Artificial neural network prediction of heat transport in hybrid nanofluid flow over a Riga plate with heat generation and Darcy-dissipation

Efficient thermal management remains a critical challenge in advanced thermal energy systems, where conventional fluids often fail to provide sufficient heat transfer performance. This study explores the thermal transport behavior of a hybrid nanofluid comprising AA7072 and AA7075 alloy nanoparticles suspended in water over a Riga plate embedded in a porous medium, motivated by the need for enhanced heat transfer under electromagnetic control. The flow is analyzed within a porous substrate under the combined integration of Darcy dissipation, internal heat generation, and heat radiant. In the presence of electromagnetic forcing by the Riga surface, accounting for the impact of thermal buoyancy to get the free convection effect on the flow phenomena. The thermophysical models equipped with various properties enhance the flow pattern. The mathematical model proposed for the suppositions mentioned above is transformed into their comparable non-dimensional structure employing similarity laws, and further numerically tackled these distorted equations. The assessment of several factors is visualized through plots with the actual range of these factors. The results demonstrated that the hybrid alloy nanofluid significantly enhances the heat transfer rate. Increasing the modified Hartmann number intensifies flow acceleration near the Riga surface, while higher thermal radiation and heat generation parameters substantially elevate the temperature distribution. Further, the optimized heat transfer rate is presented using a deep learning algorithm, utilizing the back-propagation technique. The best performance level of the response is obtained for the variation of the particular factors shows a best fit model. Hybrid nanofluids develops heat transfer performance compared with conventional fluids. Electromagnetic control increases flow and temperature on a Riga plate. Neural network accurately predicts the heat transfer behaviour for energy systems.