Graphene‐Au‐Cu‐MXene Multilayer Metamaterial Plasmonic Biosensor With Machine Learning‐Assisted Optimization for Label‐Free THz Detection of Waterborne Bacterial Pathogens

ABSTRACT Detection of waterborne bacterial pathogens such as Escherichia coli , Salmonella typhimurium , and Vibrio cholerae requires methods that operate with high sensitivity and can be deployed outside laboratory settings. This study describes a multilayer metamaterial plasmonic biosensor operating in the terahertz frequency range for label‐free refractive index sensing. The device uses a 4 × 4 periodic array of vertically stacked resonant nanostructures on a silicon substrate. The structure combines a gold Y‐shaped nanoresonator, a copper circular cavity, a MXene square‐ring resonator, and a graphene circular disc. This configuration supports strong field confinement, electrical tunability through graphene, and reduced reliance on noble metals.Finite element simulations in COMSOL Multiphysics quantify the dependence of absorption on incidence angle, graphene chemical potential, and resonator geometry. The optimized configuration uses a copper circular resonator diameter of 5500 nm, a MXene square‐ring outer dimension of 2000 nm, and a gold Y‐resonator arm width of 600 nm. Within a refractive index range of n = 1.33 to n = 1.3921, the device achieves a peak sensitivity of 0.751 THz/RIU and a figure of merit of 1.140 RIU −1 . The frequency response shows a linear relation with refractive index, with R 2 = 0.93337 across the evaluated material configurations. A regression‐based surrogate model trained on the simulation dataset predicts device response with R 2 above 0.9992 and mean absolute percentage error below 0.2%. This model reduces the need for repeated full‐wave simulations during design iterations. The results support the use of the proposed structure for label‐free THz sensing of waterborne pathogens over relevant refractive index ranges.