کاربرد شبکه‌ عصبی موجک در تخمین دمای متوسط هوا شهرستان ساری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار گروه مهندسی آب، دانشگاه لرستان

2 دانشجوی دکترای سازه های آبی

چکیده

دمای هوا که در ایستگاه‌های هواشناسی استاندارد اندازه‌گیری می‌شود یکی از توصیف‌کننده‌های اصلی وضعیت محیط زمین است. بنابراین برآورد و تخمین دقیق دمای متوسط روزانه در هر منطقه یکی از پیش­نیازهای مهم برای برنامه‌ریزی کشاورزی و نیز مدیریت منابع آب می‌باشد که به روش‌های مختلفی همچون مدل‌های تجربی، نیمه تجربی و هوشمند قابل انجام است. در این پژوهش کاربرد شبکه عصبی موجک به منظور برآورد متوسط دمای روزانه هوا در ایستگاه ساری مورد بررسی و ارزیابی قرار گرفته و کارایی آن  با مدل شبکه عصبی مصنوعی مقایسه گردید. جهت مدل‌سازی از داده‌های دمانگار ایستگاه هواشناسی ساری واقع در استان مازندران استفاده شد. پارامتر رطوبت نسبی، دمای بیشینه، دمای کمینه، سرعت باد و تبخیر در مقیاس زمانی روزانه در طی سال آبی (1382-1392) بعنوان ورودی شبکه و دمای متوسط روزانه هوا به عنوان خروجی شبکه انتخاب گردید. معیارهای ضریب همبستگی، ریشه میانگین مربعات خطا و ضریب نش ساتکلیف برای ارزیابی و مقایسه عملکرد مدل‌ها مورداستفاده قرار گرفت. مقایسه نتایج نشان داد مدل شبکه عصبی موجک عملکرد بهتری نسبت به مدل شبکه عصبی مصنوعی در مدل‌سازی دارد، بگونه ای که مدل شبکه عصبی موجک با بالاترین ضریب همبستگی (999/0)، ریشه میانگین مربعات خطا (001/0) و نیز بیشترین معیار نش ساتکلیف (998/0) در مرحله صحت سنجی در اولویت قرار گرفت. در مجموع نتایج نشان داد مدل شبکه عصبی موجک در تخمین بیشتر مقادیر دقت بالایی از خود نشان داده است.

کلیدواژه‌ها


عنوان مقاله [English]

Application of Wavelet Neural Network for Estimation of Mean Daily Temperature in Sari Area

نویسندگان [English]

  • Babak Shahinejad 1
  • reza dehghani 2
1 Assistant Professor Department of Water Engineering
2 PHD student water structures
چکیده [English]

