Machine Learning-Driven Compensation for Nonideal Channels in AWG-Based FBG Interrogator

We present an experimental study of a fiber Bragg grating (FBG) interrogator based on a silicon oxynitride photonic integrated arrayed waveguide grating (AWG). While AWG-based interrogators are compact and scalable, their practical performance is limited by nonideal spectral responses. To address this, two calibration strategies within a 2.4 nm spectral region were compared: first, a segmented analytical model based on a sigmoid fitting function, and second a machine learning (ML)-based regression model. The analytical method achieves a root-mean-square error of 7.11 pm within the calibrated range, while the ML approach based on exponential regression achieves 3.17 pm. Moreover, the ML model demonstrates generalization across an extended 2.9 nm wavelength span, maintaining sub-5 pm accuracy without refitting. Residual and error distribution analyses further illustrate the tradeoffs between the two approaches. ML-based calibration provides a robust, data-driven alternative to analytical methods, delivering enhanced accuracy for nonideal channel responses, reduced manual calibration effort, and improved scalability across diverse FBG sensor configurations.