Anomaly detection method for urban river water quality based on background model prediction using three-dimensional fluorescence

Abstract Three-dimensional fluorescence spectroscopy has great potential for detecting water quality anomalies in urban rivers and protecting against organic pollution. However, current detection methods inadequately address critical application scenarios, such as fluctuations in river water background, low concentration of pollutants, and the fluorescence peaks overlap between pollutants and background. In this paper, a fluorescence spectrum feature extraction method which is effective for the above scenarios was proposed. The proposed method involves a sequential process. First, the original spectrum undergoes preprocessing using a novel method. Next, an alternating residual tri-linearization technique is applied to establish a predictive model for river water spectrum changes. Subsequently, the background model is utilized for spectrum decomposition and reconstruction of the test sample. This reconstructed spectrum is then used to derive the residual spectrum by comparison with the original. Finally, frequency domain features are extracted from the residual spectrum to enable classification, while the background model undergoes real-time updates. In the three meaningful scenarios mentioned above, the accuracy of the proposed method for anomaly detection reached 99%, 82%, and 98%, respectively. Our accuracy is higher than several typical benchmark methods.