University of Tabriz Water and Soil Science 2008-5133 20 3 2010 10 23 Performance Evaluation of Artificial Neural Networks for Predicting Rivers Water Quality Indices (BOD and DO) in Hamadan Morad Beik River Performance Evaluation of Artificial Neural Networks for Predicting Rivers Water Quality Indices (BOD and DO) in Hamadan Morad Beik River 199 210 1342 FA E Olyaie H Banejad MT Samadi AR Rahmani MH Saghi Journal Article 2014 05 12 One of the important factor for development in each region is the availability of appropriate water <br />resources. In addition to water quantity quality is also of great importance. The aim of this study is <br />to medel the qualitative indices (BOD, DO) of river water using multi-layer perceptron neural <br />network. In this paper, the information and data from Morad Beik river of hamadan including 10 <br />monthly parameters of water quality in a one-year period and at six stations were used to predict <br />biological exygen demand (BOD) and dissolved oxygen (DO), as indices affecting water quality. <br />Efficiency of the neural network model was evaluated by some statistical criteria including <br />correlation coefficient (R), root mean square error (RMSE) and mean absolute error (MAE). In the <br />optimum structure of neural network the correlations coefficient for BOD and DO were 0.986 and <br />0.969, and root mean square errors were 8.42 and 0.84 respectively. The results indicated the ability <br />of multi-layers perceptron neural network as a suitable technique for simulating changes in BOD <br />and DO indices. One of the important factor for development in each region is the availability of appropriate water <br />resources. In addition to water quantity quality is also of great importance. The aim of this study is <br />to medel the qualitative indices (BOD, DO) of river water using multi-layer perceptron neural <br />network. In this paper, the information and data from Morad Beik river of hamadan including 10 <br />monthly parameters of water quality in a one-year period and at six stations were used to predict <br />biological exygen demand (BOD) and dissolved oxygen (DO), as indices affecting water quality. <br />Efficiency of the neural network model was evaluated by some statistical criteria including <br />correlation coefficient (R), root mean square error (RMSE) and mean absolute error (MAE). In the <br />optimum structure of neural network the correlations coefficient for BOD and DO were 0.986 and <br />0.969, and root mean square errors were 8.42 and 0.84 respectively. The results indicated the ability <br />of multi-layers perceptron neural network as a suitable technique for simulating changes in BOD <br />and DO indices. https://water-soil.tabrizu.ac.ir/article_1342_6849804b0d71bebf5a687d876fc2f3b4.pdf