Comparison of the performance of stochastic models in forecasting daily dissolved oxygen data in dam-Lake Thesaurus

Abstract

This study presents the development and validation of three different stochastic models on the basis of (a) their efficiency to forecast and (b) their ability to utilize auxiliary environmental information. The three models are ARIMA models, transfer function (TF) models, and artificial neural networks. Four-year (2004–2007) daily measurements of dissolved oxygen at four different depths (1, 20, 40 and 70 m) of Thesaurus dam-lake in River Nestos, Eastern Macedonia, Greece, were used to obtain the best models for these time series. For the final selected models, four statistical criteria (mean square error (MSE), roοt-mean-square error (RMSE), MAPE, and NSC) were used to evaluate the accuracy of the forecast and to compare the forecasting ability for one step ahead of each approach. For 1- and 20-m depth, the best forecast is obtained by ARIMA models, while for the 40-m depth, TF models gives the best forecast. Finally for the 70-m depth, according to the MSE, RMSE, and NSC statistical criteria, ARIMA models are the best, while for the MAPE, TF models are the best. Further research could be carried out concerning on (a) the comparison of these models with other forecasting ones, (b) the application of forecasting for more than one step ahead (m = 2, 3, …), and (c) the implementation of such models in other deep lakes and the assessment of the comparison between them. © 2016 Balaban Desalination Publications. All rights reserved.