In this investigation, an artificial intelligence-based neural network is used to estimate solutions for the flow and heat transfer characteristics of Ag-CuO/Water hybrid nanofluid past a rotating stretching sheet. Heat source/sink, convective movement, nonlinear thermal radiation, and chemical reactions are all taken into consideration in the energy and concentration equations. The modelled equations are transformed into ordinary differential equations by implementing a suitable similarity transformation. The Levenberg–Marquardt method is used by an artificial neural network (ANN) for solving equations computationally. The outcomes of training, testing, and validation are examined using regression plots, error histograms, performance charts, and transition state analysis to assess the accuracy of the suggested methodology. An enhancement in the Magnetic (M), Rotation (), and porosity (K) parameters leads to a rise in temperature and concentration profiles; however, a converse effect has been observed with an increment in the Stretching (λ) and ratio (γ) parameters. Growing the Space-dependent heat source/sink (A^*) and nonlinear thermal radiation parameter (Rd) appreciates the velocity profiles; nonetheless, it decreases for the stretching ratio parameter (λ). To illustrate the precision of the numerical method used, a comparison table is shown, showing an impressive degree of agreement with earlier reported results. The findings show that the hybrid nanofluid offers the possibility of increased thermal performance in application in engineering applications by dramatically improving the heat transmission properties under the applicable circumstances. The quantitative findings of our research work are that velocity, temperature, and concentration fields exhibit strong parametric sensitivity: λ and γ generally suppress flow, heat, and mass transport, while M, K, Rd, and related parameters enhance boundary-layer thickness, temperature, and concentration but may reduce transfer rates due to Lorentz and radiative effects. Skin friction increases with M, Rc, λ, and related parameters, whereas heat and mass transfer rates decline at higher M and Rd owing to thermal boundary-layer thickening and magnetic damping. The AINN trained via the Levenberg–Marquardt algorithm demonstrated near-perfect accuracy (MSE ≈ 0, R = 1), minimal error dispersion, and robust convergence, validating its effectiveness in modeling complex HNF transport phenomena. The results demonstrate that heat transfer is improved for a strong non-linear thermal radiation parameter by 30%, considerably. The novelty of this work lies in integrating an Artificial Intelligence Neural Network (AINN) with the Levenberg–Marquardt algorithm to model complex nonlinear heat and mass transfer phenomena in hybrid nanofluids efficiently. This approach addresses a key research gap by providing a predictive, adaptable framework that minimizes the computational expense and limitations of conventional numerical simulations. The model captures coupled thermal and concentration boundary layer behaviors that conventional methods struggle to approximate efficiently. It also provides a generalized predictive framework adaptable to different nanofluid compositions and flow conditions. Real-life applications include thermal management in microelectronics, cooling of energy storage systems, and enhancing heat exchangers. Additionally, it can be used in biomedical cooling, solar thermal collectors, and industrial processes requiring efficient heat and mass transport.
Anjum et al. (Tue,) studied this question.