Intelligent predictive neural network analysis on LTNE impacts on thermophoretic particle deposition in HFE 7100 nanofluid with Co3O4 nanoparticle Authors: Saba Liaqat, Bouthaina Dammak, Muhammad Sabaoon Khan, Walid Abdelfattah, Joy Djuansjah, Ilyas Khan, Munawar Abbas, Nidhal Ben Khedher Published: 2026 ABSTRACT This study examines the outcome of heat generation on thermophoretic particle deposition in Co3O4/HFE-7100 nanofluid flowing past a vertical cylinder in a permeable media under local thermal non-equilibrium conditions employing an ANN coupled with a Bayesian-regularized back-propagation algorithm. For contrast, a simplified mathematical formulation is also used to examine the thermal behavior without local thermal equilibrium assumptions, that is, without LTNE limitations. The solid matrix and fluid phase are treated as distinct temperature fields in the LTNE framework, necessitating unique thermal gradients for each phase. Optimizing heat transfer performance using ANN-based regression modeling is the main goal of this work. Well-structured training and testing datasets are used to guarantee numerical stability and prediction resilience, and the Bayesian-regularization back-propagation technique is applied to enhance generalization capacity. The impact of dominating governing factors is illustrated graphically, and an error evaluation is provided to gauge model correctness. The ANN model was trained using the obtained dataset and then tested against numerical values of important engineering variables. Tables and graphs are utilized to show how new factors affect the flow’s dynamics. The rate of liquid phase heat transmission declines as the inter-phase heat transport values increase. Introduction Machine learning approaches like as neural networks and regression models offer a quick and effective alternative to traditional CFD by allowing for real-time prediction of temperature, pressure, and velocity in complex flows. These techniques are useful for improving heat exchangers, aerodynamic designs, and energy-efficient fluid systems because they lower computational costs without compromising accuracy. In fluid dynamics applications, machine learning helps close the gap between accuracy and computing cost by discovering important governing factors that increase efficiency and reduce energy losses. Zeeshan et al. [1] examined radiation effects flowing over a porous expanding sheet in the Maxwell hybrid nanofluid solution of an artificial neural network with many slips. Mirza et al. [2] examined networks of Levenberg–Marquardt neurons are used in the smart computing approach to evaluate a dusty trihybrid nanofluid’s two-phase flow employing the CCHFM (Cattaneo-Christov heat flux model). Benderradji et al. [3] observed the application of hybrid deep neural networks and metaheuristic algorithms to optimize heat exchange in a cavity filled with magnetized nanofluid. Aoudia et al. [4] examined an ANN research thermal radiation and thermophoresis affects for the Marangoni convection-induced nanofluid convective flow with thermosolutal flow. Shah et al. [5] scrutinized the estimate of a model of a heated convective Carreau nanofluid using an artificial neural network across an exponentially stretched sheet, magnetic, and heat source/sink diffusions. Kumar et al. [6] scrutinized the computational fluid dynamics investigation and prediction of heat transportation in dusty fluid flow via hot surfaces using deep neural networks. Abdal et al. [7] examined artificial neural networks with bioconvection and nonlinear heat radiation for a Riga plate’s tangent hyperbolic NF (nanofluid) flow. The multiphysics investigation of convective flow in an inverted T-shaped porous enclosure: ANN-based parametric estimate was scrutinized by Kumar et al. [8]. Shahbaz et al. [9] studied the intelligent computing paradigm of 3D laminated MHD nanofluids over a sheet. Using deep learning parameter estimation, Kumar et al. [10] investigated thermo-magnetic radiative flow in porous enclosures. The numerical treatment of DFF of propylene glycol with CNTs under the effects of activation energy and MHD is examined by Shahbaz and Ahmad [11]. Shahbaz et al. [12] investigated at the new proposal of recurrent neural networks to analyses the heat transfers of radiative Casson nanofluid flow formed of CNTs over a surface. The intelligent predictive networks for magnetohydrodynamics nanofluid containing thermal conductivity and CNTs over a permeable medium were investigated by Shahbaz and Ahmad [13]. Shaaban et al. [14] used intelligent predictive neural network study to scrutinize the properties of Stefan blowing on the chemical reactive flow of Boger NF (nanofluid) with brownian motion and thermophoresis. When there is a temperature differential, small, micron-scale particles floating in a gas will move from hotter to cooler areas, a phenomenon known as thermophoresis. Applications for this phenomenon are many and include the research of exhaust gas paths in combustion systems, the separation of tiny particles from gas streams, and the study of particle deposition on turbine blade surfaces. In systems with tiny particles subjected to wide temperature fluctuations, it also has a major impact on mass transfer processes. Because of its wide range of applications, thermophoresis has garnered a lot of interest in both science and engineering. Shaaban et al. [15] examined applications in sophisticated thermal management systems, including the optimization of thermophoresis in hybrid nanofluid using heat radiation and nanomaterial performance. The effects of activation energy and two viscosity models on synovial fluid are analyzed by Khan et al. [16] using TPD (thermophoretic particle deposition). Karthik et al. [17] inspected mass transportation examination of THNF (trihybrid nanofluid) flow via a wedge as affected by thermal radiation and thermophoretic deposition. The impact of combination of nanoparticles and deposition of thermophoretic particles on the flow of NF over the Riga wedge was analyze by Madhukesh et al. [18]. Mahariq et al. [19] examine the THNF with oxytactic microbes in a thermo-bioconvection flow. Pal and