Do you want to publish a course? Click here

Using Neural Networks models with Wavelet transform technology To Predict Flows Coming into 16 Tishreen Lake

استخدام الشبكات العصبية الصنعية مع تقنية التحويل المويجي للتنبؤ بالتدفق اليومي الوارد إلى بحيرة سد 16 تشرين

2108   0   105   0 ( 0 )
 Publication date 2017
and research's language is العربية
 Created by Shamra Editor




Ask ChatGPT about the research

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.


Artificial intelligence review:
Research summary
تتناول هذه الدراسة استخدام الشبكات العصبية الاصطناعية وتقنية التحويل المويجي للتنبؤ بالتدفق اليومي الوارد إلى بحيرة سد 16 تشرين في اللاذقية، سوريا. تم تقسيم البيانات للفترة من 2006 إلى 2012 إلى مجموعتين: تدريب واختبار. استخدمت تقنية التحويل المويجي المتقطع لمعالجة البيانات قبل إدخالها إلى الشبكة العصبية، وذلك للتخلص من مشاكل القيم العظمى والصغرى. تم تحليل السلاسل الزمنية إلى ثلاثة مستويات من الدقة واستخدام السلاسل الفرعية الناتجة كمدخلات للشبكة العصبية أمامية التغذية التي تعتمد على خوارزمية الانتشار العكسي لتدريبها. أظهرت النتائج أن النموذج Wavelet-ANN ذو الهيكلية (1-2-6) هو الأفضل في تمثيل الظاهرة المدروسة والتنبؤ بالجريان اليومي الوارد إلى بحيرة سد 16 تشرين ليوم واحد قادم، حيث بلغ معامل الارتباط 0.96 وجذر مربع متوسط الخطأ 1.97 م³/ثانية. تشير الدراسة إلى أن استخدام الشبكات العصبية الاصطناعية مع تقنية التحويل المويجي يمكن أن يحسن من دقة التنبؤ بالتدفقات اليومية، مما يسهم في تحسين إدارة الموارد المائية والتخطيط لمواجهة الفيضانات والجفاف.
Critical review
تعتبر هذه الدراسة خطوة مهمة في مجال استخدام التقنيات الحديثة لتحسين دقة التنبؤ بالتدفقات المائية، إلا أن هناك بعض النقاط التي يمكن تحسينها. أولاً، قد يكون من المفيد توسيع فترة البيانات المستخدمة لتشمل سنوات إضافية، مما قد يعزز من دقة النموذج. ثانياً، يمكن استكشاف تأثير عوامل إضافية مثل التبخر ورطوبة التربة على دقة التنبؤ. ثالثاً، يمكن مقارنة أداء النموذج المقترح مع نماذج أخرى مثل الشبكات العصبية العميقة أو نماذج التعلم الآلي الأخرى لمعرفة مدى تفوق النموذج الحالي. وأخيراً، قد يكون من المفيد تطبيق النموذج على مناطق أخرى ذات خصائص هيدرولوجية مختلفة للتحقق من عمومية النتائج.
Questions related to the research
  1. ما هي الفترة الزمنية التي تم استخدام بياناتها في هذه الدراسة؟

    تم استخدام بيانات الفترة من عام 2006 إلى عام 2012 في هذه الدراسة.

  2. ما هي التقنية المستخدمة لمعالجة البيانات قبل إدخالها إلى الشبكة العصبية؟

    تم استخدام تقنية التحويل المويجي المتقطع لمعالجة البيانات قبل إدخالها إلى الشبكة العصبية.

  3. ما هو الهيكل الأفضل للنموذج وفقاً للدراسة؟

    النموذج Wavelet-ANN ذو الهيكلية (1-2-6) هو الأفضل وفقاً للدراسة.

  4. ما هي القيم التي تم تحقيقها لمعامل الارتباط وجذر مربع متوسط الخطأ؟

    بلغ معامل الارتباط 0.96 وجذر مربع متوسط الخطأ 1.97 م³/ثانية.


References used
ADAMOWSKI, J, F. River flow forecasting using wavelet and cross-wavelet transform models. Hydrological Processes, 22, 2008, 4877-4891
BOX, G, E, P; JENKINS, G. M .Time Series Analysis: Forecasting and Control. Holden Day Inc; San Francisco, 1976
JAIN, A; SRINIVASULU, S. Development of Effective and Efficient Rainfall- Runoff Models Using Integration of Deterministic, Real-Coded Genetic Algorithms and Artificial Neural Network Techniques. Water Resources Research, Vol. 40, No. 4, 2004, Article ID: W04302. doi:10.1029/2003WR002355
rate research

Read More

The research aims to determine the water Quality Index for the Lake of 16 Tishreen Dam. To achieve this aim, we have carried out different periodical physic-chemical and bacterial measurements on the lake water. The samples were taken at five sites along the lake for a period of one complete year. The indicators that have been measured are: Temperature, Turbidity, PH, EC, DO, BOD5, NO3, NO2, NH4 ,PO4, F.C. Measurement results were represented diagrammatically, and compared with the Syrian Specification Standards for portable Water. The lake was classed according to these Indices: Malays quality index, Canadian Indices (NSFWQI), (NEWWQI). The Lake was Classed according to these indices as following: from third grade at all locations (Malays Index), from second grade at the middle lake and from a third grade to all other locations (NSFWQI), and from second grade at all locations (NEWWQI). According to this indices the water is not good for drinking and needs treatment. The Productivity of the lake was determined. The Lake is Eutrophic according to TN,TP in the middle but Hypertrophic according to TN,TP in all other locations.
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 study included 132 Free – living fish in Lake of 16 Tishreen Dam, collected randomly during the period from 22/11/2011 until 22/10/2012, on average once a month, for detecting the infection of parasitic copepoda, and determine the distribution rate, and their effect on the fish productivity.
The study included 144 Free – living fish from the Lake of 16 Tishreen Dam, collected randomly during the period from 12/2011 until 11/2012, on monthly basis to detect the infection with Epistylis sp. and determine its distribution rate. Fish sam ples were: Cyprinus carpio L., Varicorhinus damascinus, Garra rufus, Tilapia zilli, and Liza abu. Tilapia zilli was the most prevalent in the lake of 16 Tishreen Dam. The study revealed fish infection with Epistylis sp. on free – living fish in the Lake, with a total infection rate 22.22 % , mainly on Tilapia zillii (29.70 %) and then on mullet (2%);No infection with Epistylis sp. Was recorded on the other fish species. The infection with this ecto Epistylis sp. was recorded for the first time in Syria in our study. The infection with Epistylis sp. was located on the skin, fins and gills. The highest infection rate was on the fins ( 42.34 %) , followed by skin (37.46 %) , and then by gills (1.87 %) . The infection with Epistylis sp. had the highest rate in summer ; i.e. during high temperature , low concentration of dissolved oxygen , and slightly high value of BOD. The study showed that, the water of 16 Tishreen Dam is relatively clean.
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.
comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا