Artificial intelligence driven multiphysics analysis of Casson bioconvective ternary nanofluid flow over an inclined needle

This study investigates the bio-convective flow of ternary Casson nanofluid across inclined moving thin needle embedded in a porous medium, considering Arrhenius activation energy and non-uniform heat generation/absorption. Such models are important in biomedical engineering, thermal energy systems, and advanced cooling technologies, where enhanced heat and mass transfer characteristics are required. The governing equations are solved numerically using the bvp4c technique, while Artificial Neural Network (ANN) analysis is employed to evaluate the accuracy and stability of the computational results. The findings reflect that increasing Casson parameter, activation energy parameter, needle thickness, bioconvection Lewis number, Peclet number, and chemical reaction parameter led to reduction in velocity distribution and reverse trend for increasing inclination angle of surface. Results show that rising chemical reaction parameter, activation energy parameter led to rise temperature distribution and opposite behavior for needle thickness. It has been reflected that increasing activation energy parameter caused to increase concentration. Graphical outcomes show that microorganism density rises with the rise of activation energy parameter, bioconvection Lewis number, Peclet number, and inclination angle. Furthermore, the ANN model demonstrates high predictive accuracy with small and uniformly distributed errors, confirming the reliability of the numerical analysis. For the better visibility, three-dimensional graphs of the velocity, temperature and concentration and microorganisms' density profiles are shown. For compact visualization of the behavior of velocity and temperature, the graphical representation of contours plots are also presented Current results are validated with published results in the literature.