Novel Neural Network-Based Prediction Model for Quantifying Hydroquinone in Compost with Biosensor Measurements

Abstract

Hydroquinone generally appears in compost as a direct pollutant or an intermediate product in the aromatic pollutant biodegradation process. The requirement of quantifying its concentration calls for efficient and economical analytical methods. In this study, artificial neural networks (ANNs) were combined with a biosensor to realize nonlinear determination of hydroquinone in a complex composting system. The direct detection range for hydroquinone in compost system using biosensor reached 1.5 × 10⁻⁸ ∼ 3.6 × 10⁻⁴ M. Meanwhile, the performance of the ANN model was compared with a nonlinear regression model with respect to the simulation accuracy and adaptability to uncertainty, etc. Nonlinear range analysis could extend the usable detection range of biosensor for hydroquinone and could improve the adaptability of the detecting system in real sample determination. Results illustrated that the combined application of biosensor measurement and artificial neural network analysis was a rapid, sensitive, and robust method in a quantitative study of a composting system. This method could be a good analytical tool for further application in real sample determination in other complex environments which refer to human life and health.