[Link].
com/scientificreports
OPEN Computational fluid dynamic and
machine learning modeling of
nanofluid flow for determination
of temperature distribution and
models comparison
Farag M. A. Altalbawy1, Ahmad Alkhayyat2,3,4, Ramdevsinh Jhala5, Anupam Yadav6,
T. Ramachandran7, Aman Shankhyan8, A. Karthikeyan9, Dhirendra Nath Thatoi10 &
Vladimir Vladimirovich Sinitsin11
This paper introduces an approach to temperature prediction by employing three distinct machine
learning models: K-Nearest Neighbors (KNN), Gaussian Process Regression (GPR), and Multi-layer
Perceptron (MLP) which are integrated into Computational Fluid Dynamics (CFD). The dataset
consists of inputs, represented by the features x and y, and the corresponding output, which is the
temperature. The case study is fluid flow of nanofluid through a pipe and the nanofluid contains CuO
particles. To enhance model efficacy, the Political Optimizer (PO) algorithm was utilized for fine-tuning
purposes. The findings substantiate the capability of the optimized frameworks in delivering precise
temperature estimations. GPR yielded a notable R2 value of 0.998, reflecting a strong concordance
between the estimated and actual measurements. In a comparable manner, the KNN approach
exhibited outstanding predictive performance, also attaining an R2 value of 0.998. MLP, although
slightly lower in performance compared to the other models, still proves to be a reliable predictor of
temperature values, with an R-squared score of 0.984. Overall, the combination of the PO algorithm
and the machine learning models showcases promising results in temperature prediction. The study’s
findings offer valuable insights for decision-making processes in a variety of domains that rely on
accurate temperature forecasting.
Keywords Nanofluid, Heat transfer, K-Nearest neighbors, Gaussian process regression, Multi-layer
perceptron
Computational fluid dynamics (CFD) has been recognized as a great tool for simulation of complex fluid flow
where the fluid flow in complex geometry can be simulated with great accuracy1–3. The recent development of
nanofluids has opened new horizon for enhancement of heat and mass transfer in fluids which is facilitated
1Department of Chemistry, University College of Duba, University of Tabuk, Tabuk, Saudi Arabia. 2Department
of Computers Techniques Engineering, College of Technical Engineering, The Islamic University, Najaf, Iraq.
3Department of Computers Techniques Engineering, College of Technical Engineering, The Islamic University
of Al Diwaniyah, Al Diwaniyah, Iraq. 4Department of Computers Techniques Engineering, College of Technical
Engineering, The Islamic University of Babylon, Babylon, Iraq. 5Marwadi University Research Center, Department of
Mechanical Engineering, Faculty of Engineering & Technology, Marwadi University, Rajkot, Gujarat 360003, India.
6Department of Computer Engineering and Application, GLA University, Mathura 281406, India. 7Department
of Mechanical Engineering, School of Engineering and Technology, JAIN (Deemed to be University), Bangalore,
Karnataka, India. 8Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and
Technology, Chitkara University, Rajpura, Punjab 140401, India. 9Department of Mechanical Engineering,
Sathyabama Institute of Science and Technology, Chennai, Tamil Nadu, India. 10Department of Mechanical
Engineering, Siksha ’O’ Anusandhan (Deemed to be University), Bhubaneswar, Odisha 751030, India. 11Research
Laboratory of Technical Self-Diagnostics and Self-Control of Devices and Systems, Department of Scientific and
Innovative Activities, Research Institute of Mechanical Engineering, South Ural State University, Lenin prospect 76,
Chelyabinsk 454080, Russian Federation. email: f_altalbawy@[Link]
Scientific Reports | (2025) 15:19073 | [Link] 1
[Link]/scientificreports/
with the aid of nanoparticles. Different nanoparticles have been used for nanofluids to enhance the heat transfer
and the contribution of nanoparticles to total heat transfer efficiency has been investigated via numerical
computations such as CFD method4–7.
The method of CFD has been recognized to be robust in simulation of fluid flow and nanofluids, however
the method is complex and huge computational resources are needed for case studies with large geometries.
Therefore, the less computationally expensive methods are preferred for industrial applications in order to
execute simulations for large geometries. In this regards, machine learning models have been suggested for
combination with CFD where they can be adopted for linking with CFD for better simulation of fluid flows with
less computational times and expenses to enhance the simulation efficiency8,9.
