Artificial neural network solution of Maxwell hybrid nanofluid with multiple slips, with radiation effects flowing across a porous extending sheet

Heat transfer phenomena in non-Newtonian nanofluids (N-N-Fs) are extensively observed across various disciplines, including nautical science, fluid biology, melt-spinning, thermal control over metallic material, protecting systems for thermal exchangers, and delays. In light of the aforementioned significance, the present investigation centers on the implementation of an artificial neural network (ANN) model to analyze the behavior of magneto-hybrid Maxwell nanofluid (MHMNF-ANN) flow across a stretched surface in a permeable medium, highlighting the novel application of hybrid nanofluid, taking into account the effects of heat generation/absorption, different slip situations, and solar radiation. The research holds significant implications for various domains such as magnetohydrodynamics (MHD) mechanisms, thermal exchange systems, and porous media, in addition to advancements in nanofluid technology. Hybrid nanoparticles composed of alumina and magnetite are suspended within a 50:50 aqueous solution of water and ethylene glycol (WEG) to constitute the hybrid nanofluid. The numerical solution is derived through the application of the RK45 method utilizing MATLAB software. The acquired dataset was employed to train the artificial neural network (ANN) model, which was subsequently validated against numerical values of significant engineering parameters. Effect of emerging factors on the flow dynamics is reported through graphs and tables.