Rainfall is considered as one of the most difficult and complex elements of the
hydrological cycle, to understand and model, due to the complexity of air operations that
generate rain. The importance of research comes from the direct relationship b
etween the
rainfall amount and economic & social activities of the population, planning scopes of the
water resources management, particularly with respect to the agricultural development.
The research aims to highlight the rainfall amounts in Tartous station which is
located in the southern part of the Syrian coast, and applying one model of Box-Jenkins
models for the purpose of predicting future rainfall amounts. Multiple Arima models have
been tested. The results showed that the model SARIMA (3,0,4) was the best one. Data
were divided into 43 years to build the model and eight years to test it. The test results
gave high accuracy in the performance, and the model was used to predict the values of
annual rainfall for the next twenty years.
Due to the importance of climate changes and their strong and increasing influences
on different human and ecological systems, It is necessary to study and understand these
changes. This research aims to determine the direction and magnitude of the
change in
temperatures and rainfall trend during 1978-2011 in Latakia, Kasaab and Slenfeh. The
study has been done through the analysis of annual, seasonal, and monthly rainfall amount
and temperature average, which showed a significant increasing in the average annual
temperature in the three regions and significant seasonally increasing except for Winter in
Latakia and Slenfeh, Autumn in Latakia. But the annual rainfall changes were nonsignificant,
while seasonally rainfall increased significantly in Slenfeh Winter and
decreased in Kasaab Winter. After dividing the entire study duration into two equal periods
1978-1995, 1995-2011 and comparing the second period with the first one, we found a
significant increasing in the average annual temperature in the three regions,
non- significant in the annual and seasonal rainfall changes. The highest significant in
seasonal temperature in Latakia, Kasaab and Slenfeh reached +1.5, +2.9, +1.8 during
September, August، and May respectively. While the annual drought showed increased
trend in Latakia and kasaab and decreased one in Slenfeh.
Due to the importance of water, and the increasing of demand at the present time due
to the tremendous development in all spheres of economic and social life, and as the
evaluation, planning and management of water sources, one of the important top
ics in
human life, especially in areas with scarce rainfall or where rainfall distribution is poor or
irregular so cannot be used for different purposes.
From here, the importance of the research in forecasting rainfall in the Husn
Suleiman station, comes, and to achieve this goal the data of time series for the average
annual rainfall precipitation been used in Husn Suleiman station which located in the
province of Tartous on longitude 36 ° 15 ' andlatitude 34 ° 56', for the period between
1959-2011,
The methodology of "Box – Jenkins" been used in the study, this methodology
relies on finding future forecasts from original data series.
Also,the applications “MINITAB, EXCEL” have been used in the statistical side and
the preparation of the study results.
As a result, the study found that rainfall value in the 'Husn Suleiman station'
decreasing, this decline amounted to 3.7 mm per year during the monitoring period.
Also, the appropriate (ARIMA) model for the series was build after it passed the
various statistical tests are required, and founded that ARIMA(1,0,0) model is a good
representation of the data and the ARIMA(4,1,5) model is the right model to forecast
future rainfall.
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).
Weather forecasting (especially rainfall) is one of the most important and challenging
operational tasks carried out by meteorological services all over the world. Itis furthermore
a complicated procedure that requires multiple specialized fields o
f expertise.
In this paper, a model based on artificial neural networks (ANNs) and wavelet Transform
is proposed as tool to predict consecutive monthly rainfalls (1933-2009) taken of
Homs Meteorological Station on accounts of the preceding events of rainfall data.
The feed-forward neural network with back-propagation Algorithm is used in the
learning and forecasting, where the time series of rain that detailed transactions and the
approximate three levels of analysis using a Discrete wavelet transform (DWT).
The study found that the neural network WNN structured )5-8-8-8-1(, able to predict
the monthly rainfall in Homs station on the long-term correlation of determination and root
mean squared-errors (0.98, 7.74mm), respectively.
Wavelet Transform technique provides a useful feature based on the analysis of the
data, which improves the performance of the model and applied this technique in ANNmodels
for rain because it is simple, as this technique can be applied to other models.
The Alsafarqieh watershed is located on the western slopes of the coastal mountain range,
Its area is 132.58 km2, It forms a part of the Alros river basin, The river starts at a height of
1200 m, A group of tributaries meet and form the Alros River
, which flows into the
Mediterranean Sea. Salaheddin Dam was constructed to store 10 MCM on the riverbed at
the intersection of the Qurdaha River with the Shehada River. The study aims to determine
the rainfall- runoff relationship in The Alsafarqieh watershed. The solution depends on the
statistical analysis of precipitation and runoff data. Then the study found the mean annual
precipitation is 159.6 MCM/year, and the mean annual flow into the Salaheddin lake was
9.4 MCM during the study period (2010-2012), so the runoff coefficient is 0.06. This
indicates a significant water loss. A mathematical equation to predict the runoff quantities
depending on the values of precipitation, has been concluded. This is important to study
water projects for water storage and flood prevention.
