Intelligent solution predicted Bayesian regularization networks for chemical reactive flow of hybrid nanoliquid with applications of bioconvection and solar radiation

The goal of this research is to evaluate the performance of gyrotactic and oxytactic microbes in hybrid nanofluid by building a deep neural network using the Bayesian regularization technique. In a hybrid nanofluid containing SWCNT and MWCNT, water serves as the base liquid. The input dataset for the network was created using the RKF-45th command. Three independent instances were created to study how the various parameters changed on the proposed model. A variety of statistical indicators are employed to evaluate the network's accuracy and precision. This technique is extremely useful for wastewater treatment since microorganisms increase the fluid's bioactivity and efficacy in removing pollutants. Furthermore, the model can be used to optimize thermal performance in energy systems like solar collectors and heat exchangers. Its predictive capabilities using artificial neural networks broaden its applicability in commercial cooling operations and environmental monitoring. The rate of heat transmission in hybrid nanofluids and nanofluids increases as the volume friction of nanoparticles increases.