Marine Water Quality Assessment using Support Vector Regression and Neutrosophic control charts

Abstract

In recent years, with the growth of industries in coastal cities, the wastewater including organic and inorganic substances were discharged into seawater, triggering seawater pollution which leads to many social problems. Hence, it is essential to examine the marine environment by considering the key factors like oxygen-related parameters, including Biological Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Dissolved Oxygen (DO). The present study suggests a hybrid statistical process monitoring framework by combining the V-Exponentially Weighted Moving Average (VEWMA) control chart with principal component analysis (PCA) . PCA is considered in this study to extract the dominating linear features from the multivariate marine water quality data. The PCA scores are integrated into NVEWMA monitoring statistics to strengthen the identification of process changes. To evaluate the effectiveness of the proposed method, a real-life marine water quality data is used. The results show that the integration of Machine Learning methods with NVEWMA control chart provides a useful method for keeping an eye on environmental processes and to identify possible shifts.