Climate Change Research

Climate Change Research

Analyzing the Performance of Machine Learning Models in Detecting Teleconnection Signals Affecting Temperature and Precipitation in Northwest Iran

Document Type : Original Article

Authors
saeed Armaghan Bostanabad 1
Behrouz Sari Sarraf 1
Majid Rezaei Banafsheh Daragh 1
Ali mohmmad Khorshiddoost 2
1 Department of Climatology, Faculty of Planning and Environmental Sciences, University of Tabriz, Tabriz, Iran
2 Department of Climatology, Faculty of Planning and Environmental Sciences, University of Tabriz, Tabriz, Iran.
10.30488/ccr.2026.579366.1337
Abstract
This study aimed to develop an intelligent and interpretable modeling framework for the monthly prediction of precipitation and temperature at 24 synoptic stations in northwest Iran over a 30‑year period. For this purpose, the performance of three different approaches was evaluated: statistical modeling (Multivariate Linear Regression, MLR), fuzzy inference (Adaptive Neuro‑Fuzzy Inference System, ANFIS), and artificial intelligence (Multilayer Perceptron neural network, MLP). To overcome the limitations of classical methods in parameter optimization, a genetic algorithm (GA) was employed to design the optimal network architecture and determine the connection weights (resulting in the hybrid GA‑MLP model). The results showed that the proposed GA-MLP hybrid model delivered the most efficient performance by reducing the RMSE (e.g., demonstrating a 30% improvement in temperature and 23.5% in precipitation compared to the MLR model) and successfully overcoming the non-convergence issue of the baseline MLP model. Specifically, it lowered the temperature prediction error at the Parsabad station to 1.3°C and the precipitation prediction error at the Jolfa station to 10.9 mm. Sensitivity analysis using a feature‑importance approach revealed the key role of six‑month time lags and teleconnections in the region’s climatic fluctuations, confirming the model’s ability to grasp the underlying physics of the problem. Furthermore, uncertainty assessment using a calibrated bootstrap method indicated a high coverage rate above 95%, ensuring the model’s reliability for operational decision‑making. Finally, topographic analysis demonstrated no significant correlation between model error and elevation, which attests to the spatial robustness of the proposed model across heterogeneous climates.
Keywords
Teleconnection
Hybrid Neural Network
Genetic Algorithm
Fuzzy Modeling
Northwest Iran
Subjects
1.    بابایی فینی،ا. فتاحی،ا. 1394. پیش آگاهی فصلی دبی ورودی به دریاچه ارومیه با استفاده از سیگنال های بزرگ مقیاس اقلیمی. نشریه جغرافیا و توسعه، شماره 40، ص 124-109.
2.    حضرتی یادکوری، ش. 1382. بررسی ارتباط تراز دریاچه ارومیه با شاخصهای اقلیمی ENSO و .NAO پایان نامه کارشناسی ارشد، دانشگاه صنعتی شریف.
3.    خسروی، م. مسگری، ا. 1395. تحلیل فضایی روابط الگوهای پیوند از دور با دمای ماهانه شمال غرب ایران. نشریه جغرافیا و آمایش شهری- منطقه ای ، شماره 21.
4.    محمدخورشید دوست، ع. قویدل رحیمی، ی. 1385. ارزیابی اثر پدیده انسو بر تغییر پذیری بارش های فصلی استان آذربایجان شرقی با استفاده از شاخص چند متغیره انسو. نشریه پژوهش های جغرافیایی- شماره 57. صص 26-15.
5.    محمدخورشید دوست، ع. قویدل رحیمی، ی. یساری، ط. و نوری، ح. 1386. تحلیل نقش پدیدهNAO  در نوسانات سالانه بارش حوضه آبریز دریاچه ارومیه. فضای جغرافیایی دوره 7، شماره 19، صص86 -63.
6.    سبحانی، ب. صلاحی، ب. گل دوست، ا. 1393. ارتباط شاخص اقلیمی NAO با مقادیر میانگین حداکثر و حداقل دمای ماهانه شمال غرب ایران. نشریه تحقیقات کاربردی علوم جغرافیایی، سال چهاردهم، شماره33 ، صص90-75.
7.    عزیززاده، م. ر. جوان، خ. 1398. تحلیل روند شاخص های حدی بارش در حوضه دریاچه ارومیه و ارتباط آن با الگوهای پیوند از دور. نشریه علمی جغرافیا و برنامه ریزی، سال 23، شماره 70، صص 247-227.
