• صفحه اصلی
  • پیش‌بینی خشک‌سالی با بهره‌گیری از مدل ترکیبی ماشین بردار پشتیبان موجکی و شاخص SPI (مطالعه موردی: حوضه دریاچه ارومیه-ایران)

اشتراک گذاری

آدرس مقاله


کد مقاله : JEST-1508-2077 (R1) بازدید : 167 صفحه: 83 - 101

10.22034/jest.2020.9578

نوع مقاله: پژوهشی

پیش‌بینی خشک‌سالی با بهره‌گیری از مدل ترکیبی ماشین بردار پشتیبان موجکی و شاخص SPI (مطالعه موردی: حوضه دریاچه ارومیه-ایران)

محورهای موضوعی : آب و محیط زیست

مهدی کماسی 1 , سروش شرقی 2

1 - عضو هیئت علمی گروه عمران دانشگاه ایت اله بروجردی (ره)
2 - دانشجوی کارشناسی ارشد، مهندسی آب و سازه‌های هیدرولیکی، دانشگاه آیت اله العظمی بروجردی (ره)، بروجرد.

تاریخ دریافت : 1396/06/01 تاریخ پذیرش : 1396/10/06 تاریخ انتشار : 1399/07/01

کلید واژه: مدل ماشین بردار پشتیبان, شاخص SPI, پیش‌بینی خشک‌سالی, حوضه ارومیه, تبدیل موجک,

چکیده مقاله :

زمینه و هدف: خشک‌سالی تهدیدی جدی برای انسان و محیط‌زیست بوده ازاین‌رو یافتن شاخصی جهت پیش بینی این پدیده از اهمیت به سزایی برخوردار است. شاخص بارش استانداردشده (SPI) یک شاخص جامع جهت طبقه‌بندی شدت خشک‌سالی به‌حساب می آید. مدل های هوش مصنوعی کلاسیک از متداول ترین مدل هایی هستند که جهت پیش بینی شاخص SPI مورداستفاده قرارگرفته‌اند. ازآن جایی‌که این مدل ها بر پایه ی ویژگی خودهم بستگی استوار هستند، بنابراین توانایی رصد نمودن سری های زمانی درازمدت و فصلی را دارا نمی باشند. در این پژوهش برای پیش بینی خشک‌سالی از مدل ترکیبی ماشین بردار پشتیبان موجکی و شاخص SPI استفاده‌شده است. روش بررسی: برای این منظور سری زمانی شاخص SPI مربوط به حوضه ارومیه توسط آنالیز موجک به چندین زیر سری با مقیاس های زمانی مختلف تبدیل‌شده و این زیر سری‌های زمانی به‌عنوان ورودی مدل ماشین بردار پشتیبان برای پیش بینی خشک‌سالی در نظر گرفته می شوند. یافته ها: نتایج حاصل از صحت سنجی مدل ها بیان گر آن است که بیش ترین مقدار ضریب تبیین و کم ترین مقدار جذر میانگین مربع خطا برای مدل منفرد ماشین بردار پشتیبان به ترتیب 865/0 و 237/0 و برای مدل ترکیبی ماشین بردار پشتیبان موجکی به ترتیب 954/0 و 056/0 می باشد. بحث و نتیجه گیری: بنابراین مدل ترکیبی ماشین بردار پشتیبان موجکی در مقایسه با مدل منفرد ماشین بردار پشتیبان توانایی به سزایی جهت پیش بینی سری زمانی شاخص SPI و نیز رصد نمودن نقاط بیشینه این سری زمانی به سبب در نظر گرفتن تغییرات فصلی دارا می باشد. از سویی نشان داده شد که این مدل ترکیبی در مقایسه با سایر مدل های خودهم بسته کلاسیک هم چون شبکه عصبی مصنوعی از دقت و کارایی بالاتری برخوردار است.

