In this study, we present a deep-learning-assisted design of a photonic crystal fiber (PCF)-based surface plasmon resonance (SPR) biosensor that enables simultaneous, label-free detection of multiple waterborne analytes. Using finite element analysis, a dual-channel PCF is modeled to generate more than 40,000 data points. A lightweight, fully connected regressor predicts the confinement loss (CL) and amplitude sensitivity (AS) from structural variables (hole sizes, gaps, metal/dielectric thicknesses) and operational variables (wavelength, refractive index (RI) of analytes in both channels), achieving R2≈0.99 with low error. The surrogate speeds up the process of exploring designs. Using SHAP analysis, it finds that wavelength and channel RIs are the main factors, while layer thicknesses mainly change channel-specific resonances. Parametric sweeps confirm stable, concurrent redshifts across channels with increasing RI, enabling multiplexed detection of bacterial pathogens and formaldehyde. The proposed model achieves maximum amplitude sensitivity (AS) of 512.87 RIU−1 , wavelength sensitivity (WS) of 10, 638.30 nm/RIU , and sensor resolution (SR) of 9.4×10−5 . The resulting architecture combines high accuracy with computational efficiency, offering a compact route to rapid, real-time water quality monitoring and food safety screening, as well as a generalizable workflow for data-driven PCF-SPR design.