Hybrid nanofluids are a type of nanofluid that is created by combining two different types of nanoparticles with a traditional fluid. These nanofluids have unique physicochemical properties that make them more effective at transferring heat than traditional nanofluids. This research paper focuses on predicting thermal and energy transport in non-Newtonian biomagnetic hybrid nanofluids that contain gold and silver nanoparticles, using Gaussian process regression (GPR). The study uses blood as the traditional fluid and incorporates the effects of thermal radiation, thermophoresis, Brownian motion and activation energy into the model equation. The governing nonlinear partial differential equations are simplified to a set of ordinary differential equations using similarity replacements. The shooting method, along with the Runge–Kutta-Fehlberg fourth–fifth-order scheme, is used to solve the transformed equations using MATLAB. The results of the study are presented through figures and tables, which include the coefficient of skin friction, Nusselt number, Sherwood number and motile microbe’s flux, illustrated with surface plots. The GPR model is developed using four basic function kernels (squared exponential, exponential, rational quadratic and matern32 functions) and evaluated using statistical indicators such as RMSE, MSE, MAE and R. The predicted results and simulated numerical values are in good agreement with the coefficient of determination (R²) of 0.999999 for all parameters. The study also finds that GPR models with exponential kernel functions outperform other kernel functions in both the Oldroyd-B and Casson hybrid nanofluid data sets. However, the findings indicate that nanofluids and hybrid nanofluids have superior thermal qualities and stability, making them promising candidates for various thermal applications including solar thermal systems, automotive cooling systems, heat sinks, engineering, medical areas and thermal energy storage.

混合纳米流体是一种纳米流体，是通过将两种不同类型的纳米颗粒与传统流体相结合而产生的。这些纳米流体具有独特的物理化学特性，使其比传统纳米流体更有效地传递热量。本研究论文的重点是使用高斯过程回归 (GPR) 预测包含金和银纳米粒子的非牛顿生物磁性混合纳米流体中的热和能量传输。该研究以血液作为传统流体，并将热辐射、热泳、布朗运动和活化能的影响纳入模型方程中。使用相似替换将控制非线性偏微分方程简化为一组常微分方程。射击法与龙格-库塔-菲尔伯格四阶-五阶格式一起使用 MATLAB 来求解变换方程。研究结果通过图表呈现，其中包括皮肤摩擦系数、努塞尔数、舍伍德数和运动微生物通量，并用曲面图说明。 GPR模型采用四种基本函数核（平方指数函数、指数函数、有理二次函数和matern32函数）开发，并使用RMSE、MSE、MAE和R等统计指标进行评估。预测结果和模拟数值与所有参数的决定系数 (R ² ) 均为 0.999999。研究还发现，在 Oldroyd-B 和 Casson 混合纳米流体数据集中，具有指数核函数的探地雷达模型优于其他核函数。然而，研究结果表明，纳米流体和混合纳米流体具有优异的热质量和稳定性，使其成为各种热应用的有希望的候选者，包括太阳能热系统、汽车冷却系统、散热器、工程、医疗领域和热能存储。