Impact of thermal radiations and viscous dissipation during the boundary layer non‐Newtonian fluid flow past a slender needle: Probed by machine learning

Abstract We examine a new model for the Casson fluid (CF) migration near a thin needle. The needle is moving along the free stream with constant velocity. The impacts of nonlinear thermal radiation, Joule heating, magnetic fields, and viscous dissipation are considered in the flow. The flow is modeled with the basic equations, whose complexity is reduced with the similarity transformations. We introduced the artificial neural network (ANN) to tackle the first‐order system of equations. ANN is trained with the numerical methods (bvp4c) solution that uses the Levenberg‐Marquardt algorithm by choosing the best possible weights. A comprehensive graphical description is provided with varying heating parameters, Eckert number, radiation parameter, velocity ratio parameter, Prandtl number, and the size of the thin needle. The rise in the needle size and velocity ratio reduce the velocity flux and increases the thermal transport. The CF parameter increases the velocity gradient. The Eckert number and radiation parameter increase the thermal profile with their increasing values. The regression plots display that data is utilized in the curve fitting, while the error histograms depict the minimal zero error. Furthermore, the mean square error and performance validation for each varying parameter are presented. For validation, the present numerical results are compared in tabular form with the published literature, where the current approach is validated.