Estimation of river flow by artificial neural networks and identification of input vectors susceptible to producing unreliable flow estimates

Reliable river flow estimates are crucial for appropriate water resources planning and management. River flow forecasting can be conducted by conceptual or physical models, or data-driven black box models. Development of physically-based models requires an understanding of ail the physical processes which impact a natural process and the interactions among them. Since identification of the relationships among these physical processes is very difficult, data-driven approaches have recently been utilized in hydrological modeling. Artificial neural networks are one of the widely used data-driven approaches for modeling hydrological processes. In this study, estimation of future monthly river flows for Guvenc River, Ankara is conducted using various artificial neural network models. Success of artificial neural network models relies on the availability of adequate data sets. A direct mapping from inputs to outputs without consideration of the complex relationships among the dependent and independent variables of the hydrological process is identified. In this study, past precipitation, river flow data, and the associated month are used to predict future river flows for Guvenc River. Impacts of various input patterns, number of training cycles, and initial values assigned to the weights of the connections are investigated. One of the major weaknesses of artificial neural networks is that they may fail to generate good estimates for extreme events, i.e. events that do not occur at all or often enough in the training data set. It is very important to be able to identify such unlikely events. A fuzzy c-means algorithm is used in this study to cluster the training and validation input vectors into regular and extreme events so that the user will have an idea about the risk of the artificial neural network model to generate unreliable results.


Modelling the temporal variation in snow-covered area derived from satellite images for simulating/forecasting of snowmelt runoff in Turkey
Tekeli, AE; Akyurek, Z; Sensoy, A; Sorman, AA; Sorman, U (Informa UK Limited, 2005-08-01)
Monitoring the change of snow-covered area (SCA) in a basin is vitally important for optimum operation of water resources, where the main contribution comes from snowmelt. A methodology for obtaining the depletion pattern of SCA, which is based on satellite image observations where mean daily air temperature is used, is applied for the 1997 water year and tested for the 1998 water year. The study is performed at the Upper Euphrates River basin in Turkey (10 216 km(2)). The major melting period in this basin...
Evaluation of performance and optimum valve settings for pressure management using forecasted daily demand curves by artificial neural networks
Yıldız, Evren; Merzi, Nuri; Department of Civil Engineering (2011)
For the appropriate operation and correct short term planning, daily demand curve (DDC) of municipal water distribution networks should be forecasted beforehand. For that purpose, artificial neural networks (ANN) is used as a new method. The proposed approach employs already recorded DDCs extracted from the database of ASKI (Ankara Water Authority) SCADA center and related independent parameters such as temperature and relative humidity obtained from DMI (State Meteorological Institute). In this study, a co...
Alternative solutions for long missing streamflow data for sustainable water resources management
Mesta, Buket; Akgün, Ömer Burak; Kentel Erdoğan, Elçin (Informa UK Limited, 2020-08-01)
Sustainable water resources management requires long time series of streamflow data. In this study, a Takagi-Sugeno fuzzy rule-based (FRB) model is developed to reconstruct long periods of missing daily streamflow data which is a common problem in developing countries. The FRB model uses observations of neighbouring stream gauges, and thus is advantageous regarding data and time requirement compared to physical models. With the proper set of inputs, the FRB model provides better estimates than the hydrologi...
Modeling biogeochemical processes in subterranean estuaries: Effect of flow dynamics and redox conditions on submarine groundwater discharge of nutrients
Spiteri, Claudette; Slomp, Caroline P.; Tuncay, Kağan; Meile, Christof (American Geophysical Union (AGU), 2008-02-22)
[1] A two-dimensional density-dependent reactive transport model, which couples groundwater flow and biogeochemical reactions, is used to investigate the fate of nutrients (NO(3)(-), NH(4)(+), and PO(4)) in idealized subterranean estuaries representing four end-members of oxic/anoxic aquifer and seawater redox conditions. Results from the simplified model representations show that the prevalent flow characteristics and redox conditions in the freshwater-seawater mixing zone determine the extent of nutrient ...
A process-based diagnostic approach to model evaluation: Application to the NWS distributed hydrologic model
Yılmaz, Koray Kamil; Wagener, Thorsten (American Geophysical Union (AGU), 2008-09-11)
Distributed hydrological models have the potential to provide improved streamflow forecasts along the entire channel network, while also simulating the spatial dynamics of evapotranspiration, soil moisture content, water quality, soil erosion, and land use change impacts. However, they are perceived as being difficult to parameterize and evaluate, thus translating into significant predictive uncertainty in the model results. Although a priori parameter estimates derived from observable watershed characteris...
Citation Formats
E. Kentel Erdoğan, “Estimation of river flow by artificial neural networks and identification of input vectors susceptible to producing unreliable flow estimates,” JOURNAL OF HYDROLOGY, pp. 481–488, 2009, Accessed: 00, 2020. [Online]. Available: