] J. Li, X. Zhang, B. Xu, and M. Yuan, “Nanofluid research and applications: A review,” International Communications in Heat and Mass Transfer, vol. 127, p. 105543, 2021. https://doi.org/10.1016/J.ICHEATMASSTRANSFER.2021.105543.
[10] J. Philip, “Magnetic nanofluids (Ferrofluids): Recent advances, applications, challenges, and future directions.,” Adv Colloid Interface Sci, vol. 311, p. 102810, 2022. https://doi.org/10.1016/j.cis.2022.102810.
[11] T. W. B. Riyadi et al., “Nanofluid heat transfer and machine learning: Insightful review of machine learning for nanofluid heat transfer enhancement in porous media and heat exchangers as sustainable and renewable energy solutions,” Results in Engineering, p., 2024. https://doi.org/10.1016/j.rineng.2024.103002.
[12] Y. Chen, W. Gong, C. Obrecht, and F. Kuznik, “A review of machine learning techniques for building electrical energy consumption prediction,” Energy and AI, vol. 21, p. 100518, 2025. https://doi.org/https://doi.org/10.1016/j.egyai.2025.100518.
[13] O. Amoo, A. Ajiboye, and M. Oyewola, “Analysis of thermophysical and transport properties of nanofluids using machine learning algorithms,” International Journal of Thermofluids, p., 2024. https://doi.org/10.1016/j.ijft.2024.100566.
[14] R. Avacharmal, “Explainable AI: Bridging the Gap between Machine Learning Models and Human Understanding,” Journal of Informatics Education and Research, p., 2024. https://doi.org/10.52783/jier.v4i2.960.
[15] Z. Altukhi, S. Pradhan, and N. Aljohani, “A Systematic Literature Review of the Latest Advancements in XAI,” Technologies (Basel), p., 2025. https://doi.org/10.3390/technologies13030093.
[16] G. Airlangga, “Decoding Energy Usage Predictions: An Application of XAI Techniques for Enhanced Model Interpretability,” Indonesian Journal of Artificial Intelligence and Data Mining, p., 2024. https://doi.org/10.24014/ijaidm.v7i2.29041.
[17] R. Dwivedi et al., “Explainable AI (XAI): Core Ideas, Techniques, and Solutions,” ACM Comput Surv, vol. 55, pp. 1–33, 2022. https://doi.org/10.1145/3561048.
[18] J. Mendel and P. Bonissone, “Critical Thinking About Explainable AI (XAI) for Rule-Based Fuzzy Systems,” IEEE Transactions on Fuzzy Systems, vol. 29, pp. 3579–3593, 2021. https://doi.org/10.1109/TFUZZ.2021.3079503.
[19] I. D. Mienye and N. Jere, “A Survey of Decision Trees: Concepts, Algorithms, and Applications,” IEEE Access, vol. 12, pp. 86716–86727, 2024. https://doi.org/10.1109/ACCESS.2024.3416838.
[20] H. Adun, I. Wole-Osho, E. Okonkwo, O. Bamisile, M. Dagbasi, and S. Abbasoğlu, “A neural network-based predictive model for the thermal conductivity of hybrid nanofluids,” International Communications in Heat and Mass Transfer, p., 2020. https://doi.org/10.1016/j.icheatmasstransfer.2020.104930.
[21] A. Basu, A. Saha, S. Banerjee, P. Roy, and B. Kundu, “A Review of Artificial Intelligence Methods in Predicting Thermophysical Properties of Nanofluids for Heat Transfer Applications,” Energies (Basel), p., 2024. https://doi.org/10.3390/en17061351.
[22] H. Wang and X. Chen, “A Comprehensive Review of Predicting the Thermophysical Properties of Nanofluids Using Machine Learning Methods,” Industrial & Engineering Chemistry Research, p., 2022. https://doi.org/10.1021/acs.iecr.2c02059.
