Artificial intelligence-based fractional modeling of radiative Jeffrey flow with heat generation and reaction effects

Abstract

This study investigates the influence of thermal radiation on the free convection flow of a Jeffrey fluid over a vertical stationary plate. To account for memory and non-local effects in the transport process, the Atangana-Baleanu fractional derivative in the Caputo sense is incorporated into the mathematical model. The governing fractional differential equations are solved analytically using the Laplace transform technique. To further validate and predict the obtained solutions, an Artificial Neural Network (ANN) based on the Levenberg–Marquardt Scheme (LMS-NNA) is developed and trained using the analytical results. The results indicate that thermal radiation significantly enhances the temperature distribution by approximately 12%, while the fluid velocity decreases by about 9% because of the increased thermal resistance and effective viscosity within the boundary layer. The ANN model accurately reproduces the analytical solutions, achieving a maximum prediction error of (10−7) and a regression coefficient ((R)) of 0.9999, demonstrating excellent predictive capability. The study combines the Atangana-Baleanu fractional derivative with an ANN-based prediction framework to analyze Jeffrey fluid flow under thermal radiation. This integrated approach provides highly accurate solutions while offering an efficient computational framework for analyzing fractional transport phenomena. The findings contribute to the understanding of radiative heat transfer in non-Newtonian fluids and may be useful in the design and optimization of advanced thermal management and energy-related engineering systems.