Artificial intelligence-assisted analysis of reactive tetra-hybrid Jeffrey nanofluid flow with thermal radiation and Joule heating

This study examines the flow characteristics of tetra-hybrid Jeffrey nanofluids in a porous medium through a vertical channel. The use of a tetra-hybrid nanofluid enables the synergistic integration of four distinct nanoparticles, yielding superior thermophysical characteristics, enhanced thermal transport, and improved suspension stability compared with conventional hybrid and tri-hybrid nanofluids. The effects of thermophoresis, Brownian motion, and slip boundary conditions are analyzed along with viscous dissipation, Joule heating, thermal radiation, and heat flux. Homogeneous and heterogeneous chemical reactions are incorporated into the mathematical model, where partial differential equations (PDEs) are converted into ordinary differential equations (ODEs). The transformed equations are solved numerically in MATLAB using the shooting method under the assumptions of low Reynolds number and long wavelength. A graphical analysis explores velocity, temperature, and concentration distributions. The results reveal that buoyancy, magnetic, and porous-medium effects govern the velocity field, while Prandtl number, thermophoresis, Brownian motion, homogeneous reaction heat, and thermal radiation significantly modify the temperature distribution; meanwhile, Schmidt number, thermophoresis, Brownian motion, and homogeneous reaction strongly influence the nanoparticle concentration. Additionally, artificial neural networks (ANNs) are employed to predict nanofluid behavior under varying physical conditions, including the influence of viscous dissipation, heat flux, and magnetic fields. The Levenberg-Marquardt backpropagation algorithm is applied for estimating key transport properties such as the Sherwood number, Nusselt number, and skin friction coefficient. ANN predictions are validated through training accuracy, performance metrics, regression analysis, and error histogram evaluations. The findings confirm that the ANN model provides highly accurate predictions, optimizing computational efficiency. This research has significant applications in energy systems, thermal regulation, chemical processing, biomedical advancements, vehicle cooling, nuclear reactors, and transportation system optimization. For the Nusselt number, the ANN predictions exhibit an average absolute percentage error of 2.9680% and a coefficient of determination (R2) of 0.9130, demonstrating good agreement with the numerical results. The maximum prediction error is 15.1120% for Case 8, followed by 8.1079% for Case 10. These results confirm that the developed ANN model can effectively reproduce the nonlinear numerical predictions over the investigated range.

Authors

Institutions

Publication Details

Journal
Discover Nano
Published
2026-11-12
DOI
https://doi.org/10.1186/s11671-026-04986-9
Primary Topic
Nanofluid Flow and Heat Transfer
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial intelligence-assisted analysis of reactive tetra-hybrid Jeffrey nanofluid flow with thermal radiation and Joule heating

Bhupendra Kumar Sharma, Farhan A. Salem, Suresh Gupta, David Laroze et al.
Discover Nano
Nanofluid Flow and Heat Transfer
article

Artificial intelligence-assisted analysis of reactive tetra-hybrid Jeffrey nanofluid flow with thermal radiation and Joule heating

Bhupendra Kumar Sharma, Farhan A. Salem, Suresh Gupta, David Laroze, Jyoti Jyoti
article en

Abstract

This study examines the flow characteristics of tetra-hybrid Jeffrey nanofluids in a porous medium through a vertical channel. The use of a tetra-hybrid nanofluid enables the synergistic integration of four distinct nanoparticles, yielding superior thermophysical characteristics, enhanced thermal transport, and improved suspension stability compared with conventional hybrid and tri-hybrid nanofluids. The effects of thermophoresis, Brownian motion, and slip boundary conditions are analyzed along with viscous dissipation, Joule heating, thermal radiation, and heat flux. Homogeneous and heterogeneous chemical reactions are incorporated into the mathematical model, where partial differential equations (PDEs) are converted into ordinary differential equations (ODEs). The transformed equations are solved numerically in MATLAB using the shooting method under the assumptions of low Reynolds number and long wavelength. A graphical analysis explores velocity, temperature, and concentration distributions. The results reveal that buoyancy, magnetic, and porous-medium effects govern the velocity field, while Prandtl number, thermophoresis, Brownian motion, homogeneous reaction heat, and thermal radiation significantly modify the temperature distribution; meanwhile, Schmidt number, thermophoresis, Brownian motion, and homogeneous reaction strongly influence the nanoparticle concentration. Additionally, artificial neural networks (ANNs) are employed to predict nanofluid behavior under varying physical conditions, including the influence of viscous dissipation, heat flux, and magnetic fields. The Levenberg-Marquardt backpropagation algorithm is applied for estimating key transport properties such as the Sherwood number, Nusselt number, and skin friction coefficient. ANN predictions are validated through training accuracy, performance metrics, regression analysis, and error histogram evaluations. The findings confirm that the ANN model provides highly accurate predictions, optimizing computational efficiency. This research has significant applications in energy systems, thermal regulation, chemical processing, biomedical advancements, vehicle cooling, nuclear reactors, and transportation system optimization. For the Nusselt number, the ANN predictions exhibit an average absolute percentage error of 2.9680% and a coefficient of determination (R2) of 0.9130, demonstrating good agreement with the numerical results. The maximum prediction error is 15.1120% for Case 8, followed by 8.1079% for Case 10. These results confirm that the developed ANN model can effectively reproduce the nonlinear numerical predictions over the investigated range.

Discover NanoVol. 21(1)
Taif University (SA), University of Tarapacá (CL), Birla Institute of Technology and Science, Pilani (IN)
Taif University
Nanofluid Flow and Heat Transfer
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon