TY - JOUR ID - 32056 TI - Artificial intelligence-based approaches for multi-station modelling of dissolve oxygen in river JO - Global Journal of Environmental Science and Management JA - GJESM LA - en SN - 2383-3572 AU - Elkiran, G. AU - Nourani, V. AU - Abba, S.I. AU - Abdullahi, J. AD - Faculty of Civil and Environmental Engineering, Near East University, Near East Boulevard 99138, Nicosia, Cyprus AD - Department of Water Resources Engineering, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran Y1 - 2018 PY - 2018 VL - 4 IS - 4 SP - 439 EP - 450 KW - Adaptive neuro fuzzy inference system (ANFIS) KW - Feed forward neural network (FFNN) KW - Multi-linear regression (MLR) KW - Dissolve oxygen (DO) KW - Water quality KW - Yamuna River DO - 10.22034/gjesm.2018.04.005 N2 - ABSTRACT: In this study, adaptive neuro-fuzzy inference system, and feed forward neural network as two artificial intelligence-based models along with conventional multiple linear regression model were used to predict the multi-station modelling of dissolve oxygen concentration at the downstream of Mathura City in India. The data used are dissolved oxygen, pH, biological oxygen demand and water temperature at upper, middle and downstream of the river. To predict outlet of dissolved oxygen of the river in each station, considering different input combinations as i) 11 inputs parameters for all three locations except, dissolved oxygen at the downstream ii) 7 inputs for middle and downstream except dissolved oxygen, at the target location and lastly iii) 3 inputs for downstream location. To determine the accuracy of the model, root mean square error and determination coefficient were employed. The simulated results of dissolved oxygen at three stations indicated that, multi-linear regression is found not to be efficient for predicting dissolved oxygen. In addition, both artificial intelligence models were found to be more capable and satisfactory for the prediction. Adaptive neuro fuzzy inference system model demonstrated high prediction ability as compared to feed forward neural network model. The results indicated that adaptive neuro fuzzy inference system model has a slight increment in performance than feed forward neural network model in validation step. Adaptive neuro fuzzy inference system proved high improvement in efficiency performance over multi-linear regression modeling up to 18% in calibration phase and 27% in validation phase for the best models. UR - https://www.gjesm.net/article_32056.html L1 - https://www.gjesm.net/article_32056_bffa826388556bf16270aeb4fdcdc9ff.pdf ER -