A hybrid decision tree/ association rules approach for long-term precipitation forecasting

Document Type : Research Paper



Long-term forecasting of hydroclimatic variables such as maximum monthly precipitation (MMP) is very important in water resources management. The previous researches have shown that discovering association between the oceanic-atmospheric climate phenomena such as Sea Surface Temperature (SST) and hydroclimatic variables such as precipitation could provide important predictive information. In this paper, the application of two data mining techniques is offered to discover affiliation between MMP values of Urmia and Tabriz synoptic stations and SSTs of the Black, Mediterranean and Red Seas. Two major steps of the modeling in this study are the classification of SST data and selecting the most effective groups and extracting hidden predictive information involved in the data. Decision tree algorithms were used for classification and selecting the most effective groups and association rules were employed to extract the hidden predictive information from the large observed data. The results show a relative correlation between the Black, Mediterranean and Red Sea SSTs and MMP of Urmia and Tabriz synoptic stations so that the confidence between the MMP values and the SST of seas is higher than 60% forstations.


  1. اسماعیلی م. (1391) مفاهیم و تکنیک‌های داده‌کاوی. انتشارات نیاز دانش، تهران، 315 ص.
  2. خسروی غ.ر. خورانی ا. و خسروی م. (1392) نقش خلیج فارس در وضعیت اقلیمی کشور. رشد آموزش جغرافیا، 28(2): 43-48.
  3. رحیمی‌خوب ع. (1390) پیش‌بینی حداکثر بارندگی ماهانة ایستگاه ایلام از روی دمای سطح آب خلیج‌فارس و دریای سرخ با استفاده از روش داده‌کاوی. تحقیقات آب و خاک ایران، 42(1): 1-7.
  4. رضایی بنفشه م. جهانبخش س. بیاتی خطیبی م. و زینالی ب. (1389) پیش‌بینی بارش پاییزه و زمستانة نیمة غربی ایران، با استفاده از دمای سطح آب دریای مدیترانه در فصول تابستان و پاییز. پژوهش‌های جغرافیای طبیعی، 74: 47-62.
  5. ناظم‌السادات س.م.ج. و قاسمی ا.ر. (1383) تأثیر نوسان‌های دمای سطح آب دریای خزر بر بارش فصول زمستان و بهار نواحی شمال و جنوب‌غربی ایران. علوم و فنون کشاورزی و منابع طبیعی، 8(4): 1-14.
  6. Akrami S.A. Nourani V. and Hakim S.J.S. (2014) Development of nonlinear model based on Wavelet-ANFIS for rainfall forecasting at Klang Gates Dam. Water Resources Management, 28(10): 2999-3018.
  7. Araghinejad S. Burn D.H. and Karamouz M. (2006) Long-lead probabilistic forecasting of streamflow using ocean-atmospheric and hydrological predictors. Water Resources Research, 42(3): W03431.
  8. Dadaser F. Celik M. and Dokuz A.S. (2012) Associations between stream flow and climatic variables at Kizilirmak river basin in Turkey. Global NEST Journal, 14(3): 354-361.
  9. Dhanya C.T. and Kumar D. (2009) Data mining for evolution of association rules for droughts and floods in India using climate inputs. Geophysical Research, 114: 1-15.
  10. Han J. Kamber M. and Pei J. (2012) Data mining: concepts and techniques. 3th Ed. Morgan Kaufmann Publishers, San Francisco, California, United States of America, 744 p.
  11. Harshburger B. Ye H. and Dzialoski J. (2002) Observational evidence of the influence of Pacific sea surface temperatures on winter precipitation and spring stream discharge in Idaho. Hydrology, 264(1-4): 157-169.
  12. He X. Guan H. and Qin J. (2015) A hybrid wavelet neural network model with mutual information and particle swarm optimization for forecasting monthly rainfall. Hydrology, 527: 88-100.
  13. Lim E.P. Hendon H.H. Hudson D. Wang G. and Alves O. (2009) Dynamical forecast of inter-El Nino variations of tropical sea surface temperature and Australian spring rainfall. Monthly Weather Review, 137(11): 3796-3810.
  14. Meidani E. and Araghinejad S. (2014) Long-lead streamflow forecasting in the Southwest of Iran by sea surface temperature of the Mediterranean Sea. Hydrologic Engineering, 19(8): 1-10.
  15. Nicholls N. (1989) Sea surface temperatures and Australian winter rainfall. Climate, 2(9):
  16. 965-973.
  17. Nourani V. Alami M.T. and Aminfar M.H. (2009) A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation. Engineering Applications of Artificial Intelligence, 22(3): 466-472.
  18. Nourani V. Hosseini Baghanam A. Adamowski J. and Kisi O. (2014) Applications of hybrid Wavelet-Artificial Intelligence models in hydrology: A review. Hydrology, 514: 358-377.
  19. Nourani V. Alizadeh F. and Roushangar K. (2016) Evaluation of a two-stage SVM and spatial statistics methods for 460 modeling monthly river suspended sediment load. Water Resources Management, 30(1): 393-407.
  20. Otero F.E.B. Freitas A.A. and Johnson C.G. (2012) Inducing decision trees with an ant colony optimization algorithm. Applied Soft Computing, 12: 3615-3626.
  21. Quinlan J.R. (1992) Learning with continuous classes. Proceedings 5th Australian Joint Conference on Artificial Intelligence, Australian.
  22. Rowell D.P. (2003) The impact of Mediterranean Sea surface temperatures on the Sahelian rainfall season. Climate, 16(5):
  23. 849-862.
  24. Saghebian S.M. Sattari M.T. Mirabbasi R. and Pal M. (2014) Ground water quality classification by decision tree method in Ardebil region, Iran. Arabian Geosciences, 7(11): 4767-4777.
  25. Sattari M.T. Anil A.S. Apaydin H. and Kodal S. (2012) Decision trees to determine the possible drought periods in Ankara. Atmosfera, 25(1): 65-83.
  26. Soukup T.L. Aziz O.A. Tootle G.A. Piechota T.C. and Wulff S.S. (2009) Long lead-time streamflow forecasting of the North Platte river incorporating ocean-atmospheric climate variability. Hydrology, 368(1-4): 131-142.
  27. Tadesse T. Wilhite D.A. Harms S.K. Hayes M.J. and Goddard S. (2004) Drought monitoring using data mining techniques: A case study for Nebraska, United States of America. Natural Hazards, 33(1): 137-159.
  28. Zahraie B. and Roozbahani A. (2011) SST clustering for winter precipitation prediction in southeast of Iran: comparison between modified k-means and genetic algorithm-based clustering methods. Expert System with Applications, 38(5): 5919-5929.