The effects of climate change on water resources management have drawn worldwide attention. Water quality predictions that are both reliable and precise are critical for an effective water resources management. Although nonlinear biological and chemical processes occurring in a lake make prediction complex, advanced techniques are needed to develop reliable models and effective management systems. Artificial intelligence (AI) is one of the most recent methods for modeling complex structures. The applications of machine learning (ML), as a part of AI, in hydrology and water resources management have been increasing in recent years. In this paper, the ability of deep neural networks (DNNs) to predict the quality parameter of dissolved oxygen (DO), in Lake Kastoria, Greece, is tested. The available dataset from 11 November 2015, to 15 March 2018, on an hourly basis, from four telemetric stations located in the study area consists of (1) Chl-a (μg/L), (2) pH, (3) temperature—Tw (°C), (4) conductivity (μS/cm), (5) turbidity (NTU), (6) ammonia (NH₄, mg/L), (7) nitrate nitrogen (N–NO₃, mg/L), and (8) dissolved oxygen (DO) (mg/L). Feed-forward deep neural networks (FF-DNNs) of DO, with different structures, are tested for all stations. All the well-trained DNNs give satisfactory results. The optimal selected FF-DNNs of DO for each station with a high efficiency (NSE > 0.89 for optimal selected structures/station) constitute a good choice for modeling dissolved oxygen. Moreover, they provide information in real time and comprise a powerful decision support system (DSS) for preventing accidental and emergency conditions that may arise from both natural and anthropogenic hazards.

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.