This work investigates the thermal and flow properties of a rotating hybrid nanofluid comprising TiO 2 – Ag nanoparticles in a water-ethylene glycol matrix across a linearly extending sheet, emphasising dissipative heat effects under magnetohydrodynamic (MHD) conditions. An essential innovation involves the amalgamation of the Fourier numerical approach with the XGBoost machine learning model to forecast and examine intricate heat and mass transfer phenomena. The model incorporates viscous and ohmic dissipation, rotational effects, and convective flow, demonstrating that ideal thermal zones can diminish hotspots by as much as 125 times, while magnetic field modulation can improve heat transfer efficiency by up to 120 times. Thorough visual assessments validate the precision of XGBoost in reproducing simulation outcomes. The novelty of this work stems from the effective fusion of machine learning with numerical simulation, providing a powerful framework for designing efficient thermal management systems in advanced engineering applications such as electronics cooling, automotive systems, and nuclear energy.
Surendar et al. (Thu,) studied this question.