[23] B. Bakthavatchalam, N. Shaik, and P. Hussain, “An Artificial Intelligence Approach to Predict the Thermophysical Properties of MWCNT Nanofluids,” Processes, p., 2020. https://doi.org/10.3390/pr8060693.
[24] W. Samek, G. Montavon, S. Lapuschkin, C. Anders, and K. Müller, “Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications,” Proceedings of the IEEE, vol. 109, pp. 247–278, 2021. https://doi.org/10.1109/JPROC.2021.3060483.
[25] D. Kulaklıoğlu, “Explainable AI: Enhancing Interpretability of Machine Learning Models,” Human Computer Interaction, p., 2024. https://doi.org/10.62802/z3pde490.
[26] W. Saeed and C. Omlin, “Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities,” ArXiv, vol. abs/2111.06420, p., 2021. https://doi.org/10.1016/j.knosys.2023.110273.
[27] B. Mohammed and S. Rachid, “A Review of Applications Artificial Intelligence in the Nanofluid Domain Hybrid AI Algorithms,” JOURNAL OF ENGINEERING STUDIES, vol. 2, Sep. 2022. https://doi.org/10.31031/AES.2021.02.000537.
[28] A. Maleki, A. Haghighi, and I. Mahariq, “Machine learning-based approaches for modeling thermophysical properties of hybrid nanofluids: A comprehensive review,” J Mol Liq, vol. 322, p. 114843, 2021. https://doi.org/10.1016/j.molliq.2020.114843.
[29] H. Ahmad et al., “Numerical and machine learning based evaluation of ethylene glycol based hybrid nano-structured (TiO2-SWCNTs) fluid flow,” Sci Rep, vol. 15, no. 1, p. 6084, 2025. https://doi.org/10.1038/s41598-025-88789-5.
[30] P. K. Kanti, P. Paramasivam, V. V. Wanatasanappan, S. Dhanasekaran, and P. Sharma, “Experimental and explainable machine learning approach on thermal conductivity and viscosity of water based graphene oxide based mono and hybrid nanofluids,” Sci Rep, vol. 14, no. 1, p. 30967, 2024. https://doi.org/10.1038/s41598-024-81955-1.
[31] M. S. Zamany and A. T. K. Abad, “Statistical Analysis and Accurate Prediction of Thermophysical Properties of ZnO-MWCNT/EG-Water Hybrid Nanofluid Using Several Artificial Intelligence Methods,” Arab J Sci Eng, p., 2024. https://doi.org/10.1007/s13369-024-09565-7.
[32] K. Sharma, P. H. V. S. T. Sai, P. Sharma, P. Kanti, P. Bhramara, and S. Akilu, “Prognostic modeling of polydisperse SiO2/Aqueous glycerol nanofluids’ thermophysical profile using an explainable artificial intelligence (XAI) approach,” Eng. Appl. Artif. Intell., vol. 126, p. 106967, 2023. https://doi.org/10.1016/j.engappai.2023.106967.
[33] A. and M. C. and B. P. and S. W. Holzinger Andreas and Saranti, “Explainable AI Methods – A Brief Overview,” in xxAI – Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, R. and F. R. and M. T. and M. K.-R. and S. W. Holzinger Andreas and Goebel, Ed., Cham: Springer International Publishing, 2022, pp. 13–38. https://doi.org/10.1007/978-3-031-04083-2_2.
[34] Md. R. Karim et al., “Explainable AI for Bioinformatics: Methods, Tools, and Applications,” Brief Bioinform, p., 2022. https://doi.org/10.48550/arXiv.2212.13261.
[35] R. Ibrahim and M. Shafiq, “Explainable Convolutional Neural Networks: A Taxonomy, Review, and Future Directions,” ACM Comput Surv, vol. 55, pp. 1–37, 2022. https://doi.org/10.1145/3563691.
[36] A. Abusitta, M. Q. Li, and B. C. M. Fung, “Survey on Explainable AI: Techniques, challenges and open issues,” Expert Syst Appl, vol. 255, no. C, Dec. 2024. https://doi.org/10.1016/j.eswa.2024.124710.
