پیش‌بینی خشکسالی یک‌ساله با استفاده از مدل فازی-عصبی، سری‌های زمانی خشکسالی و شاخصهای اقلیمی (مطالعه موردی: زاهدان)

نوع مقاله: مقاله پژوهشی

نویسندگان

1 کارشناس ارشد عمران آب، دانشکده مهندسی عمران، زاهدان دانشگاه سیستان و بلوچستان، زاهدان

2 دانشیار گروه مهندسی عمران، دانشگاه سیستان و بلوچستان، زاهدان

3 دانشیار جغرافیای طبیعی، دانشگاه سیستان و بلوچستان، زاهدان

چکیده

تحقیق حاضر تلاشی برای پیش‌بینی خشکسالی یک سال بعد در شهر زاهدان با استفاده از مقادیر پیشین شاخص خشکسالی بارندگی استاندارد شده (SPI) و 19 عدد از شاخصهای اقلیمی است. به این منظور از قابلیتهای سیستم استنتاج فازی- عصبی تطبیقی (ANFIS) برای ساخت مدل‌های پیش‌بینی و از شاخص خشکسالی SPI برای نمایش کمّی خشکسالی استفاده گردید. در ابتدا از روش محاسبه همبستگی برای تحلیل ارتباط میان خشکسالی‌ها و شاخصهای اقلیمی استفاده شده و مناسب‌ترین شاخصهای اقلیمی انتخاب گردیدند. در مرحله بعد پیش‌بینی خشکسالی‌ها در مقیاس زمانی 12 ماهه صورت پذیرفت. ترکیبات مختلفی از متغیرهای ورودی در مدل‌های پیش‌بینی فازی- عصبی ANFIS وارد گردیدند. شاخص خشکسالی SPI نیز به‌عنوان خروجی مدل‌ها معرفی شد. نتایج نشان داد که تنها استفاده از سری‌های زمانی مشابه سال قبل شاخص خشکسالی SPI در پیش‌بینی خشکسالی‌های 12 ماهه مؤثر است. با این حال از بین شاخصهای اقلیمی مورد بررسی، شاخص Nino4 مناسب‌ترین نتایج را ارائه داد.

کلیدواژه‌ها


عنوان مقاله [English]

Drought Forecasting Using Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Drought Time Series and Climate Indices For Next Coming Year, (Case Study: Zahedan)

نویسندگان [English]

  • Hossein Hosseinpour Niknam 1
  • Mehdi Azhdari Moghadam 2
  • Mahmoud Khosravi 3
1 M.Sc. of Water Eng., Dept. of Civil Eng., Systan and Balochestan Universtiy, Zahedan
2 Assoc. Prof. of Civil Eng., Systan and Balochestan University, Zahedan
3 Assoc. Prof. of Natural Geography, Systan and Balochestan University, Zahedan
چکیده [English]

In this research in order to forecast drought for the next coming year in Zahedan, using previous Standardized Precipitation Index (SPI) data and 19 other climate indices were used.  For this purpose Adaptive Neuro-Fuzzy Inference System (ANFIS) was applied to build the predicting model and SPI drought index for drought quantity.  At first calculating correlation approach for analysis between droughts and climate indices was used and the most suitable indices were selected. In the next stage drought prediction for period of 12 months was done. Different combinations among input variables in ANFIS models were entered. SPI drought index was the output of the model.  The results showed that just using time series like the previous year drought SPI index in forecasting the 12 month drought was effective. However among all climate indices that were used, Nino4 showed the most suitable results.

کلیدواژه‌ها [English]

  • Drought forecasting
  • Standardized Precipitation Index (SPI)
  • Climate Indices
  • ANFIS
  • Zahedan
1- Alizadeh, A. (2004). Principle of applied hydrology, 17th Ed., Imam Reza University, Mashhad, Iran. (In Persian)

2- The OFDA/CRED International Disaster Database. (2009). <www.em-dat.net> (Dec. 5, 2009).

3- I.R. Iran Metorological Organistaion. (2006). <www.weather.ir> (Jan. 15, 2007).