چکیده انگلیسی:

Background and Objectives: Drought is regarded as a serious threat for people and environment. As a result, finding some indices to forecast the drought is an important issue that needs to be addressed urgently. The appropriate and flexible index for drought classification is the Standardized Precipitation Index (SPI). Artificial intelligence models were commonly used to forecast SPI time series. These models are based on auto regressive property. So, they are not able to monitor the seasonal and long-term patterns in time series. In this study, the Wavelet-Support Vector Machine (WSVM) approach was used for the drought forecasting through employing SPI. Method: In this way, the SPI time series of Urmia Lake watershed was decomposed to multiple frequent time series by wavelet transform; then, these time series were imposed as input data to the Support Vector Machine (SVM) model to forecast the drought. Findings: The results showed that, the maximum value of R2 and minimum value of RMSE indexes for SVM model are 0.865 and 0.237 and for WSVM model are 0.954 and 0.056 respectively in verification step. Discussion and Conclusion: So, the propounded hybrid model has superior ability in forecasting SPI time series comparing with the single SVM model and also it can accurately assess the extreme data in SPI time series by considering the seasonality effects. Finally, it was concluded that, the proposed hybrid model is relatively more appropriate than classical autoregressive models such as ANN.  

منابع و مأخذ:


  1. Cacciamani, C., Morgillo, A., Marchesi, S., Pavan, V.,2007. Monitoring and forecasting drought on a regional scale: Emilia-Romagna Region. Water Science and Technology. Lib, Vol. 62, pp. 29–48.
    2.
  2. Tsakiris, G., Vangelis, H.,2004. Towards a drought watch system based on spatial SPI. Water Resources Management, Vol. 18. pp. 11–12.
    3.
  3. Mishra, A.K., Desai, V.R.,2006. Drought forecasting using feed-forward recursive neural network. Ecological Modelling, Vol. 198(1-2), pp. 127-138.
    4.
  4. Azhdari Moghadam, M., Khosravi, M., Hosseinpour Niknam, H., Jafari Nodoshan, E.,2012. Drought forecasting using neuro-fuzzy model. Climate indices and time series of precipitation and drought. Applied Geography and. Development, Vol. 26, pp. 17–20.
    5.
  5. Marj, A.F., Meijerink, A.M.J.,2011. Agricultural drought forecasting using satellite images, climate indices and artificial neural network. International Journal of Remote Sensing, Vol. 32(24), pp. 9707–9719.
    6.
  6. Ebrahimpour, R., 2014. Using Artificial Neural Networks to Estimate the Return Sludge Rate, A Case Study of Torbat Heydarieh Wastewater Treatment Plant. Journal of Water and Wastewater, Vol. 25(4), pp. 99-107. (In Persian)
    7.
  7. Shafie, A., Taha, M.R., Noureldin, A., 2007. A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. Journal of Water Resources Management, Vol. 21, pp. 533–556.
    8.
  8. Banihabib, M., Valipoor, M., Behbahani, S. 2011. Comparison of Autoregressive Static and Artificial Dynamic Neural Network for the Forecasting of Monthly Inflow of Dez Reservoir. Journal of Environmental Science and Technology, Vol. 13(4), pp. 1-14.
    9.
  9. Lin G., Chen G., Huang P., Chou Y., 2009. Support vector machine-based models for hourly reservoir inflow forecasting during typhoon-warning periods. Journal of hydrology. Vol. 372, pp.17–29.
    10.
