Evapotranspiration is an important component of the
hydrologic cycle, and the accurate prediction of this parameter is
very important for many water resources applications. Thus, the
aim of this study is prediction of monthly reference
evapotranspiration using Artificial Neural Networks (ANNs) and
fuzzy inference system (FIS).
This study includes the possibility of using Artificial neural
networks (ANNs) with back-propagation algorithm in a short-term
prediction of water level in Qattinah Lake. The data used are the
water level data in the lake and rainfall data for the period from
1/5/2007 to 28/2/2005. 2009).
Rainfall is highly non-linear and complicated phenomena, which require nonlinear
mathematical modeling and simulation for accurate prediction. This study
comparing the performance of the prediction of one-day-ahead, where Two
Feed Forward Neural N
etwork FFNN models were developed and implemented
to predict the rainfall on daily for three months (December, January, February).
These models are Artificial Neural Network traditional (ANN) model and artificial
neural network technique combined with wavelet decomposition (Wavelet-
Neural) According to two different methods to build a model using two types of
wavelets of Daubechies family (db2, db5). In order to compare the performance
of the models in their ability to predict the rains on short-term (for one and two
and three-days-ahead) the last months of the period of study, used some statistical
standards, These parameters include the Root Mean Square Error RMSE,
Coefficient Of Correlation (R).
the aim of this study is
determination of the most influential climatic factors in the rainfall
runoff relationship in Al-Kabir Al-shimalee river using artificial
neural networks. The inputs included Precipitation, runoff, in
different delays, in
addition on لاclimate factor in each network, to
determinate the best model.
Evaporation is a major meteorological component of the hydrologic cycle, and it
plays an influential role in the development and management of water resources. The aim
of this study is to predict of the monthly pan evaporation in Homs meteostation
using
Artificial Neural Networks (ANNs), which based on monthly air temperature and relative
humidity data only as inputs, and monthly pan evaporation as output of the network. The
network was trained and verified using a back-propagation algorithm with different
learning methods, number of processing elements in the hidden layer(s), and the number of
hidden layers. Results shown good ability of (2-10-1) ANN to predict of monthly pan
evaporation with total correlation coefficient equals 96.786 % and root mean square error
equals 24.52 mm/month for the total data set. This study recommends using the artificial
neural networks approach to identify the most effective parameters to predict evaporation.
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.
