Artificial neural network optimization of gyrotactic microbes in water hybrid nanoliquid with carbon nanotubes using modified Hamilton crosser model

The artificial neural network-optimized model for exploring local thermal non-equilibrium (LTNE) influences on gyrotactic microorganisms in a chemically reactive SWCNTs-MWCNTs/water-based hybrid nanofluid has a wide range of applications in advanced engineering and biotechnology. It has the potential to upsurge heat transfer performance in microfluidic and cooling systems that incorporate hybrid nanofluid and microbial activity. In biotechnology, the model aids in the optimization of microorganism-driven mixing, sensing, and biodegradation processes in complicated heat and chemical environments. It can also help with the design of more efficient reactors and bio-suspension systems, as gyrotactic microorganisms improve fluid stability and energy transmission. Additionally, the application of neural networks enables real-time optimization and predictive control, which is advantageous for smart bio-nanofluid systems, environmental remediation, and industrial thermal management. The goal of this investigation is to use artificial neural networks to evaluate the outcome of local thermal non-equilibrium on microbes in hybrid nanofluid flow over a sheet with porous media. The liquid phase thermal profile increases as the values of the interphase heat transfer parameter grow, whereas the solid phase thermal profile decreases.