Chatterjee [20] examined effects of thermophoresis and Brownian motion in a composite material, magnetohydrodynamic dissipative occurs when small layers of chemically reactive nanoliquid radiate outward on an unstable expanding sheet. The two-phase model of micropolar NF flow across a surface using DFF and chemical reaction analysis was investigated by Nayak et al. [21]. The performance of magneto-viscoelastic fluid flow over a porous media with a heat generation were scrutinized by Nayak et al. [22] using a hybrid approach. Two different modeling techniques for the fluid stage and the solid matrix are frequently utilized to characterize heat transport in permeable media. Assuming that both stages share the same thermal field, the first is the LTE (local thermal equilibrium) model. When there are discernible temperature variations between the fluid and solid stages, this assumption is refuted. The LTNE model, which considers the solid and fluid temperatures independently, is better suitable under these circumstances. The LTNE framework has gotten very little attention in porous medium heat transfer investigations, despite its higher level of physical realism. The outcome of triple adiabatic barriers within a permeable cavity in a model with LTNE and non-darcy flow was examine by Yousif et al. [23]. Alhadhrami et al. [24] reviewed the investigation of mass transportation in a chemically reacting non-Newtonian fluid flow under conditions of LTNE. Thaku et al. [25] scrutinized the subcritical dynamics and nonlinear stability of ferroconvection in porous media with pair stresses when there is thermal non-equilibrium. Bhargavi and Makinde [26] observed the numerical investigation of fluid-saturated porous-filled duct’s axial conduction utilizing a LTNE model. Galal et al. [27] explored tetra hybrid nanofluid MHD chemical reactive flow with velocity slip conditions: the impact of LTNE. Nayak et al. [28] examined the CCHFM on convection of micropolar NF with chemical reaction. Nayak et al. [29] study how heat loss and DFF inertial drag affect micropolar HNF flow via extending surface. Because of their numerous scientific and technological uses, nanofluids have garnered a lot of interest lately. Beyond engineering systems, they are crucial in medicinal domains, such as allowing tailored cancer therapy using nanoscale drug delivery systems and detecting arterial blockages in blood flow using radioactive tracer methods. Additionally, waste treatment procedures make use of nanofluids, which promotes the sustainability of the environment and cleaner energy generation. Home refrigeration systems, fuel cells, chillers, heat exchangers, boiler exhaust temperature control, engine cooling and thermal management, microelectronic devices, and hybrid engines are only a few of the industrial and manufacturing industries’ uses for them. Nanofluids are still a primary focus of current research and development because of their wide range of useful applications. The examination of heat transportation properties in MHD hybrid nanofluids with varying thermal radiations and viscosities was inspect by Anwar et al. [30]. The radiative flux of an HNF was scrutinized by Abbas et al. [31] using the CCFM to inspect the impact of elastic deformation. Areshi et al. [32] used an expanding sheet to investigate the effects of NPs radius and interparticle spacing on the mixed convective flow of a water-based NF containing alumina nanoparticles in MHD. The outcomes of heat radiation on oxytactic germs in a HNF including SWCNTs and MWCNTs with Soret-Dufour effects are investigated by Abbas et al. [33]. Senbagaraja and De [34] examined the tangent hyperbolic nanofluid bioconvective EMHD statistical analysis with heat radiation and heat source. The Williamson blood flow in a permeable media with SDE and trihybrid nanofluid was scrutinized by Sudarmozhi et al. [35] using AI-based neural network model, demonstrating the strong capability of soft-computing techniques to predict complex nonlinear thermo-biological transport phenomena. Rehman et al. [36] extended advanced nanofluid modeling by examining thermocapillary, radiative, and MHD effects on unsteady couple-stress THNF flow over a surface, revealing notable improvement in heat transmission due to the combined physical mechanisms. A computational approach for fourth-grade aluminum-alloy NF flow over a Riga plate was developed by Ahmad et al. [37], emphasising the impact of electromagnetic forcing and non-Newtonian behaviour on thermal performance. Going on to engineering applications, Kapustenko et al. [38] examined heat transmission increase in small heat exchangers with various channel shapes and discovered that thermal efficiency is greatly increased by geometric design. In the context of energy storage, Kovács et al. [39] analyzed radiative and convective heat transmission in lithium-ion battery cells, addressing key thermal safety and management issues. A few other interesting studies are given in [40–44]. Ahmad et al. [45] formulated a computational model to investigate fourth-grade nanofluid flow over an Riga plate with aluminum alloy nanoparticles, demonstrating that electromagnetic effects markedly enhance thermal performance. Szűcs [46] utilized a combined CFD–FEM approach to evaluate thermal characteristic length scales, providing a deeper understanding of convective heat transfer in complex systems. Orosz et al. [47] introduced a graph-theoretic method for designing heat exchanger networks with minimized utility requirements, enhancing energy recovery efficiency, while Morauszki et al. [48] conducted detailed simulations of coupled fluid flow, combustion, and heat transfer in internal combustion engines, highlighting key aspects of thermal control. Furthermore, Szűcs [49] analyzed compressibility effects in reconstructed porous media, revealing significant impacts on flow resistance and heat transfer behavior, and Orosz and Friedler [50] explored multiple optimal configurations for heat exchanger network design, supporting practical and energy-efficient industrial applications. There are several real-world uses for the technique used to investigate LTNE effects in MHD