Supervised Stochastic Approach for computational analysis of convectively heated magnetized nanofluid flow with bioconvection aspects

Abstract

Our study delves into the dynamics of a convective Magneto-Hydrodynamic Bioconvective Nanofluid model (MHD-BCNFM) flowing over a convectively heated stretched sheet. To accomplish this, we utilize the distinctive capabilities of the Supervised Stochastic Approach for Computational Analysis (SSACA). By integrating similarity transformations, we convert the partial differential equations (PDEs) governing the system into coupled ordinary differential equations (ODEs). We generate the dataset for our approach using the Adam numerical technique specifically tailored for the (MHD-BCNFM). Achieving this involves systematic modulation of parameters such as λ, bioconvection Péclet number Pe, Bioconvection constant σ, Brownian motion parameter Nb, and thermophoresis parameter Nt. ''Moreover, we utilize a reference dataset to compute numerical values of various physical quantities in the (MHD-BCNFM) employing SSACA-based Artificial Intelligence methods. The effectiveness of our devised SSACA approach is demonstrated by a negligible mean squared error, ranging from approximately 10−8 to 10−10. Histograms exhibit a maximum error range of 10−5, closely aligning with optimal correlation/regression measures. Outstanding performance metrics in terms of Mean Squared Error (MSE) are attained at levels such as l 9.93E−12, 1.07E−11, 6.28E−10, 1.43E−11, 2.09E−09, 3.65E−11, 2.97E−11, and 2.80E−13 against 320, 430, 209, 85, 356, 295, 66, and 136 epochs. A comparative study between the proposed and reference datasets underscores the authenticity and precision of SSACA, supported by error analyses ranging from E-05 to E-09 across all scenarios.

Keywords

• Computational Analysis
• Supervised Stochastic approach
• Levenberg-Marquardt Bioconvection
• Nanofluid