Artificial Intelligence Neural network modeling of radiative nanofluid flow via a vertical cone in porous substance with activation energy effect

Artificial Intelligence Neural networks simulate human cognitive processes to help computers comprehend data. Deep learning uses a multilayer network of neurons, similar to the human brain. The technique creates an adaptive framework that lets computers learn from mistakes and improve over time. This study examines the impact of activation energy in a downward cone. The transfer is facilitated by a thermally radiant Williamson nanofluid and an overexposed porous medium. By utilizing suitable transformation equations, the governing partial differential equations (PDEs) can be reduced to a set of two nonlinear ordinary differential equations (NODE). The projected outcomes of the proposed Artificial Intelligence Neural Network (AINN) demonstrate a notable superiority over other solution methods, as shown by the Mean Square Error (MSE) analysis. Additionally, it was detected that the developed Artificial Intelligence Neural Network model had a remarkable level of efficacy in the process of estimation, as shown by a correlation coefficient value of 1.