تازه های تحقیق
عنوان مقاله [English]
The impact of drought on different parts is not the same. In a situation where different regions of the country have experienced a significant decline in rainfall, its impact on water resources is still unclear or the decline of surface water resources has no effect on agricultural production (Satari et al., 1395).
Increasing or decreasing in hydrological time series can be described by changes in precipitation factors, evaporation, temperature, and the like (Nourani, 1395). Evaporation modeling from the reservoir level is important to predict the evaporation rate from the surface and the amount of water lost through evaporation and evacuated water and to have a proper planning to reduce the amount of this evaporation and its economic estimation. The heavy volume of computations and their time-consuming performance, especially in phenomena such as sudden floods, cause many financial losses and annoyances every year. One of these utilized and intelligent tools is artificial neural network which reaches acceptable output by establishing appropriate relationships between input variables in the shortest possible time and establishes the relationship with the output tool and provides the best possible result to
experts. (Rajaei et al., 2010). In this regard, studies have been conducted in the world, including the study of the effect of different compounds of climatic parameters on the evaporation losses of the dam reservoir (Deswal & Pal, 2008).
- Meteorological data routing nonlinear
Before proceeding to discuss the modeling and selecting the optimal model for the regions under discussion, the best nonlinear fittings are obtained from the parameters affecting evaporation. For the study area, the fitting diagram for temperature data (oC), rainfall (mm), wind speed (Km/h), lake surface area (Km2) and evaporation (mm) were used, which resulted in the results and relationships for each of them.
- Introducing Artificial Neural Network
An artificial neural network consists of three main layers of the input, the hidden (middle layer) and the output layers. The layer where the results of the model analysis are generated and the modeling is done is the output layer of the model (Fig. 1). The middle layer acts as the processor of the model and the processor nodes are at this stage (Traore et al., 2010).
Fig.1 Artificial Neural Network structure with input, output and intermediate (hidden) layers
- Artificial Neural Network Modeling for Minab Dam
In order to use the artificial neural network, data from the Minab Dam was estimated from the data of the years 1998 to 2014 in MATLAB software. The best structures for the neural network are given in Table 1:
Table.1 Error and correlation coefficient obtained by artificial neural network
Neural network structure
- Training data
For modeling of the neural network, 80% of the data was randomly selected by the MATLAB software. One of the most important diagrams used in neural network modeling is the actual values graph and evapotranspiration values using artificial neural network for training data (Fig. 2).
Fig.2 Diagram of observation data and modeling at training stage, ANN [5,5,1]
- Test data
The remaining 20% of the data was also used to test the model obtained by the artificial neural network (Fig. 3).
Fig.3 Diagram of observation data and modeling at testing stage, ANN [5,5,1]
Discussion and conclusion
Evaporation, as one of the natural parameters, has always been of interest to experts and researchers due to the high role that human has in reaching the outflow of water. In this research, we tried to evaluate the accuracy of this model by using the artificial neural network model in estimating evaporation from the lake level of the Minab Dam. In order to investigate the evolution of the evaporation parameters for the 19-year data, the best-fit nonlinear regression was drawn and the general trend of evolution of the effective parameters was studied. For modeling of the evaporation using artificial neural network, 19-year-old statistics between the years 1995 and 2013 were used.
The best structure for estimating evaporation from the level of Minab Dam is selected in this paper. In this structure, the first and second layers have 5 neurons with 1000 replications to get the best result. The statistical coefficients obtained from the analysis using artificial neural network were considered in selecting the best structure. In this structure, the correlation coefficient with the value of 0.8941 had the highest value and the error values of training and testing the data were respectively 0.0011 and 0.0082. After this structures, ANN (3, 7,1), ANN (4,10,1), ANN (4,11,1), ANN (5,3,1) had acceptable correlation coefficient values and error in determining the amount of evaporation from the Minab dam.
- MSc Student, Faculty of New Sciences and Technologies, University of Tehran.