Evaporation forms one of the hydrology cycle elements that it's hard to measure its actual amounts in the field conditions, so it’s estimated by calculations of experimental relations, which depend on climatic elements data. So the research goal is t
o build a mathematical model to estimate monthly evaporation amount in plain area of Syrian Coast, using Artificial Neural Network (ANN), and depending on dry air temperature, and produce comparison study between the results of network and other models. The mathematical model was built by the (NN-tool box), which is one of the v tools. A multilayer ANN architecture of error Back-propagation algorithm was built. The suitable training algorithms, number of hidden layers, number of neurons in each hidden layer, were determined.
The results showed that the ANN (1-9-1) was the best model with MSE of 0.0032 for validation group, using Transfer Function Logsigmoid and Linear in hidden and output layers, respectively.
A comparison model for the results obtained from the proposed ANN with EVANOV model by using SIMULINK technique was developed. This indicated that the ANN using temperature only gives results more accurate than EVANOV equation in determining evaporation.
Evapotranspiration forms one of the hydrology cycle elements that it's hard to
measure its actual amounts in the field conditions, so it’s estimated by calculations of
experimental relations that depend on climatic elements data. These estimations
include
different errors because of approximation processes. The research goals to accurate
estimation of the monthly reference evapotranspiration amount in Safita area (on the east
coast of the Mediterranean Sea), and the research depends on the technique of Artificial
Neural Network (ANN), and the mathematical model was built by the
(nftool), which is one of the Matlab tools, depending on monthly air temperature and
relative humidity data which were taken from Safita meteorological station, and the data of
monthly pan evaporation (Class A pan) has been used, after modifying its results, for the
purpose of checking the performance accuracy of the network, by using Simulink
technique, which is existing in Matlab Programs Package. The results of the research
verify that a multi-layer ANN of error Back-propagation algorithm gives a good result in
estimating monthly reference Evapo-transpiration for the used data group.
The evaluation of surface water resources is a necessary input to solving water
management problems, which includes finding a relationship between precipitation and
runoff, and this relationship is a high degree of complexity. The rain of the most
important
factors that greatly effect on rivers discharge, and process to prediction of these flows must
take this factor into account, and much of the attention and study, artificial neural networks
and is considered one of the most modern methods in terms of accuracy results in linking
these multiple factors and highly complex. In order to predict the runoff contained daily to
Lake Dam Tishreen 16 in Latakia, the subject of our research, the application of different
models of artificial neural networks (ANN), was the previous input flows and rain.
Divided the data set for the period between (2006-2012) into two sets: training and
test, has been processing the data before using them as inputs to the neural network using
Discrete Wavelet Transform technique, to get rid of the maximum values and the values of
zero, where t the analysis of time series at three levels of accuracy before they are used
sub- series resulting as inputs to the Feed Forward ANN that depend back-propagation
algorithm for training.
The results indicated that with the structural neural network (1-2-6) Wavelet-ANN
model, are the best in the representation of the characteristics studied and best able to
predict runoff daily contained to Lake Dam Tishreen 16 for a day in advance, where he
reached the correlation coefficient the root of the mean of squared-errors (R2 = 0.96,
RMSE = 1.97m3 / sec), respectively.