In recent years, the field of Machine Learning (ML) has been a focal point of interest for scholars across a
wide spectrum of academic disciplines. These models now serve as fundamental tools in contemporary research,
facilitating advanced methods for identifying patterns, forecasting outcomes, categorizing data, and supporting
complex decision-making processes10–12. In this study we used K-Nearest Neighbors (KNN), Gaussian Process
Regression (GPR), and Multi-layer Perceptron (MLP) to calculate temperature parameter for simulation of heat
transfer within a nanofluidic system. The models are used to learn synthetic data from a CFD simulation where
temperature distribution in a pipe containing nanofluid is used.
The KNN algorithm offers distinct benefits due to its ability to estimate outcomes by averaging the values
associated with the most proximate instances within the input space. This method determines the K most
similar observations relative to a new input and infers the corresponding output by deriving the mean value
from these selected reference points13. GPR is a non-parametric regression technique that utilizes a Gaussian
process to model the data distribution. By fitting a flexible function to the training data, GPR captures complex
relationships between input features and the target variable. This approach enables accurate predictions while
accounting for uncertainty. GPR’s versatility and ability to model data distributions make it a powerful tool for
regression tasks in diverse domains14. MLP is a widely used ANN-based model for regression tasks. Constructed
with multiple layers of interconnected artificial neurons, the MLP model possesses the remarkable capability to
capture intricate nonlinear patterns and dependencies within the dataset. By leveraging its deep architecture,
MLP provides a powerful tool for accurate and flexible prediction in various domains15.
Dataset
The dataset utilized in the study includes a total of 2000 points, wherein the independent variables are represented
by x and y, while the dependent variable is Temperature. The dataset is the same as data used in the past research
as reported by Zhao9. In this system, x and y represent the spatial coordinate of the pipe geometry where CFD
simulations based on finite volume method are executed to determine the temperature distribution for a fluid
flow inside a pipe containing CuO nanoparticles. Transport phenomena equations are solved numerically via
the finite volume scheme and the results are used for ML modeling. Figure 1 is a histogram that displays the
distribution of the temperature values in the dataset9.
Methodology
Gaussian process regression (GPR)
GPR is a probabilistic regression model that employs a collection of random variables to define a Gaussian
process. The GPR model represents the target variable as a function of input variables and aims to estimate the
underlying function based on observed data. The GPR model is defined as16:
Fig. 1. Distribution of the temperature of nanofluid.
Scientific Reports | (2025) 15:19073 | [Link] 2
[Link]/scientificreports/
y = f (x) + ε
where y represents the target variable, x denotes the input variable, f is the underlying function, and ε represents
the residual error17,18.
K-Nearest neighbors (KNN)
KNN is a robust non-parametric ML model that estimates the target points by utilizing the collective information
from the K nearest neighbors in the feature space. KNN utilizes the resemblance among adjacent data instances
to examine the dataset’s local characteristics for predictive purposes. When presented with a novel input, the
algorithm locates the K most comparable entries within the training data and determines the predicted value by
averaging the outcomes associated with these nearby instances19,20.
The KNN model determines the predicted value y for a given test input x as13:
1 ∑
K
y= yi
K
i=1
where yi represents the target values of the K nearest neighbors.
Multilayer perceptron (MLP)
A MLP represents a type of artificial neural architecture distinguished by several hierarchical strata of interlinked
processing units, often referred to as artificial neurons. In the architecture of the MLP, individual neurons utilize
non-linear activation mechanisms on their received inputs21,22.
The output of an MLP model is calculated through forward propagation, which involves passing the input
through the network layers. The predicted value y for a given input x can be expressed as23,24:
y = f (W2 · σ (W1 · x + b1 ) + b2 )
In this equation, W1 and W2 stand for the weight matrices, b1 and b2 denote the bias vectors, and σ denotes
the activation function applied element-wise.
Data preprocessing
Before applying the regression models, the following data preprocessing steps were performed:
• Outlier Detection: Anomalous data (outlier) identification was conducted through application of the z-score
technique. This approach measures how far an individual observation diverges from the distribution’s central
tendency, expressed in terms of standard deviation units relative to the mean. By determining the z-score
value for each data point, it is possible to identify outliers that deviate significantly from the average values.
Typically, a threshold is set to determine whether a data point is considered an outlier25.
• Normalization: In this study, normalization of the data was performed using the min-max scaler. By utilizing
the min-max scaler, the values of each feature can be effectively transformed to a predetermined range, typ-
ically spanning from 0 to 1. During the scaling process, the minimum value of the feature is subtracted, and
the result is divided by the range between the maximum and minimum values26.
Hyperparameter tuning
This research employed the Political Optimizer (PO) algorithm to adjust hyperparameters effectively. PO
represents an optimization strategy that draws conceptual inspiration from political dynamics and societal
interactions. The algorithm simulates political deliberation, wherein agents exchange perspectives, engage in
mutual influence, and collaboratively progress toward a shared resolution27. The PO algorithm explores the
hyperparameter domain through successive modifications of the positions associated with metaphorical
political parties, where each party embodies a unique configuration of hyperparameters. Through processes akin
to opinion shaping, mutual influence, and inter-party dynamics, the algorithm systematically steers the search
toward optimal configurations that enhance the targeted performance criteria28,29.
Results and discussion
The predictive power of the trained models was determined using various performance metrics. Table 1
summarizes the results obtained.
GPR attained a remarkable coefficient of determination (R2) of 0.99893, reflecting an exceptionally strong
alignment between the model’s predictions and the observed temperature data. The RMSE was found to be
1.2920E-01, demonstrating the model’s capability to accurately estimate temperature fluctuations. Additionally,
the MAPE was measured at 2.97944E-04, indicating a small average deviation between predicted and actual
values.
The KNN model likewise exhibited strong predictive capability, achieving an R2 value of 0.99852, indicative
of a high level of agreement between predicted and actual outcomes. The recorded RMSE of 1.5231E-01
signifies the model’s proficiency in capturing temperature variations, indicating its ability to accurately estimate
temperature values. This conclusion is further supported by the MAPE value of 2.00414E-04, which reinforces
the model’s accuracy in predicting temperature values.
MLP, while slightly lower in performance compared to GPR and KNN, still provided reliable predictions. An
R2 score of 0.98426 was achieved by this model, indicating a strong statistical association between the predicted
Scientific Reports | (2025) 15:19073 | [Link] 3
[Link]/scientificreports/
Model R2 Score RMSE MAPE
GPR 0.99893 1.2920E-01 2.97944E-04
KNN 0.99852 1.5231E-01 2.00414E-04
MLP 0.98426 4.9120E-01 9.27298E-04
Table 1. Performance analysis of different ML models.
Fig. 2. Comparison between estimated and actual temperature values obtained using the GPR model.
results and the observed temperature measurements. The RMSE was measured at 4.9120E-01, reflecting the
model’s ability to estimate temperature fluctuations. A MAPE of 9.27298E-04 signifies a notably low average
discrepancy between the forecasted outcomes and the corresponding observed values, highlighting the model’s
high predictive accuracy.
The obtained results collectively showcase the notable performance of the GPR, KNN, and MLP models in
temperature prediction. Specifically, GPR and KNN exhibit superior accuracy and precision compared to MLP.
These facts can be confirmed using fitting charts in Figs. 2, 3 and 4 which are comparisons of predicted and
observed temperature values using all three models. Figures 5, 6 and 7 also show the three-dimensional surface
of the final models, which are generally similar, but differ in smoothness9.
Also, the GPR model was used as the best model to generate Figs. 8 and 9 which are the effect of coordinates
on temperature. The 2D representation of T distribution is indicated in Fig. 10 which shows agreement with the
results reported by Zhao for simulation of nanofluid flow9. The parabolic observation of T distribution can be
attributed to the velocity profile and the effect of viscous forces inside the fluid which is in a pipe. In fact, the
minimum T can be obtained at the center of tube due to the heat transfer flux imposed on the tube wall, while
heat transfer is driven by convection and conduction through the fluid.
Conclusion
This investigation examined the efficacy of three distinct machine learning models, specifically GPR, KNN, and
MLP in the context of temperature forecasting. Ultimately, the findings of this study suggest that. The training
of the models was conducted on a dataset comprising of input features, namely x and y, and their corresponding
temperature values. The dataset underwent preprocessing procedures, and the models were optimized through
the utilization of the PO (Political Optimizer) algorithm.