CoO4/HFE-7100 nanofluid flow through a permeable media with heat production. The nonlinear link between governing parameters and thermal behavior is captured by a back-propagated neural network, which allows for more precise temperature and heat transfer characteristic prediction at a lower computing cost. The study’s objective is as follows:To examine the outcome of heat production on a nanofluid’s flow, and solid profiles and thermal fluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100.The network’s worthy performance is determined by a learning curve on the MSE-based fitness, histograms, and regression measurements.This research objective to leverage the influences of LTNE on thermal boundary layer flow of CoO4/HFE-7100 based nanofluid.To observe the outcomes of the Lorentz force on the MBL flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100 based nanofluid.To inspect the outcome of heat production on the thermal BLF of a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. To examine the outcome of heat production on a nanofluid’s flow, and solid profiles and thermal fluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. To examine the outcome of heat production on a nanofluid’s flow, and solid profiles and thermal fluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. The network’s worthy performance is determined by a learning curve on the MSE-based fitness, histograms, and regression measurements. The network’s worthy performance is determined by a learning curve on the MSE-based fitness, histograms, and regression measurements. This research objective to leverage the influences of LTNE on thermal boundary layer flow of CoO4/HFE-7100 based nanofluid. This research objective to leverage the influences of LTNE on thermal boundary layer flow of CoO4/HFE-7100 based nanofluid. To observe the outcomes of the Lorentz force on the MBL flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100 based nanofluid. To observe the outcomes of the Lorentz force on the MBL flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100 based nanofluid. To inspect the outcome of heat production on the thermal BLF of a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. To inspect the outcome of heat production on the thermal BLF of a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. Model of mass and heat transport flow In this work, the effects of magnetohydrodynamics on thermophoresis particle deposition in a \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100 nanofluid passing a vertical cylinder implanted in a permeable medium are examined in relation to internal heat generation. In order to examine the ensuing flow behavior and heat transfer characteristics in connection to important regulating factors, the physical arrangement, depicted in Fig. 1 [40–42], takes into account a vertical cylindrical shape. Below is a summary of the basic presumptions and formulation of the suggested model.The study examines how heat radiation affects the nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100.Despite their cylindrical structure, the nanoparticles are of the same size.Implications of LTNE on a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \frac{\partial }{\partial x}\left( {ur} \right) + \frac{\partial }{\partial r}\left( {vr} \right) = 0, $$\end{document}2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \rho_{{\text{nf }}} \left( {u\left( {\frac{\partial u}{{\partial x}}} \right) + v\left( {\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {\mu_{{\text{nf }}} \left( {{\mathrm{r}}\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) - {\upsigma}_{nf} B_{0}^{2} u - \frac{{\mu_{{\text{nf }}} }}{{k^{*} }}u + g(\rho {\upbeta })_{nf} \left( {T - T_{\infty } } \right), $$\end{document}3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\rho C_{p} } \right)_{{\text{nf }}} \left( {u\left( {\frac{\partial T}{{\partial x}}} \right) + v\left( {\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {k_{{\text{nf }}} } \right)\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{16\sigma^{*} T_{\infty }^{3} }}{{3k^{*} }}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right) + \left( { - T_{\infty } + T} \right)Q_{{0 }} + \left( { - {\mathrm{T}} + T_{p} } \right)h_{fs} , $$\end{document}4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ 0 = \frac{{k_{p} }}{{(\rho c_{p} )_{p} }}\frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{{\partial T_{p} }}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{h_{fs} }}{{(\rho c_{p} )_{p} }}\left( { - T_{p} + {\mathrm{T}}} \right), $$\end{document}5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ v\left( {\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) + u\left( {\frac{\partial C}{{\partial x}}} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}D_{{\text{B }}} \left( {{\mathrm{r}}\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) - \frac{\partial }{\partial r}\left( { - k_{t} \frac{\nu }{{T_{ref} }}\frac{\partial T}{{\partial {\mathrm{r}}}}\left( {C - C_{\infty } } \right)} \right). $$\end{document}Fig. 1Flow description The study examines how heat radiation affects the nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. The study examines how heat radiation affects the nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100. Despite their cylindrical structure, the nanoparticles are of the same size. Despite their cylindrical structure, the nanoparticles are of the same size. Implications of LTNE on a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \frac{\partial }{\partial x}\left( {ur} \right) + \frac{\partial }{\partial r}\left( {vr} \right) = 0, $$\end{document}2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \rho_{{\text{nf }}} \left( {u\left( {\frac{\partial u}{{\partial x}}} \right) + v\left( {\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {\mu_{{\text{nf }}} \left( {{\mathrm{r}}\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) - {\upsigma}_{nf} B_{0}^{2} u - \frac{{\mu_{{\text{nf }}} }}{{k^{*} }}u + g(\rho {\upbeta })_{nf} \left( {T - T_{\infty } } \right), $$\end{document}3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\rho C_{p} } \right)_{{\text{nf }}} \left( {u\left( {\frac{\partial T}{{\partial x}}} \right) + v\left( {\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {k_{{\text{nf }}} } \right)\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{16\sigma^{*} T_{\infty }^{3} }}{{3k^{*} }}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right) + \left( { - T_{\infty } + T} \right)Q_{{0 }} + \left( { - {\mathrm{T}} + T_{p} } \right)h_{fs} , $$\end{document}4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ 0 = \frac{{k_{p} }}{{(\rho c_{p} )_{p} }}\frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{{\partial T_{p} }}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{h_{fs} }}{{(\rho c_{p} )_{p} }}\left( { - T_{p} + {\mathrm{T}}} \right), $$\end{document}5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ v\left( {\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) + u\left( {\frac{\partial C}{{\partial x}}} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}D_{{\text{B }}} \left( {{\mathrm{r}}\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) - \frac{\partial }{\partial r}\left( { - k_{t} \frac{\nu }{{T_{ref} }}\frac{\partial T}{{\partial {\mathrm{r}}}}\left( {C - C_{\infty } } \right)} \right). $$\end{document} Implications of LTNE on a nanofluid based on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {/}$$\end{document} HFE-7100.1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \frac{\partial }{\partial x}\left( {ur} \right) + \frac{\partial }{\partial r}\left( {vr} \right) = 0, $$\end{document}2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \rho_{{\text{nf }}} \left( {u\left( {\frac{\partial u}{{\partial x}}} \right) + v\left( {\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {\mu_{{\text{nf }}} \left( {{\mathrm{r}}\frac{\partial u}{{\partial {\mathrm{r}}}}} \right)} \right) - {\upsigma}_{nf} B_{0}^{2} u - \frac{{\mu_{{\text{nf }}} }}{{k^{*} }}u + g(\rho {\upbeta })_{nf} \left( {T - T_{\infty } } \right), $$\end{document}3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\rho C_{p} } \right)_{{\text{nf }}} \left( {u\left( {\frac{\partial T}{{\partial x}}} \right) + v\left( {\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) = \frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {k_{{\text{nf }}} } \right)\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{16\sigma^{*} T_{\infty }^{3} }}{{3k^{*} }}\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{\partial T}{{\partial {\mathrm{r}}}}} \right) + \left( { - T_{\infty } + T} \right)Q_{{0 }} + \left( { - {\mathrm{T}} + T_{p} } \right)h_{fs} , $$\end{document}4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ 0 = \frac{{k_{p} }}{{(\rho c_{p} )_{p} }}\frac{1}{{\mathrm{r}}}\left( {\frac{\partial }{{\partial {\mathrm{r}}}}\left( {{\mathrm{r}}\frac{{\partial T_{p} }}{{\partial {\mathrm{r}}}}} \right)} \right) + \frac{{h_{fs} }}{{(\rho c_{p} )_{p} }}\left( { - T_{p} + {\mathrm{T}}} \right), $$\end{document}5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ v\left( {\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) + u\left( {\frac{\partial C}{{\partial x}}} \right) = \frac{1}{{\mathrm{r}}}\frac{\partial }{{\partial {\mathrm{r}}}}D_{{\text{B }}} \left( {{\mathrm{r}}\frac{\partial C}{{\partial {\mathrm{r}}}}} \right) - \frac{\partial }{\partial r}\left( { - k_{t} \frac{\nu }{{T_{ref} }}\frac{\partial T}{{\partial {\mathrm{r}}}}\left( {C - C_{\infty } } \right)} \right). $$\end{document} Flow description The BCs ([40–42]):6\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ T = T_{w} ,{ }u = u_{w} , { }C = C_{w} ,{\text{ v}} = { }0,{\mathrm{r}} = r_{0} $$\end{document}7\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ T \to T_{\infty } , u \to 0, C \to C_{\infty } ,{\mathrm{r}} \to r_{\infty } . $$\end{document} Subjected to transformations [41]:8\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \eta = \frac{{{\mathrm{r}}^{2} - {\mathrm{r}}_{0}^{2} }}{{{\mathrm{r}}_{0} 2x}}Re_{c}^{{\frac{ - 1}{{{\mathrm{n}} + 1}}}} ,v = - \frac{\partial \psi }{{\partial x}}\frac{1}{{\mathrm{r}}},u = \frac{\partial \psi }{{\partial x}}\frac{1}{{\mathrm{r}}} , $$\end{document}9\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \psi = {\mathrm{Re}}_{c}^{{\frac{ - 1}{{n + 1}}}} Ur_{0} f, \theta = \frac{{T - T_{\infty } }}{{T_{w} - T_{\infty } }}, \phi = \frac{{C - C_{\infty } }}{{C_{w} - C_{\infty } }}, \theta_{p} = \frac{{T_{p} - t_{\infty } }}{{t_{w} - t_{\infty } }}. $$\end{document} ODEs10\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ P_{1} \left( {\left( {1 + 2\lambda } \right)f^{\prime\prime\prime} + 2\lambda f^{\prime}{\prime} } \right) - P_{3} M f ^{\prime} - P_{1} K f ^{\prime} + P_{2} \left( { - f^{{{^{\prime}}2}} + \frac{2n}{{n + 1}}ff^{\prime\prime}} \right) + P_{4} Gr\theta = 0, $$\end{document}11\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\left( {2\lambda + 1} \right)\theta^{\prime\prime} + 2\lambda \theta^{\prime}} \right)\left( {P_{5} + Rd} \right) + P_{6} \frac{2n}{{n + 1}}\Pr f\theta^{\prime} + \Pr H\left( {\theta_{p} - \theta } \right) + \Pr Q_{T } \theta = 0, $$\end{document}12\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\left( {2\lambda + 1} \right)\theta_{p}^{^{\prime\prime}} + 2\lambda \theta_{p}^{\prime} } \right) + \Pr \gamma H\left( {\theta - \theta_{p} } \right) = 0 $$\end{document}13\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\left( {2\lambda + 1} \right)\phi^{\prime\prime} + 2\lambda \phi^{\prime}} \right) + \frac{2nSc}{{n + 1}}f\phi^{\prime} - \tau Sc\left( {\phi^{\prime}\theta^{\prime} + \phi \theta^{\prime\prime}} \right) = 0. $$\end{document} Reduced BCs14\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ { }f\left( 0 \right) = { }0, f^{\prime}\left( 0 \right) = 1,{ } { } $$\end{document}15\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \phi \left( 0 \right) = 1, \theta \left( 0 \right) = 1, \theta_{p} \left( 0 \right) = 1, $$\end{document}16\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ {\uptheta}_{p} \left( \infty \right) \to 0,{\uptheta }\left( \infty \right) \to 0,f^{\prime}\left( \infty \right) \to 0,\phi \left( \infty \right) \to 0. $$\end{document} Porosity-modified conductivity ratio \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \gamma = \frac{{k_{f} }}{{k_{s} }}$$\end{document},\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ Sc = \frac{{\nu_{f} }}{{D_{B} }}$$\end{document} Schmidt number, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Gr = \frac{{g(\rho {\upbeta })_{f} \left( {T_{w} - T_{\infty } } \right)}}{{Uv_{f}^{2} }}$$\end{document} Grashof number, Eckert number \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Ec = \frac{{u_{w}^{2} }}{{\left( {T_{{\mathrm{w}}} - T_{\infty } } \right)\left( {C_{p} } \right)_{f} }}$$\end{document}, Inter-phase heat transportation factor \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ H = \frac{{\alpha_{f} h_{fs} }}{{{\mathrm{U}}k_{f} }} ,$$\end{document} Prandtl number \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Pr}} = \frac{{v_{f} \left( {\rho C_{p} } \right)_{f} }}{{k_{f} }} $$\end{document} Heat source parameter \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{{\text{T }}} = \frac{{Q_{0} }}{{\left( {\rho C_{p} } \right)_{f} }} ,$$\end{document} Magnetic Parameter \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$M = \frac{{\sigma_{f} B_{0}^{2} }}{{U\rho_{f} }}$$\end{document},\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ {\uptau } = \frac{{ - k\left( {T_{w} - T_{\infty } } \right)}}{{T_{ref} v_{f} }}{ }$$\end{document} thermophoretic parameter. The basic aspects of NF are shown in Table 1. The characteristics of NPs and based liquid are seen in Table 2.Table 1Thermo-physical features of a nanofluid (NF) [40, 41]CharacteristicsNanofluid(\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rho_{nf}$$\end{document})\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{2} = \frac{{\rho_{hnf} }}{{\rho_{f} }} = \left[ {\left\{ {{\Phi }\frac{{\rho_{{s_{1} }} }}{{\rho_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\sigma_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\rho \beta )_{hf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{3} = \frac{{\sigma_{nf} }}{{\sigma_{f} }}{ } = \left[ {\frac{{\sigma_{{s_{1} }} \left( {\left( {{\mathrm{s}} - 1} \right){\Phi } + 1} \right) + \left( {{\mathrm{s}} - 1} \right)\sigma_{f} \left( {1 - {\Phi }} \right)}}{{\sigma_{f} \left( {\left( {{\mathrm{s}} - 1} \right) + {\Phi }} \right) + \sigma_{{s_{1} }} \left( {1 - {\Phi }} \right)}}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{4} = \frac{{(\rho \beta )_{nf} }}{{(\rho \beta )_{f} }} = \left[ {\left\{ {{\Phi }\frac{{(\rho \beta )_{{s_{1} }} }}{{(\rho \beta )_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mu_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{1} = \frac{{\mu_{nf} }}{{\mu_{f} }} = \frac{1}{{\left( {1 - {\Phi }} \right)^{2.5} }}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left( {\rho c_{p} } \right)_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{6} = \frac{{\left( {\rho c_{p} } \right)_{nf} }}{{\left( {\rho c_{p} } \right)_{f} }} = \left[ {\left\{ {{\Phi }\frac{{\left( {\rho c_{p} } \right)_{{s_{1} }} }}{{\left( {\rho c_{p} } \right)_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left( {k_{nf} } \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{5} = \frac{{k_{nf} }}{{k_{f} }}{ } = \frac{{\left( {\left( {{\mathrm{S}} - 1} \right)k_{f} + k_{{s_{1} }} } \right) - 2{\Phi }\left( {k_{f} - k_{{s_{1} }} } \right)}}{{\left( {{\mathrm{S}} - 1)k_{f} + k_{{s_{1} }} } \right) + {\Phi }\left( {k_{f} - k_{{s_{1} }} } \right)}}$$\end{document}Table 2The thermos-physical aspects of improper fluid and NPs [43, 44]Characteristics constituents\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{c}}_{{\boldsymbol{p}}} \left( {{ }{\mathbf{J}}/{\mathbf{kgK}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{k}}\left( {{ }{\mathbf{W}}/{\mathbf{mK}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{\beta}}\left( {1/{\mathbf{K}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{\rho}}\left( {{\mathbf{kg}}/{\mathbf{m}}_{3} } \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{ Co}}_{3} {\mathrm{O}}_{4}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$421$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$99.2$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$42.7$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$8862$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{HFE}} - 7100{ }$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ 1180 $$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.0678$$\end{document}0.0018\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1510$$\end{document} Table 1Thermo-physical features of a nanofluid (NF) [40, 41]CharacteristicsNanofluid(\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rho_{nf}$$\end{document})\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{2} = \frac{{\rho_{hnf} }}{{\rho_{f} }} = \left[ {\left\{ {{\Phi }\frac{{\rho_{{s_{1} }} }}{{\rho_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\sigma_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\rho \beta )_{hf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{3} = \frac{{\sigma_{nf} }}{{\sigma_{f} }}{ } = \left[ {\frac{{\sigma_{{s_{1} }} \left( {\left( {{\mathrm{s}} - 1} \right){\Phi } + 1} \right) + \left( {{\mathrm{s}} - 1} \right)\sigma_{f} \left( {1 - {\Phi }} \right)}}{{\sigma_{f} \left( {\left( {{\mathrm{s}} - 1} \right) + {\Phi }} \right) + \sigma_{{s_{1} }} \left( {1 - {\Phi }} \right)}}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{4} = \frac{{(\rho \beta )_{nf} }}{{(\rho \beta )_{f} }} = \left[ {\left\{ {{\Phi }\frac{{(\rho \beta )_{{s_{1} }} }}{{(\rho \beta )_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mu_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{1} = \frac{{\mu_{nf} }}{{\mu_{f} }} = \frac{1}{{\left( {1 - {\Phi }} \right)^{2.5} }}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left( {\rho c_{p} } \right)_{nf}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{6} = \frac{{\left( {\rho c_{p} } \right)_{nf} }}{{\left( {\rho c_{p} } \right)_{f} }} = \left[ {\left\{ {{\Phi }\frac{{\left( {\rho c_{p} } \right)_{{s_{1} }} }}{{\left( {\rho c_{p} } \right)_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left( {k_{nf} } \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{5} = \frac{{k_{nf} }}{{k_{f} }}{ } = \frac{{\left( {\left( {{\mathrm{S}} - 1} \right)k_{f} + k_{{s_{1} }} } \right) - 2{\Phi }\left( {k_{f} - k_{{s_{1} }} } \right)}}{{\left( {{\mathrm{S}} - 1)k_{f} + k_{{s_{1} }} } \right) + {\Phi }\left( {k_{f} - k_{{s_{1} }} } \right)}}$$\end{document} Thermo-physical features of a nanofluid (NF) [40, 41] \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\sigma_{nf}$$\end{document} \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\rho \beta )_{hf}$$\end{document} \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{3} = \frac{{\sigma_{nf} }}{{\sigma_{f} }}{ } = \left[ {\frac{{\sigma_{{s_{1} }} \left( {\left( {{\mathrm{s}} - 1} \right){\Phi } + 1} \right) + \left( {{\mathrm{s}} - 1} \right)\sigma_{f} \left( {1 - {\Phi }} \right)}}{{\sigma_{f} \left( {\left( {{\mathrm{s}} - 1} \right) + {\Phi }} \right) + \sigma_{{s_{1} }} \left( {1 - {\Phi }} \right)}}} \right]$$\end{document} \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P_{4} = \frac{{(\rho \beta )_{nf} }}{{(\rho \beta )_{f} }} = \left[ {\left\{ {{\Phi }\frac{{(\rho \beta )_{{s_{1} }} }}{{(\rho \beta )_{f} }} + \left( {1 - {\Phi }} \right)} \right\}} \right]$$\end{document} Table 2The thermos-physical aspects of improper fluid and NPs [43, 44]Characteristics constituents\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{c}}_{{\boldsymbol{p}}} \left( {{ }{\mathbf{J}}/{\mathbf{kgK}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{k}}\left( {{ }{\mathbf{W}}/{\mathbf{mK}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{\beta}}\left( {1/{\mathbf{K}}} \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{\rho}}\left( {{\mathbf{kg}}/{\mathbf{m}}_{3} } \right)$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{ Co}}_{3} {\mathrm{O}}_{4}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$421$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$99.2$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$42.7$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$8862$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{HFE}} - 7100{ }$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ 1180 $$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.0678$$\end{document}0.0018\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1510$$\end{document} The thermos-physical aspects of improper fluid and NPs [43, 44] The Sherwood number, liquid and solid phase rate of transfer are as follows:17\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\mathrm{Re}} \right)^{{ - \frac{1}{n + 1}}} Nu = - \left( {P_{5} + Rd} \right)\theta^{\prime}\left( 0 \right), $$\end{document}18\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {\mathrm{Re}} \right)^{{ - \frac{1}{n + 1}}} Nn = - \theta_{p} \left( 0 \right), $$\end{document}19\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \left( {Re} \right)^{{ - \frac{1}{n + 1}}} { }Sh = - \phi^{\prime}\left( 0 \right). $$\end{document} Solution methodology Artificial neural networks are computer models that mimic the structure of neurons in the human brain. They are often used in pattern recognition, classification, and function approximation. A typical ANN consists of an output layer, an input layer, and one or more hidden layers. The connected neurons, make up each connection and each layer is given a weight that represents the extent of the neurons’ effect on one another. To lessen the difference among anticipated and actual outcomes, these weights are changed during training. The most often used ANN architecture is the NN. During training, the weights are frequently modified by the back-propagation method’s calculation. This function computes the difference between the model’s output and the actual (target) values. Regarding the currently employed Bayesian Regularization back-propagated technique (BRBT) model (Table 3):Histogram evaluation, which displays the error distribution.One technique for confirming the model is regression analysis, which evaluates the association among aim and predicted values.The analysis known as Mean Squared Error (MSE) gauges how accurate predictions are.Table 3Result of Bayesian-Regularization techniqueCasesPerformanceTrainingTestingGradientTimeEpochI4.73 × E−134.35 × E−138.14 × E−134.55 × E−0916271II1.15 × E−111.15 × E−111.19 × E−112.13 × E−0813221III1.29 × E−121.21 × E−121.93 × E−129.68 × E−0810162IV1.33 × E−111.25 × E−112.03 × E−111.24 × E−0812207V2.72 × E−122.07 × E−128.56 × E−127.02 × E−0916268VI1.02 × E−118.22 × E−122.83 × E−119.07 × E−0819265 Histogram evaluation, which displays the error distribution. Histogram evaluation, which displays the error distribution. One technique for confirming the model is regression analysis, which evaluates the association among aim and predicted values. One technique for confirming the model is regression analysis, which evaluates the association among aim and predicted values. The analysis known as Mean Squared Error (MSE) gauges how accurate predictions are. The analysis known as Mean Squared Error (MSE) gauges how accurate predictions are. Table 3Result of Bayesian-Regularization techniqueCasesPerformanceTrainingTestingGradientTimeEpochI4.73 × E−134.35 × E−138.14 × E−134.55 × E−0916271II1.15 × E−111.15 × E−111.19 × E−112.13 × E−0813221III1.29 × E−121.21 × E−121.93 × E−129.68 × E−0810162IV1.33 × E−111.25 × E−112.03 × E−111.24 × E−0812207V2.72 × E−122.07 × E−128.56 × E−127.02 × E−0916268VI1.02 × E−118.22 × E−122.83 × E−119.07 × E−0819265 Result of Bayesian-Regularization technique The remarkable generalization capacity of the created neural network over unseen data is shown in Figs. 2A, 3A, 4A, 5A, 6A, and 7A, which show the optimal validation performance at the appropriate epochs for the testing datasets and training. The network effectively learns the physics of the problem and sustains a good prediction ability outside of the trained data range, according to the performance trends. Differences in gradient, mean squared error, and training performance for six exemplary examples representing epochs 271, 221, 162, 207, 268, and 265 are shown in Figs. 2B, 3B, 4B, 5B, 6B, and 7B. These images demonstrate the Artificial Neural Network’s (ANN) progressive and adaptive learning