  10. Han, D., Chan, L., Zhu, N., 2007. Flood forecasting using support vector machines. Journal of Hydroinformatics, Vol. 9(4), pp. 267-276.
    11.
  11. Tripathi, S.h., Srinivas, V.V., Nanjundiah R.S., 2006. Downscaling of precipitation for climate change scenarios: A support vector machine approach, Journal of Hydrology, Vol. 330, pp. 621– 640.
    12.
  12. Wang, W., Men, C., Lu, W., 2008. Online prediction model based on support vector machine. Neuro Computing, Vol. 71, pp. 550-558.
    13.
  13. Behzad, M.K., Asghari, M., Eazi, M., Palhang M., 2009. Generalization performance of support vector machines and neural networks runoff modeling. Expert Systems with Applications, Vol. 36, pp. 7624-7629.
    14.
  14. Asefa, T., Kemblowski, M.W., Urroz, G., McKee, M. Khalil, A., 2004. Support vectors-based groundwater head observation networks design. Water Resources Research, Vol. 40 (11).
    15.
  15. Asefa, T., Kemblowski, M.W., McKee, M., Khalil A., 2006. Multi-time scale stream flow prediction: The support vector machines approach. Journal of Hydrology, Vol. 318, pp. 7–16.
    16.
  16. Dibike, Y.B., Velickov, S., Solomatine, D., Abbott, M.B., 2001. Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering, Vol. 15 (3), pp. 208–216.
    17.
  17. Liong, S.Y., Sivapragasam, C., 2002. Flood stage forecasting with support vector machines. The Journal of the American Water Resources Association, Vol. 38 (1), pp. 173–196.
    18.
  18. Sahraie, S., Zaker Moshfegh, M., 2013, River Flow Prediction Using Case Study Support Vector Machine, 7th National Congress of Civil Engineering, Zahedan, Sistan and Baluchestan University. (In Persian)
    19.
  19. Nikbakht Shahbazi, A., Zahraei, B., Sadghi, H., Manshouri, M., Nasseri, M., 2011. Seasonality meteorological drought prediction using support vector machine. World Applied Sciences Journal, Vol. 13(6), pp. 1387-1397.
    20.
  20. Zahraei, B., Nasseri, M., 2014. Basin scale meteorological drought forecasting using support vector machine. International Conference on Drought Management Strategies in Arid and Semi-Arid Regions.
    21.
  21. Cannas, B., Fanni, A., See, L., Sias, G., 2006. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Physics and Chemistry of the Earth, Vol. 31(18), pp. 1164–1171.
    22.
  22. Kim, T., Valdes, J.B., 2003. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering, Vol. 6, pp. 319–328.
    23.
  23. Vermes, L., 2001. How to work out a Drought mitigation strategy. European Regional conference of ICID.
    24.
  24. McKee, T.B., Doesken, N.J., Kleist, J., 1993. The relationship of drought frequency and duration to time scales. in Proceedings of the 8th Conference on Applied Climatology, Anaheim, Calif, USA.
    25.
  25. Vapnik, V.N., Cortes, C., 1995.  Support Vector Networks. Machine Learning, Vol. 20, pp. 273–297.
    26.
  26. Nourani, V., Komasi, M., Taghi Alami, M., 2012. Hybrid wavelet–genetic programming approach to optimize artificial neural network modeling of rainfall–runoff process, Journal of Hydrology Engineering, Vol. 17(6), pp. 724–741.
    27.
  27. Mallat, S.G., 1998. A Wavelet Tour of Signal Processing. Second ed. Academic Press. San Diego.
    28.
  28. Nourani V., Kisi Ö., Komasi M., 2011. Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology, Vol. 402, pp. 41–59.
    29.
  29. Nourani V., Komasi M., Mano A., 2009. A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water Resources Management, Vol. 23, pp. 2877–2894.
    30.

