Application of ANN and SVM for prediction nutrients in rivers

Abstract

This paper presents the results of predicting nutrients in rivers on national level by the use of two artificial intelligence methodologies. Artificial neural network (ANN) and support vector machine (SVM) were used to predict annual concentration of nitrate and phosphate in rivers of eleven European countries. For creation of an optimal model of prediction, 23 industrial, economical and agricultural parameters were used for the period from 2000 to 2011. The data from 2000 to 2010 was used for training, while the data for 2011 was used for model validation. Optimization of different parameters of ANN and SVM was conducted in order to obtain the model with the best performances. Results of created models were evaluated by using statistical performances indicator named coefficient of determination (R2). The obtained results showed that ANN has better results in predicting nitrate and phosphate compared to SVM models. These results suggest that ANN model is a promising tool for prediction of nutrients in rivers.