Introduction
The average air temperature prediction great importance in the field of water resources management, agriculture, water and a lot of things everyday. Air temperature is also one of the components of the hydrological and ecological models is input, as well as land evaluation models. On the other hand, because the weather has a significant impact on social life, and individual centers worldwide scientific research on climate issues raised as a priority, nearly as fundamental. Quantitative prediction of air temperature is one of the most important elements in managing and programming of surface water resources, especially take suitable decisions in occurrence of drought event.
Objective: In this study, recorded data sets in Sari Station (located in Mazandaran province), were used to investigate the precision of different Air temperature prediction models. The wavelet neural network model and artificial neural network models selected for modeling of daily Air temperature, and the results were compared to examine the accuracy of studied models.  Methods: Daily Air temperature were selected and observed of this basin in the Sari station that were applied for calibration and validation of models. For this purpose, at first 80 % of daily Air temperature data (2002-2010) were selected to calibrate selected models, and 20 % of data (2010-2012) were used to validate models. For modeling, meteorological data from sari synoptic station (Mazandaran Province) were used. Humidity parameters, maximum temperature, minimum temperature, wind speed and evaporation in daily time scale during a ten year time period (2002-2012) are inputs of the network, and mean temperature as network output is selected. Wavenet called wavelet-based neural network which combined with wavelet theory and neural networks have been created.It also have supportive of the benefits and features of neural networks and charm and flexibility and strong mathematical foundations and analysis of multi-scale wavelet . a combination of wavelet theory with neural network concepts to the creation of wavelet neural network and feedforward neural shock can be a good alternative for estimating approximate nonlinear functions .Feedforward neural network with sigmoid activation function is in the hidden layer While at the nerve shocked wavelet ,wavelet functions as activation function of hidden layer feedforward networks are considered, In both these networks and scale wavelet transformation parameters are optimized with their weight.
Artificial neural networks inspired by the brain's information processing systems, design and emerged intoTo help the learning process and with the use of processors called neurons trying to understand the inherent relationships between data mapping between input space and optimal space. Hidden layer or layers, the information received from the input layer and output layer are the processing and disposal.Based on the artificial neural network structure, its major features high processing speed, the ability to learn the pattern,The ability to extend the model after learning, flexibility against unwanted errorsNo disruption to error on the part of the connection due to weight distribution network. The first practical application of synthetic networks with the introduction of Multilayer Perceptron network wasConsultants. for training this network back propagation algorithm is used.The basis of this algorithm is based on error correction learning ruleThat consists of two main routes.By adjusting the parameters in the MLP model error signal and input signal occurs.Determine the number of layers and neurons is the most important issues in simulation with artificial neural network. Criteria of correlation coefficient, root mean square error and Nash Sutcliff coefficient were used to evaluate and compare the performance of models. . Coefficient of correlation, root mean square error and Nash Sutcliffe coefficient was used to evaluate and compare the performance of the models.
Results: Results showed that all two models (in a structure), consisting gives better than results any other structure. And also, based on results according to the evaluation criterion, the models was used to wavelet neural network model, most accurate (R=0.999), and the lowest root mean square error (RMSE=0.001) and the highest standards Nash Sutcliffe (NS=0.998) the validation phase is capable.
Conclusions: Finally, wavelet neural network model outperformed the artificial neural network. So, wavelet neural network model can be effective in forecasting the daily Air temperature and in turn facilitate the development and implementation of Prevent drought will be useful. , and the use of wavelet neural network model can estimate the drought effectively, Which in return facilitates the development and implementation of management strategies to avoid drought.

کلیدواژه‌ها [English]

  • Estimation
  • Air Temperature
  • Artifical Neural Network
  • Wavelet Neural Network
  • Sari
  1.  

    1.       Abhishek, K., Singh, M. P., Ghosh, S.,  and  A. Anand,  2012, Weather Forecasting Model using Artificial Neural Network,  Journal of Procedia Technology, Vol.4, No.4, pp. 311-318