behavior as well as its capacity to iteratively eliminate training errors through the Bayesian-Regularization back-propagation process. The suggested training strategy’s numerical effectiveness is confirmed by the gradient and error values, which steadily decrease as the number of epochs increases, suggesting a stable convergence process. The solution fitting graphs shown in Figs. 2C, 3C, 4C, 5C, 6C, and 7C further emphasize the correctness of the ANN approach. The tight alignment of the projected curves with the actual data indicates that the ANN has successfully learned the nonlinear mapping among the input and output variables. This results in minimal variances and good data-fitting properties. This fitting result validates the robustness and reliability of the network for modeling complex thermos-physical processes, particularly in nonlinear heat transport systems. The error histograms in Figs. 2D, 3D, 4D, 5D, 6D, and 7D provide more details regarding the convergence characteristics and numerical stability of the proposed ANN model. There are probably relatively few deviations from the predictions because the majority of the error values are concentrated near zero, suggesting that the network has a high degree of truth and precision. Such a narrow error distribution shows the model’s strong capacity to simplify over many datasets and maintain stability across repeated training stages. Lastly, the thorough regression analysis for the testing datasets and training is shown in Figs. 2E, 3E, 4E, 5E, 6E, and 7E. A regression coefficient (R = 1) and the regression line’s almost perfect alignment with the target data indicate a high degree of correlation between the expected and actual findings. This demonstrates how well the ANN captures the complex physical interdependencies and nonlinear interactions between the controlling factors that affect the process of heat transport. The well-trained ANN model, which is optimized using the Bayesian–Regularized back-propagation technique, provides a highly accurate, stable, and dependable computational framework for modeling complex heat transport phenomena, as demonstrated by the combined results from Figs. 2A–7E. For modern thermal-fluid analysis, this method offers several benefits that enable the optimization of engineering systems with increased computational effectiveness and physical realism. Figures 8 and 9a & b depict how the flow profile \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$f^{\prime}\left( \eta \right)$$\end{document} and temperature distribution \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta \left( \eta \right)$$\end{document} are impacted by the Φ. When nanoparticle volume fraction (Φ) rises, the thermal rises and the liquid velocity falls. This happens as a higher nanoparticle concentration results in a denser nanofluid, which improves heat retention while also decreasing flow rate, leading to better thermal performance. Figures 8 and 9a & b show how \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H$$\end{document} affect \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta \left( \eta \right)$$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\uptheta}_{p} \left( \eta \right). $$\end{document} The \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H$$\end{document} development raises the temperature profile of the solid and liquid stages. The thermal field for the liquid phase θ(η) grows as H does (Fig. 10). The temperature gradient in the liquid phase decreases as \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H$$\end{document} rises due to the fast heat transportation among the phases, but the thermal gradient in the solid phase grows. Figures 11 and 12a & b reveal the outcome of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Q}}_{T}$$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ \theta_{p} \left( \eta \right).$$\end{document} As the value of the heat source variable upsurges, so does the thermal dispersion. The significance of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau$$\end{document} on concentration profile and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Sh$$\end{document} are display in Figs. 13 and 14a & b. In this case, the concentration profile is improved and the mass transfer rate declines due to an upsurge in \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau$$\end{document}. The influence of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi$$\end{document}, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{T}$$\end{document} and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H$$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Nu$$\end{document} are diplsay in Figs. 15, 16, and 17a & b. The fluid phase heat transport increase as augments the values of heat nanoparticles volume friction and heat generation. The rate of heat transportation drops as enhance the values of interphase heat transportation factor. The heat transportation rates from the present study and investigative studies using just integer situations and common parameters are compared in Table 4. It is clear that the two outcomes are comparable. This makes the present study more legitimate.Fig. 2Scenario IFig. 3Scenario IIFig. 4Instance IIIFig. 5Scenario IVFig. 6Scenario VFig. 7Scenario VIFig. 8a & b Performance of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$f^{\prime}\left( \eta \right) $$\end{document} fieldFig. 9a & b Influence of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\uptheta }\left( \eta \right) $$\end{document} fieldFig. 10a & b Implication of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta \left( \eta \right) $$\end{document} fieldFig. 11a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta_{p} \left( \eta \right) $$\end{document} fieldFig. 12a & b Performance of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{T} $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\uptheta }\left( \eta \right) $$\end{document} fieldFig. 13a & b Outcome of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\phi \left( \eta \right) $$\end{document} fieldFig. 14a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Sh}} $$\end{document} fieldFig. 15a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{Nu }}$$\end{document} fieldFig. 16a & b Outcome of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{T} $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Nu}} $$\end{document} fieldFig. 17a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{Nu }}$$\end{document} fieldTable 4 Subtracting the extra parameters from the earlier published research in order to evaluate the present results\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathbf{Nu}}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{M}}$$\end{document}Present resultsNazir et al. [41]\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.0$$\end{document}3.30781163.3078104\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.4$$\end{document}3.32292893.3229269\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.8$$\end{document}3.31602423.3160236 Scenario I Scenario II Instance III Scenario IV Scenario V Scenario VI a & b Performance of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$f^{\prime}\left( \eta \right) $$\end{document} field a & b Influence of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\uptheta }\left( \eta \right) $$\end{document} field a & b Implication of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta \left( \eta \right) $$\end{document} field a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta_{p} \left( \eta \right) $$\end{document} field a & b Performance of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{T} $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\uptheta }\left( \eta \right) $$\end{document} field a & b Outcome of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\phi \left( \eta \right) $$\end{document} field a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\tau $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Sh}} $$\end{document} field a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\varphi $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{Nu }}$$\end{document} field a & b Outcome of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$Q_{T} $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Nu}} $$\end{document} field a & b Result of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$H $$\end{document} on \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{Nu }}$$\end{document} field Table 4 Subtracting the extra parameters from the earlier published research in order to evaluate the present results\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathbf{Nu}}$$\end{document}\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\boldsymbol{M}}$$\end{document}Present resultsNazir et al. [41]\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.0$$\end{document}3.30781163.3078104\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.4$$\end{document}3.32292893.3229269\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.8$$\end{document}3.31602423.3160236 Subtracting the extra parameters from the earlier published research in order to evaluate the present results Final remarks This study used a back-propagated neural network to evaluate the effects of LTNE on MHD Co3O4/HFE-7100 nanofluid using a heated vertical cylinder, permeable medium, and thermophoresis. The investigation’s findings are as follows:Depending on the heat source’s characteristics, the thermal curve shows a rising trend.The ANN model can predict the Schmidt number with a high degree of precision.As the inter-phase transport of heat factor rises, the solid phase heat transfers of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decrease.The nanoparticle volume fraction increases as flow drops, as seen by the increase in the temperature profiles of the solid and liquid stages.As the thermophoretic variable increases, the concentration boundary layer flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decreases.The rate of liquid phase heat transmission declines as the inter-phase heat transport values increase. Depending on the heat source’s characteristics, the thermal curve shows a rising trend. Depending on the heat source’s characteristics, the thermal curve shows a rising trend. The ANN model can predict the Schmidt number with a high degree of precision. The ANN model can predict the Schmidt number with a high degree of precision. As the inter-phase transport of heat factor rises, the solid phase heat transfers of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decrease. As the inter-phase transport of heat factor rises, the solid phase heat transfers of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decrease. The nanoparticle volume fraction increases as flow drops, as seen by the increase in the temperature profiles of the solid and liquid stages. The nanoparticle volume fraction increases as flow drops, as seen by the increase in the temperature profiles of the solid and liquid stages. As the thermophoretic variable increases, the concentration boundary layer flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decreases. As the thermophoretic variable increases, the concentration boundary layer flow of the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{Co}}_{{3}} {\mathrm{O}}_{4} {\mathrm{/HFE}}$$\end{document}-7100 based nanofluid decreases. The rate of liquid phase heat transmission declines as the inter-phase heat transport values increase. The rate of liquid phase heat transmission declines as the inter-phase heat transport values increase. Future work The suggested machine learning model for bioconvection flow of hybrid nanofluids with oxytactic microorganisms, based on the Levenberg–Marquardt algorithm, shows promise for future applications in biomedical engineering, environmental systems, and industrial heat transfer. It can be employed to improve medication delivery systems, bioreactor performance, and oxygen transport in microbial processes. Furthermore, the model can help with the design of improved cooling technologies, wastewater treatment, and biofuel production systems by properly anticipating complicated interactions between fluid flow, nanoparticles, and microbes, resulting in more efficient and sustainable engineering solutions.