Machine Learning-Enhanced Dual-Parameter Fiber Sensor Using Tilted Grating for Simultaneous Turbidity and Temperature Monitoring

We designed a fiber-optic sensor based on a tilted fiber Bragg grating (TFBG) that simultaneously monitors turbidity and temperature by analyzing spectral intensity variations via scattering effect and wavelength shifts through interference effect. Additionally, we introduced a Random Forest (RF) model for dual-parameter analysis and prediction of marine data. By constructing multiple decision trees and aggregating their predictions through voting or averaging, this model demonstrates enhanced accuracy and robustness. The system achieves remarkable performance in turbidity prediction, with a root mean square error (RMSE) as low as 0.0036, while temperature monitoring yields an RMSE of 0.0079, confirming the model's effectiveness in analyzing and predicting both parameters. This architecture integrates optical sensing with machine learning, establishing a new paradigm for intelligent marine monitoring solutions.