Machine learning-based investigation of activation energy for bio-convective boundary layer flow inspired by challenges in aerospace heat transfer systems

In this study, a machine learning-based investigation to measure boundary layer flow even when the wall is at different temperatures and interacts with motile gyrotactic microorganisms is conducted with direct applications in optimizing fuel combustion, improving biofuel production, and designing advanced thermal management systems. To deal with this complex flow scenario and its variants, a nonlinear autoregressive with Exogenous inputs model is implemented and trained by the Levenberg-Marquardt method. The model is verified by comparing it to the reference dataset created with Adams' numerical methods. Similarity transformations are put to work in this framework, they reduce governing equations down to a manageable form that is then solved iteratively. According to the findings, wall temperature changes significantly affect the distribution and flow characteristics of microorganisms within a boundary layer. This, in turn, affects flow stability and heat transfer functions. The machine learning model achieved a high degree of accuracy, as indicated by low Mean Squared Error values, and successfully maintained its performance across diverse flow scenarios. The model achieved negligible MSE magnitudes, with scenarios reaching a Mean Square Error (MSE) of approximately 8.718 × 10 −11 to 1.073 × 10 −10 consistently indicating high prediction accuracy and alignment with reference solutions. This means that the machine learning procedure portrayed a good generalization capability. The research offers an effective tool for studying complex biofluid systems, delivering increased predictive accuracy combined with decreased processing time from simulations that involve microorganism-laden flows at different temperatures. The findings offer valuable contributions to sustainable energy technologies, environmental conservation, and the development of novel fuel systems, aligning with the growing need for energy efficiency and pollution control.