 

 

 

 

 

 

 

 

 

 

 

_||_

  1. Cacciamani, C., Morgillo, A., Marchesi, S., Pavan, V.,2007. Monitoring and forecasting drought on a regional scale: Emilia-Romagna Region. Water Science and Technology. Lib, Vol. 62, pp. 29–48.
    2.
  2. Tsakiris, G., Vangelis, H.,2004. Towards a drought watch system based on spatial SPI. Water Resources Management, Vol. 18. pp. 11–12.
    3.
  3. Mishra, A.K., Desai, V.R.,2006. Drought forecasting using feed-forward recursive neural network. Ecological Modelling, Vol. 198(1-2), pp. 127-138.
    4.
  4. Azhdari Moghadam, M., Khosravi, M., Hosseinpour Niknam, H., Jafari Nodoshan, E.,2012. Drought forecasting using neuro-fuzzy model. Climate indices and time series of precipitation and drought. Applied Geography and. Development, Vol. 26, pp. 17–20.
    5.
  5. Marj, A.F., Meijerink, A.M.J.,2011. Agricultural drought forecasting using satellite images, climate indices and artificial neural network. International Journal of Remote Sensing, Vol. 32(24), pp. 9707–9719.
    6.
  6. Ebrahimpour, R., 2014. Using Artificial Neural Networks to Estimate the Return Sludge Rate, A Case Study of Torbat Heydarieh Wastewater Treatment Plant. Journal of Water and Wastewater, Vol. 25(4), pp. 99-107. (In Persian)
    7.
  7. Shafie, A., Taha, M.R., Noureldin, A., 2007. A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. Journal of Water Resources Management, Vol. 21, pp. 533–556.
    8.
  8. Banihabib, M., Valipoor, M., Behbahani, S. 2011. Comparison of Autoregressive Static and Artificial Dynamic Neural Network for the Forecasting of Monthly Inflow of Dez Reservoir. Journal of Environmental Science and Technology, Vol. 13(4), pp. 1-14.
    9.
  9. Lin G., Chen G., Huang P., Chou Y., 2009. Support vector machine-based models for hourly reservoir inflow forecasting during typhoon-warning periods. Journal of hydrology. Vol. 372, pp.17–29.
    10.
  10. Han, D., Chan, L., Zhu, N., 2007. Flood forecasting using support vector machines. Journal of Hydroinformatics, Vol. 9(4), pp. 267-276.
    11.
  11. Tripathi, S.h., Srinivas, V.V., Nanjundiah R.S., 2006. Downscaling of precipitation for climate change scenarios: A support vector machine approach, Journal of Hydrology, Vol. 330, pp. 621– 640.
    12.
  12. Wang, W., Men, C., Lu, W., 2008. Online prediction model based on support vector machine. Neuro Computing, Vol. 71, pp. 550-558.
    13.
  13. Behzad, M.K., Asghari, M., Eazi, M., Palhang M., 2009. Generalization performance of support vector machines and neural networks runoff modeling. Expert Systems with Applications, Vol. 36, pp. 7624-7629.
    14.
  14. Asefa, T., Kemblowski, M.W., Urroz, G., McKee, M. Khalil, A., 2004. Support vectors-based groundwater head observation networks design. Water Resources Research, Vol. 40 (11).
    15.
  15. Asefa, T., Kemblowski, M.W., McKee, M., Khalil A., 2006. Multi-time scale stream flow prediction: The support vector machines approach. Journal of Hydrology, Vol. 318, pp. 7–16.
    16.
  16. Dibike, Y.B., Velickov, S., Solomatine, D., Abbott, M.B., 2001. Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering, Vol. 15 (3), pp. 208–216.
    17.
  17. Liong, S.Y., Sivapragasam, C., 2002. Flood stage forecasting with support vector machines. The Journal of the American Water Resources Association, Vol. 38 (1), pp. 173–196.
    18.
  18. Sahraie, S., Zaker Moshfegh, M., 2013, River Flow Prediction Using Case Study Support Vector Machine, 7th National Congress of Civil Engineering, Zahedan, Sistan and Baluchestan University. (In Persian)
    19.
  19. Nikbakht Shahbazi, A., Zahraei, B., Sadghi, H., Manshouri, M., Nasseri, M., 2011. Seasonality meteorological drought prediction using support vector machine. World Applied Sciences Journal, Vol. 13(6), pp. 1387-1397.
    20.
  20. Zahraei, B., Nasseri, M., 2014. Basin scale meteorological drought forecasting using support vector machine. International Conference on Drought Management Strategies in Arid and Semi-Arid Regions.
    21.
  21. Cannas, B., Fanni, A., See, L., Sias, G., 2006. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Physics and Chemistry of the Earth, Vol. 31(18), pp. 1164–1171.
    22.
  22. Kim, T., Valdes, J.B., 2003. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering, Vol. 6, pp. 319–328.
    23.
  23. Vermes, L., 2001. How to work out a Drought mitigation strategy. European Regional conference of ICID.
    24.
  24. McKee, T.B., Doesken, N.J., Kleist, J., 1993. The relationship of drought frequency and duration to time scales. in Proceedings of the 8th Conference on Applied Climatology, Anaheim, Calif, USA.
    25.
  25. Vapnik, V.N., Cortes, C., 1995.  Support Vector Networks. Machine Learning, Vol. 20, pp. 273–297.
    26.
  26. Nourani, V., Komasi, M., Taghi Alami, M., 2012. Hybrid wavelet–genetic programming approach to optimize artificial neural network modeling of rainfall–runoff process, Journal of Hydrology Engineering, Vol. 17(6), pp. 724–741.
    27.
  27. Mallat, S.G., 1998. A Wavelet Tour of Signal Processing. Second ed. Academic Press. San Diego.
    28.
  28. Nourani V., Kisi Ö., Komasi M., 2011. Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology, Vol. 402, pp. 41–59.
    29.
  29. Nourani V., Komasi M., Mano A., 2009. A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water Resources Management, Vol. 23, pp. 2877–2894.
    30.

 

 

 

 

 

 

 

 

 

 

 

مقالات مرتبط

حقوق این وب‌سایت متعلق به سامانه مدیریت نشریات دانشگاه آزاد اسلامی است.
حق نشر © 1403-1400

صفحه اصلی| عضویت/ ورود| درباره سند| تماس با ما|
[English] [العربية] [en] [ar]