    1. Banejad, H., Kamali, M., Amir Moradi, K., and A. Oliaei, 2013, Forecasting Some of the Qualitative Parameters of Rivers Using Wavelet Artificial Neural Network Hybrid (W-ANN) Model (Case of study: Jajroud River of Tehran and Gharaso River of Kermanshah), Journal of Health and Environment, Vol. 6, No.3, pp. 277-294
    2. Bani Habib, M. A., Rahimi Khob, A., and A. Arabi, 2007, The maximum daily temperature estimation using artificial neural networks and satellite images Nova (Case Study: Orumiyeh Lake basin), Journal of Environmental Science and Technology, Vol.9, No.3, pp.185-202
    3. Emamifar, S., Rahimi Khob, A.,  and A. A. Nourozi, 2014, Evaluation of the M5 model tree and artificial neural network to estimate the average daily air temperature on land surface temperature data from MODIS sensor, Iran Soil and Water Research, Vol.45, No.4,pp.423-433
    4. Ghorbani, M. A., Shiri, J., and H. Kazemi, 2009, Estimated maximum, medium and minimum air temperatures in Tabriz using artificial intelligence, Journal of Soil and Water, Vol.20, No.3, pp.87-104
    5. Habibi, M., Rezaei Pajand, H., and M. Farzandi, 2008, Model to estimate the average daily temperature in arid and semi-arid Iran, Iran Water Resources Research, Vol.4, No.1, pp.70-74
    6. Hornik, K, 1998, Multilayer feed-forward networks are universal approximators, Neural Networks , Vol.2, No.5, pp. 359–366.
    7. Hosseini, S. A, 2009, Estimation of maximum temperatures in Ardabil city by using artificial neural network theory, Researcher University of Ardabil, Natural Geography Department.
    8. Karthika, B.S.,  and P. C. Deka,  2016,  Modeling of Air Temperature using ANFIS by Wavelet Refined Parameters, International Journal of Intelligent Systems and Applications, Vol.8,  No.1, pp.25-34
    9. Kaveh, A., and A. Iran Manesh, 2005, Artificial Neural Networks in Structural Optimization, Third Edition. Publications Building and Housing Research Center.
    10. Kisi, O., Karahan, M.,  and Z. Sen,  2006, River suspended sediment modeling using fuzzy logic approach ,Hydrol Process, Vol.20, No.2, pp. 4351-4362.
    11. Nagy, H.,  Watanabe, K.,  and  M. Hirano, 2002, Prediction of sediment load concentration in rivers using artificial neural network model, Journal of Hydraulics Engineering, Vol.128, No.4, pp.558-559.
    12. Nourani, V.,  Kisi,  Ö.,  and  M. Komasi,  2011, Two hybrid artificial intelligence approaches for modeling rainfall–runoff process, Journal of Hydrology, Vol.402, No.2, pp.41–59.
    13. Nourani, V., Alami,  M. T.,   and M. H. Aminfar, 2009, A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation, Engineering Applications of Artificial Intelligence, Vol.22, No.2,pp.466–472.
      1. Okkan,U, 2012, Wavelet neural network model for reservoir inflow prediction, journal of Scientia Iranica, Vol.4, No.2, pp.1445–1455
      2. Safavi, A.A., and J. A.  Romagnoli, 1997, Application of wavelet-based neural networks to modelling and optimisation of an experimental distillation column, (IFAC Journal of) Engineering Applications of Artificial Intelligence, Vol.10, No.3, pp. 301-313
      3. Safshekan, F., Pir Moradian, N., and R. A.  Sharifian, 2011, Simulation of rainfall-runoff hydrograph according to the time pattern of rainfall and the use of artificial neural network in the famous Kasilian Basin. Engineering Sciences Iranian Journal of Watershed Management, Vol.5, No.15, pp. 1-10
      4. Salahi, B., Hosseini, S. A., Shanghi Moghanlo, H., and B.  Sobhani, 2010, Maximum temperatures predicted using artificial neural network model: A Case Study of Ardabil city. Journal of Geographical Research,Vol.25, No.3, pp.57-78
      5. Sharifi, S.S.,  Rezaverdinejad, V.,  and V. Nourani,  2016, Estimation of Daily Global Solar Radiation using Wavelet Regression, ANN, GEP and Empirical Models: A Comparative Study of Selected Temperature-Based Approaches, Journal of Atmospheric and Solar-Terrestrial Physics, Vol,149. No.3, pp.131-145
      6. Teshneh Lab, M.,  and M. Monshi, 2003, Prediction of meteorological parameters using fuzzy neural network based on the education parameters Tully, third and first regional Conference on Climate Change Conference. University of Esfahan
      7. Tokar, A.S., and  P. A. Johnson, 1999, Rainfall- Runoff modeling using artificial neuralnetworks, Journal of Hydrology Engineering, Vol.3, No.2, pp.232-239.
      8. Venkata Ramana, R.,  Krishna, B., Kumar, S. R.,  and N. G. Pandey, 2013, Monthly Rainfall Prediction Using Wavelet Neural Network Analysis, Water Resources Management, Vol.27, No.10, pp.3697-3711
      9. Wang, D.,  Safavi, A. A., and  J. A. Romagnoli,  2000, Wavelet-based adaptive robust M-estimator for non-linear system identification, AIChE Journal, Vol.46, No.8, pp.1607-1615
      10. Wang, W.,  and J. Ding, 2003, Wavelet Network Model and Its Application to the Prediction of Hydrology, Nature and Science, Vol.1, No.1, pp.67-71.
      11. Zhu, Y. M.,  Lu, X.X.,  and  Y. Zhou,  2007, Suspended sediment flux modeling with artificial neural network: An example of the longchuanjiang river in the upper yangtze catchment, Geomorphology, Vol.84, No.4, pp.111-125.