Machine learning impact of radiative blood flow over a wedge in a time-dependent MHD Williamson fluid

Abstract

The main objective of this research is to examine the radiation effects of an unsteady MHD Williamson biofluid (Blood) over a wedge that interacts with thermophoresis diffusion and Brownian motion. The necessary prerequisites of partial differential equations (PDEs) ensure the development of suitable mathematical frameworks for momentum, energy, and concentration. These appropriate nonlinear PDEs are frequently transmuted into ordinary differential equations (ODEs) by implemented similarity transformation. The results of these ODEs have a significant impact on the BVP4C approach from the MATLAB package computational structures. The graphs and tabular data provided the various values for pertinent parameters on the non-dimensional velocity temperature, concentration profiles, and the numerical values of skin friction, Nusselt number, and Sherwood number were found and discussed in detail. A novel aspect of the research effort was the effective incorporation of multiple linear regression (MLR) employing machine learning (ML), a statistical technique to forecast the physical quantities for present numerical results with an accuracy of 95%. Finally, the response and predicted variables were verified using linear regression. The potential benefit of these outcomes is to develop novel therapeutic and diagnostic strategies for cancer treatment, as well as for a better understanding of medical problems and designing more effective drug delivery systems. In particular, for significant developments in computer technology and resources, the enormous computational cost of these simulations still keeps them from becoming a clinical tool. An additional benefit is that the outcomes showed acceptable congruence with the tangible findings of recent research and enlargements for future investigators.