The findings indicate that the three models exhibited exceptional performance in forecasting temperature
values. The GPR model attained a remarkable R2 of 0.99893, denoting a robust association between the projected
and observed temperature values. The KNN algorithm exhibited exceptional performance, as evidenced by its
R-squared of 0.99852. Despite obtaining a marginally reduced R2 value of 0.98426, the MLP model demonstrated
dependable predictive capabilities.
The accuracy of the models in estimating temperature fluctuations was confirmed by the RMSE values. The
GPR method yielded an RMSE of 1.2920E-01, whereas the KNN approach resulted in an RMSE of 1.5231E-
01. The MLP model exhibited a comparatively elevated root mean square error (RMSE) value of 4.9120E-01,
suggesting the presence of a certain degree of unpredictability in its forecasts.
Furthermore, the MAPE values were computed to evaluate the typical discrepancy between the projected and
observed temperature values. The GPR and KNN models demonstrated reduced MAPE values (2.97944E-04
Scientific Reports | (2025) 15:19073 | [Link] 4
[Link]/scientificreports/
Fig. 3. Comparison between predicted and actual temperature values obtained using the KNN model.
Fig. 4. Comparison between predicted and actual temperature values obtained using the MLP model.
and 2.00414E-04, respectively), suggesting a diminished mean deviation. The MLP model exhibited a marginally
elevated MAPE metric of 9.27298E-04; however, it yielded predictions that were reasonably precise.
Scientific Reports | (2025) 15:19073 | [Link] 5
[Link]/scientificreports/
Fig. 5. 3D surface of GPR model.
Fig. 6. 3D surface of KNN model.
Scientific Reports | (2025) 15:19073 | [Link] 6
[Link]/scientificreports/
Fig. 7. 3D surface of MLP model.
Fig. 8. Temperature change with x-coordinate change.
Scientific Reports | (2025) 15:19073 | [Link] 7
[Link]/scientificreports/
Fig. 9. Temperature change with y-coordinate change.
Fig. 10. Contour plot of temperature.
Data availability
The datasets used during the current study are available from the corresponding author on reasonable request.
Received: 31 March 2025; Accepted: 19 May 2025
References
1. Bode, F. et al. Impact of realistic boundary conditions on CFD simulations: A case study of vehicle ventilation. Build. Environ. 267,
112264 (2025).
2. Luan, X. et al. Calibration and sensitivity analysis of under-expanded hydrogen jet CFD simulation based on surrogate modeling.
J. Loss Prev. Process Ind. 94, 105535 (2025).
3. Yao, N. N. et al. Progress in CFD simulation for ammonia-fueled internal combustion engines and gas turbines. J. Energy Inst. 119,
101951 (2025).
4. Aldossary, S., Sakout, A. & El Hassan, M. CFD simulations of heat transfer enhancement using Al2O3–air nanofluid flows in the
annulus region between two long concentric cylinders. Energy Rep. 8, 678–686 (2022).
5. Delavari, V. & Hashemabadi, S. H. CFD simulation of heat transfer enhancement of Al2O3/water and Al2O3/ethylene glycol
nanofluids in a car radiator. Appl. Therm. Eng. 73(1), 380–390 (2014).
6. Natarajan, A. et al. CFD simulation of heat transfer enhancement in circular tube with twisted tape insert by using nanofluids.
Mater. Today: Proc. 21, 572–577 (2020).
7. Zhang, S. et al. Turbulent heat transfer and flow analysis of hybrid Al2O3-CuO/water nanofluid: an experiment and CFD
simulation study. Appl. Therm. Eng. 188, 116589 (2021).
8. Godasiaei, S. H. & Kamali, H. A. Evaluating machine learning as an alternative to CFD for heat transfer modeling. Microgravity
Sci. Technol. 37(1), 6 (2025).
Scientific Reports | (2025) 15:19073 | [Link] 8
[Link]/scientificreports/
9. Zhao, H. Computational modeling of nanofluid heat transfer using fuzzy-based bee algorithm and machine learning method. Case
Stud. Therm. Eng. 54, 104021 (2024).
10. Polikar, R. Ensemble learning. In Ensemble Machine Learning, 1–34 (Springer, 2012).
11. Sagi, O. & Rokach, L. Ensemble learning: A survey. Wiley Interdiscip. Rev. Data Min. Knowl. Discov.. 8(4), e1249 (2018).
12. Almehizia, A. A. et al. Numerical optimization of drug solubility inside the supercritical carbon dioxide system using different
machine learning models. J. Mol. Liq. 392, 123466 (2023).
13. Kramer, O. & Kramer, O. K-nearest neighbors. Dimensionality reduction with unsupervised nearest neighbors, 13–23 (2013).
14. Wang, J. An intuitive tutorial to Gaussian processes regression. arXiv preprint arXiv:2009.10862 (2020).
15. Ramchoun, H. et al. Multilayer perceptron: Architecture optimization and training. (2016).
16. Rasmussen, C. E. Gaussian processes in machine learning. In Summer School on Machine Learning (Springer, 2003).
17. Ebden, M. Gaussian processes: A quick introduction. arXiv preprint arXiv:1505.02965 (2015).
18. Ruiz, A. V. & Olariu, C. A general algorithm for exploration with gaussian processes in complex, unknown environments. In IEEE
International Conference on Robotics and Automation (ICRA). (IEEE, 2015).
19. Cover, T. Estimation by the nearest neighbor rule. IEEE Trans. Inf. Theory. 14(1), 50–55 (1968).
20. Chen, C. R. & Three Kartini, U. K-nearest neighbor neural network models for very short-term global solar irradiance forecasting
based on meteorological data. Energies. 10(2), 186 (2017).
21. Gardner, M. W. & Dorling, S. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric
sciences. Atmos. Environ. 32(14–15), 2627–2636 (1998).
22. Amendolia, S. R. et al. A comparative study of k-nearest neighbour, support vector machine and multi-layer perceptron for
thalassemia screening. Chemometr. Intell. Lab. Syst. 69(1–2), 13–20 (2003).
23. Mielniczuk, J. & Tyrcha, J. Consistency of multilayer perceptron regression estimators. Neural Netw. 6(7), 1019–1022 (1993).
24. Noriega, L. Multilayer Perceptron Tutorial., vol. 4, 5 (School of Computing, Staffordshire University, 2005).
25. Aggarwal, V. et al. Detection of spatial outlier by using improved Z-score test. In 2019 3rd International Conference on Trends in
Electronics and Informatics (ICOEI). (IEEE, 2019).
26. Kappal, S. Data normalization using median median absolute deviation MMAD based Z-score for robust predictions vs. min–max
normalization. Lond. J. Res. Sci. Nat. Formal. (2019).
27. Askari, Q., Younas, I. & Saeed, M. Political optimizer: A novel socio-inspired meta-heuristic for global optimization. Knowl. Based
Syst. 195, 105709 (2020).
28. Manita, G. & Korbaa, O. Binary political optimizer for feature selection using gene expression data. Comput. Intell. Neurosci. 2020.
(2020).
29. Awad, R. Sizing optimization of truss structures using the political optimizer (PO) algorithm. In Structures (Elsevier, 2021).
Acknowledgements
The authors are thankful to the Higher Education of the Russian Federation for supporting this work (through
project No. FENU-2023-0010) for their support of this work.
Author contributions
Farag M. A. Altalbawy: Writing, Investigation, Methodology, Software, [Link] Alkhayyat: Writing,
Investigation, Methodology, [Link] Jhala: Writing, Investigation, Methodology, [Link]-
upam Yadav: Writing, Analysis, Methodology, Software, [Link] T.: Writing, Investigation,
Methodology, Software, [Link] Shankhyan: Writing, Investigation, Methodology, Software, Visuali-
[Link] A.: Writing, Investigation, [Link] Nath Thatoi: Writing, Investigation, Meth-
odology, Resources, [Link] Vladimirovich Sinitsin: Writing, Investigation, Methodology, Software,
Validation.
Declarations
Competing interests
The authors declare no competing interests.
Additional information
Correspondence and requests for materials should be addressed to F.M.A.A.
Reprints and permissions information is available at [Link]/reprints.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and
institutional affiliations.
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives
4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in
any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide
a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have
permission under this licence to share adapted material derived from this article or parts of it. The images or
other third party material in this article are included in the article’s Creative Commons licence, unless indicated
otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence
and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to
obtain permission directly from the copyright holder. To view a copy of this licence, visit http://c reativecom
mo
ns.org/l icenses/by -nc-nd/4.0/.
© The Author(s) 2025
Scientific Reports | (2025) 15:19073 | [Link] 9