8.    فاتحی مرج، ا. داودی، م. و آرمان، ن. 1387. پیش بینی خشکسالی با استفاده از SOI و NINO3,4 و شبکه عصبی، راهکاری برای مقابله با آن. پنجمین همایش ملی علوم و مهندسی آبریزداران ایران( مدیریت پایدار بلایای طبیعی).
9. قویدل رحیمی،ی. فرج زاده،م و کاکاپور، س. 1393. بررسی اثر الگوهای پیوند از دور شمال خزر بر نوسانات بارش های پاییزی مناطق غرب و شمال غرب ایران. نشریه پژوهشی جغرافیا و برنامه ریزی، سال 18، شماره 49، ص 217-230.
10. میرهاشمی، ح.، حسنوند، ز. (1401). ﺗﺄثیر الگوهای پیوند از دور بر بارش های ماهانه ایستگاه های شهر خرم آباد و کرمانشاه. مدل سازی و مدیریت آب و خاک، 3 (4): 151-133.
11. ناظم السادات، س. 1378. بررسی پدیده النینو – نوسانات جنوبی (ENSO) بر بارندگی پاییزه ایران. کنفرانس منطقه ای تغییر اقلیم تهران: سازمان هواشناسی کشور.
12. Ahmadi, M., Kamangar, M., Salimi, S. et al. A new approach in evaluation impacts of teleconnection indices on temperature and precipitation in Iran. Theor Appl Climatol 150, 15–33 (2022). https://doi.org/10.1007/s00704-022-04138-w
13. Barnston, A. G., & Livezey, R. E. (1987). Classification, seasonality and persistence of low-frequency atmospheric circulation patterns. Monthly Weather Review, 115(6), 1083-1126.
14. Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
15. Ghasemi, A. R., & Khalili, D. (2006). The influence of the North Atlantic Oscillation on the winter precipitation of Iran. Theoretical and Applied Climatology, 85(3–4), 149–165. https://doi.org/10.1007/s00704-005-0187-y
16. Gupta, H. V., Kling, H., Yilmaz, K. K., & Martinez, G. F. (2009). Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. Journal of Hydrology, 377)1-2), 80–91. https://doi.org/10.1016/j.jhydrol.2009.08.003
17. Hagan, M. T., & Menhaj, M. B. (1994). Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5)6), 989–993. https://doi.org/10.1109/72.329697
18. Han, J., Pei, J., & Tong, H. (2011). Data Mining: Concepts and Techniques )3rd ed.). Morgan Kaufmann. https://doi.org/10.1016/C2009-0-61819-5
19. Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson Education.
20. Helali.J & Salimi, S& Lotfi, M & Hosseini, A & Bayat,A & Ahmadi,M & Naderizarneh., S.2020. Investigation of the effect of large-scale atmospheric signals at different time lags on the autumn precipitation of Iran’s watersheds, Arabian Journal of Geosciences,2020,13:932. https://doi.org/10.1007/s12517-020-05840-7.
21. Hurrell, J. W. (1995). Decadal trends in the North Atlantic Oscillation: regional temperatures and precipitation. Science, 269(5224), 676-679.
23. IPCC. (2021). Climate Change 2021: The Physical Science Basis. Cambridge University Press.
24. Jang, J. S. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541
25. Jang, J.-S. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541
26. Kisi, O. (2005). Suspended sediment estimation using neuro-fuzzy and neural network approaches. Hydrological Sciences Journal, 50(4), 683–696. https://doi.org/10.1623/hysj.2005.50.4.683
27. Kisi, O. (2005). Suspended sediment estimation using neuro-fuzzy and neural network approaches. Hydrological Sciences Journal, 50(4), 683-696.
28. Koutsoyiannis, D. (2003). Climate change, the Hurst phenomenon, and hydrological statistics. Hydrological Sciences Journal, 48(1), 3–24. https://doi.org/10.1623/hysj.48.1.3.43481
29. Maier, H. R., & Dandy, G. C. (2000). Neural networks for the prediction and forecasting of water resources variables. Environmental Modelling & Software, 15(1), 101-124.
30. Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., & Veith, T. L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50(3), 885–900. https://doi.org/10.13031/2013.23153
31. Nazemosadat M. J., Shahgholian, K (2017) Heavy precipitation in southwest of Iran: association with the Madden- Julian Oscillation and synoptic scale analysis. Climate Dynamics, 49: 3091-3109
32. Nazemosadat M. J., Shahgholian, K., Ghaedamin, H., Nazemosadat, E (2020) Introducing ne climate indicies for identifying wet/dry spells within and Madden-Julian oscillation phase. International Journal of Climatology, 41, E1686-E1699.
33. Nazemosadat, M. J., & Cordery, I. (2000). On the relationships between ENSO and autumn rainfall in Iran. International Journal of Climatology, 20(1), 47–61. https://doi.org/10.1002/(SICI)1097-0088(200001)20:1<47:AID-JOC461>3.0.CO;2-W
34. Nazemosadat, M. J., A. R. Ghasemi and I. Cordery. 2003. The linkage between precipitation in Iran and NSW Australia. The Proceeding of the Third Regional and First National Conference on Climate Change, Isfahan, Iran.
35. Pakdaman, M., Babaeian, I., & Fathian, F. (2024). Monthly precipitation forecasting in the northwest of Iran using machine learning methods and teleconnection indices. Journal of Climate Research, 15(57), 1–16. https://doi.org/10.22031/cr.2024.101235.1098
36. Pakdaman, M., Babaeian, I., Javanshiri, Z., and Falamarzi, Y., 2022b, European multi model ensemble (EMME): A new approach for monthly forecast of precipitation: Water Resources Management, 36(2), 611-623.
37. Pakdaman, M., Falamarzi, Y., Babaeian, I., and Javanshiri, Z., 2020, Post-processing of the North American multi-model ensemble for monthly forecast of precipitation based on neural network models: Theoretical and Applied Climatology, 141(1-2), 405-41
38. Patro, S. G., & Sahu, K. K. )2015). Normalization: A preprocessing stage. International Journal of Advanced Research in Computer Science and Software Engineering, 5(3), 122–125. https://doi.org/10.17148/IJARCCE.2016.5327
39. Pourasghar F, Tozuka T, Jahanbakhsh S, Sari Sarraf B, Ghaemi H, Yamagata T (2012) The interannual precipitation variability in the southern part of Iran as linked to large-scale climate modes. Climate Dynamics, 39:2329-2341.
40. Pourasghar, F., Toofan, S., & Eslami, H. (2012). The relationship between North Atlantic Oscillation (NAO) and winter precipitation in Northwest Iran. Theoretical and Applied Climatology, 110(1–2), 85–93. https://doi.org/10.1007/s00704-012-0594-2
41. Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat, F. )2019). Deep learning and process understanding for data-driven Earth system science. Nature, 566(7743), 195-204. https://doi.org/10.1038/s41586-019-0912-1
42. Ropelewski, C. F., & Halpert, M. S. (1987). Global and regional scale precipitation patterns associated with the El Niño/Southern Oscillation. Monthly Weather Review, 115(8), 1606-1626.
43. Seber, G. A. F., & Wild, C. J. (2003). Nonlinear Regression. Wiley-Interscience. https://doi.org/10.1002/0471725315
44. Shen, C. (2018). A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resources Research, 54(11), 8558–8593. https://doi.org/10.1029/2018WR022643
45. Sola, J., & Sevilla, J. (1997). Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transactions on Nuclear Science, 44)3), 1464–1468. https://doi.org/10.1109/23.589532
46. Tabari, H., Hosseinzadeh Talaee, P., Shifteh Some'e, B. and Willems, P., 2014. Possible influences of North Atlantic Oscillation on winter reference evapotranspiration in Iran, Global and Planetary Change, v.117, p.28-39.
47. Tabari, H., Hosseinzadeh Talaee, P., Shifteh Some'e, B., Willems, P. (2014), Possible influences of North
48. Vaheddoost, B., Aksoy, H. (2017). Structural characteristics of annual precipitation in Lake Urmia basin. Theoretical and Applied Climatology 128(3-4): 919–932.
49. Wallace, J. M., & Gutzler, D. S. (1981). Teleconnections in the geopotential height field during the Northern Hemisphere winter. Monthly Weather Review, 109(4), 784-812.
50. Willmott, C. J., & Matsuura, K. )2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79–82. https://doi.org/10.3354/cr030079