Integrating artificial intelligence and machine learning with numerical simulation for enhanced thermal performance of ternary nanofluid

Abstract The motivation for this investigation stems from a perceived gap in the vast literature on nanofluids, specifically in relation to their interactions with different surfaces and their numerical simulation. The main objective of this study is to effectively utilize novel machine learning (ML) and artificial intelligence (AI) techniques to investigate the thermal behavior of magnetohydrodynamic ternary nanofluids via an impermeable cylinder subject to activation energy and chemical reactions. We adopt the Levenberg–Marquardt algorithm with backpropagation artificial neural network technique (LMA-ANN), an AI-based scheme, to achieve this goal. The transition of governing equations to ordinary differential equations is accomplished through the use of similarity scaling. Obtained equations are then numerically evaluated using modified finite difference discretization (the Keller-Box approach). Regression scores equal to 1 indicate an excellent match between the numerical data and the predictions. The results demonstrate that temperature diminishes with the activation energy component, but it escalates with the chemical reaction. The activation energy parameter enhances both heat and mass transport processes. The results produced by this framework possess significant significance and usefulness in the field of biotechnology, drug delivery, cancer treatment, biological engineering, and bio-imaging.