Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

Abstract

Accurate quantification of dissolved oxygen (DO) is critically important for managing water resources and controlling pollution. Artificial intelligence (AI) models have been successfully applied for modeling DO content in aquatic ecosystems with limited data. However, the efficacy of these AI models in predicting DO levels in the hypoxic river systems having multiple pollution sources and complicated pollutants behaviors is unclear. Given this dilemma, we developed a promising AI model, known as support vector machine (SVM), to predict the DO concentration in a hypoxic river in southeastern China. Four different calibration models, specifically, multiple linear regression, back propagation neural network, general regression neural network, and SVM, were established, and their prediction accuracy was systemically investigated and compared. A total of 11 hydro-chemical variables were used as model inputs. These variables were measured bimonthly at eight sampling sites along the ruralsuburban-urban portion of Wen-Rui Tang River from 2004 to 2008. The performances of the established models were assessed through the mean square error (MSE), determination coefficient (R 2 ), and Nash-Sutcliffe (NS) model efficiency. The results indicated that the SVM model was superior to other models in predicting DO concentration in Wen-Rui Tang River. For SVM, the MSE, R 2 , and NS values for the testing subset were 0.9416 mg/L, 0.8646, and 0.8763, respectively. Sensitivity analysis showed that ammonium-nitrogen was the most significant input variable of the proposal SVM model. Overall, these results demonstrated that the proposed SVM model can efficiently predict water quality, especially for highly impaired and hypoxic river systems.

Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality

“…Moreover, there are several studies based on multiple linear regression methods combined with AI to develop WQ models (Slaughter et al, 2017;Tomas et al, 2017). An AI system was developed (Ji et al, 2017) by combining multiple models based on SVM, ANNs, LR to prove the supremacy of SVM in predicting dissolved oxygen (DO) concentration in Wen-Rui Tang River, China. Similarly, to predict the level of DO, a general regression neural network (GRNN) was proposed by (Antanasijević et al, 2014) for the Danube River.…”

Hybrid Machine Learning Ensemble Techniques for Modeling Dissolved Oxygen Concentration

“…This necessitates the development of a strong, accurate and non-linear hydro-environmental method known as the AI approach. In parallel with this, different types of AI based models have been explored for DO prediction such as artificial neural network (ANN) [11]- [15], support vector machine (SVM) [9], [16]- [20], adaptive neuro-fuzzy inference system (ANFIS) [13], [15], [21]- [24], complementary wavelet-AI model, and hybrid evolutionary algorithms [25], [26], [20], [29], [30] extreme learning machine (ELM) [30], [31], deep learning neural network [32], [33] and fuzzy logic models [34]- [36] for the modeling and prediction of DO concentration.…”

Marine Dissolved Oxygen Prediction With Tree Tuned Deep Neural Network

“…Some machine learning algorithms have been used to learn hydrological data. For example, an artificial neural network (ANN) was employed to dissolved oxygen (DO) concentrations of the canals in Bangkok [10], random forest algorithm was used to predict DO in the southern ocean [11], and support vector regression was used to predict DO in Wen-Rui Tang river [12]. However, deep learning methods have not been applied to predict MDOC widely.…”