Machine learning-driven analysis of heat transfer in chemically reactive fluid flow considering Soret-Dufour effects

• The flow and thermal performance of Tangent hyperbolic nanofluid were investigated. • Impacts of thermal radiation, chemical reaction, concentration, MHD, and Soret–Dufour effects were identified. • A novel advanced Gaussian Neural Network (GNN) combined with a Hybrid Cuckoo Search (HCS) procedure was proposed for various case predictions. • Numerical calculations and average relative errors of current models were conducted. The study investigates tangent hyperbolic nanofluid flow across an extended media, emphasizing magnetohydrodynamic influences, mixed convection, and nanoparticle transport with the help of an innovative and advanced technique. It employs a sophisticated Gaussian Neural Network and Hybrid Cuckoo Search to mimic complex fluid dynamics accurately, ensuring efficient computation and solution precision. By transforming the governing system of nonlinear partial differential equations into ordinary differential equations via similarity transformation, the methodology attains computational efficiency and solution precision. Statistical measures confirm the model's resilience, indicating absolute error variations from E −05 to E −12 and mean squared errors continuously between E −02 − E −07 , highlighting the reliability of the model, while the Error in Nash-Sutcliffe Efficiency values fall within the interval E −05 − E −15 . The Theil's Inequality Coefficient values lie in the range of E −01 − 10 −07 . The findings underscore the model's capacity to improve thermal management, energy efficiency, and process dependability in sectors like chemical processing, environmental engineering, and sustainable energy production. This study positions the Gaussian Neural Networks framework as a robust computational instrument, providing a foundation for subsequent investigations into intricate geometries, multi-physics phenomena, and magnetohydrodynamic systems for novel technology applications.