4- Farokhnia, A., Morid, S., and Ghaemi, H. (2008). “Inyestigation on large scale climatiologically signals to predict long term drough.” 3rd Proc. Iranian Water Resources Management Conferece, Tabriz University, Tabriz. (In Persian)

5- Anvari, S. (2008). “Increse artificial models to predict reiver discharge using distributed climatologically and snow surface data.” MSc. Thesis, Hydraulic Structures, Tarbiat Modares University, Tehran, Iran. (In Persian)

6- Bagherzadeh Chehreh, K. (2005). “Evaluation of meteorological signals on forecasting in Tehran province using artificial neural network.” M.S. Thesis, Hydraulic Structures, Tarbiat Modares University, Tehran, Iran.

7- Hosseinpour Niknam, H., Azhdary Moghaddam, M., and Khosravi, M. (2010). “Drought forecasting using adaptive neuro-fuzzy inferece system (ANFIS) and teleconnections patterns, case study: Zahedan.” 4th International Congress of Islamic World Geographers (ICIWG), University of Sistan and Balouchestan, Zahedan, Iran. (In Persian)

8- Poustizadeh, N., Samani, J.M.V., and Dezfuli, A.K. (2008). “River flow forecasting using fuzay inference system.” Iran, Water Resources Research, 4 (2), 23-34. (In Persian)

9- Bacanli, U., Firat, M., and Dikbas, F. (2008). “Adaptive neuro-fuzzy inference system (ANFIS) for drought forecasting.” Stoch. Environ. Res. Risk Assess, 23 (8), 1143-1154.

10- Zounemat Kermani, M., and Teshnehlab, M. (2008). “Using adaptive neuro-fuzzy inference system for hydrological time series prediction.” Applied Soft Computing, 8(2), 928-936.

11- Morid, S., Smakhtin, V., and Bagherzadeh, K. (2007). “Drought forecasting using artificial neural networks and time series of drought indices.” International J. of Climatology, 27, 2103-2111.

12- Karamouz, M., Tabesh, M., Nazif, S., and Moridi, A. (2005). “Estimation of hydraulic pressure in water network using artificial nevral network and fuzzy logic.” J. of Water and Wastewater, 53, 3-14. (In Persian)

13- Saadatpour, M., Afshar, A., and Bozorg Haddad, O. (2006). “Fuzzy simulation- optimization model for waste load allocation.” J. of Water and Wastewater, 56, 2-10. (In Persian)

14- Nayak, P., Sudheer, K., Rangan, D., and Ramasa, K. (2004). “A neuro-fuzzy computing technique for modeling hydrological time series.” J. of Hydrology, 291, 52-66.

15- Pongracz, R., Bogardi, I., and Ducksteinc, L. (1999). “Application of fuzzy rule-based modeling technique to regional drought.” J. of Hydrology, 224, 100-114.

16- McKee, T.B., Doesken, N.J., and Kleist, J. (1993).  “The relationship of drought frequency and duration to time steps.” Preprints, 8th  Conference on Applied Climatology, Anaheim, California, 179-184.

17- Raziei, T., Daneshkar Arasteh, P., Akhtari, R., and Saghafian, B. (2007). “Investigation of meteorological droughts in the Sistan and Balouchestan province, using the standardized precipitation index and Markov Chain model.” Iran Water Resources Reserch, 3 (1), 25-35. (In Persian)

18- Khosravi, M. (2004). “Study of relation between large scale Northern Hemiphere atmospheric circulation Pattern with sistan and Balouchestan naaual drought.” Irannian J. of Geography and Development, 3, 167-188. (In Persian)

19- Hosseinpour Niknam, H. (2009). “Drough forecasting using adaptive neuro-fuzzy inference system (ANFIS) and climate indices case study, Zahedan, Iran.” M.Sc. Thesis, University of Systan and Balouchestan, Zahedan. (In Persian)

20- NOAA. (2009). <http://www.esrl.noaa.gov/psd/data/climateindices/list/.> (Aug. 12, 2009)

21- Jang, J.-S.R.(1993). “ANFIS: Adaptive network based fuzzy inference system.” IEEE Transactions on Systems, Man and Cybernetics, 23 (3), 665-683.