مقایسه مدل‌های رگرسیون بردار پشتیبان، برنامه‌ریزی بیان ژن و آیهکرس در پیش‌بینی تغییرات رواناب تحت تاثیر تغییر اقلیم (مطالعه موردی: سد جامیشان)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی ارشد گروه علوم و مهندسی آب، دانشکده کشاورزی، دانشگاه رازی، کرمانشاه، ایران

2 استادیار گروه علوم و مهندسی آب،دانشکده کشاورزی، دانشگاه رازی، کرمانشاه، ایران

چکیده

امروزه اثرات تغییر اقلیم و گرمایش جهانی به دلیل افزایش گاز‌های گلخانه‌ای در جهان به اثبات رسیده‌است. وقوع این شرایط، فرآیند‌‌های هیدرولوژیکی مانند بارش و جریان رودخانه‌ها را که یکی از منابع اصلی تامین کننده آب حوضه است، تحت تاثیر قرار می‌دهد. در این تحقیق مقادیر ماهانه بارش، دما و دبی سد جامیشان در سال‌های ۲۰۱۷-۱۹۸۸ به­عنوان دوره پایه در نظر گرفته شده‌‌‌است. به دلیل اینکه خروجی مدل‌های اقلیمی دقت و تفکیک مکانی و زمانی مورد نظر را ندارد، لذا لازم است که خروجی مدل‌های CMIP5 برای منطقه مورد نظر ریزمقیاس شود. در این پژوهش با استفاده از روش عامل تغییر، داده‌های دو مدل FLO_ESM و CNRM_CM5 تحت سناریو RCP8.5 ریزمقیاس شده و پارامترهای ماهانه دما و بارش سد جامیشان برای دوره‌ی ۲۰۵۰-۲۰۲۱ تولید گردید. برای ارزیابی تاثیر تغییر اقلیم بر تغییرات رواناب منطقه مورد نظر به بررسی و مقایسه‌ی مدل‌های رگرسیون بردار پشتیبان، برنامه‌ریزی بیان ژن و آیهکرس با استفاده از زبان برنامه نویسی پایتونپرداخته‌شد. نتایج مدل‌های اقلیمی افزایش دمای بین ۱/۰ تا ۴/۱ درجه سلسیوس را به­ترتیب برای دو مدل FLO_ESM و CNRM_CM5 نشان می‌دهد. همچنین نتایج بارش شبیه­سازی شده نشان می‌دهد که میانگین درازمدت ماهانه تحت سناریو RCP8.5 در دوره آتی به­ترتیب ۱/۱ و ۸/۵ درصد نسبت به دوره پایه کاهش داشته‌است. به طور کلی بررسی نتایج حاصل از پیش‌بینی دبی در هر سه مدل رگرسیون بردار پشتیبان، برنامه‌ریزی بیان ژن و آیهکرس حاکی از کاهش رواناب است که بیش­ترین کاهش رواناب مربوط به SVM در مدل FLO_ESM با ۹/۲۸ درصد و کمترین کاهش رواناب مربوط به GEP در مدل CNRM_CM5 با ۱/۱۴ درصد می‌باشد و در این پژوهش مدل‌های آیهکرس و بیان ژن نسبت به روش رگرسیون بردار پشتیبان از دقت مطلوب‌تری برخوردار هستند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Comparison of SVM, GEP and IHACRES Models in Prediction of Runoff Changes Due to Climate Change (Case Study: Jamishan Dam)

نویسندگان [English]

  • Banafsheh Rahimi 1
  • Maryam Hafezparast Mavaddat 2
1 Department of Water Science and Engineering, Razi University, Kermanshahi, Iran
2 Assistant Professor ,Department of Water Science and Engineering, Razi University, Kermanshahi, Iran
چکیده [English]

Today, the effects of climate change and global warming have been demonstrated by rising greenhouse gases. Occurrence of these conditions affects hydrological processes such as precipitation and river flow, which is one of the main sources of water for the basin. In this study, the monthly values of precipitation, temperature and inflow of Jamishan Dam during the period of 1988-2017 are considered as the basic period. The output of climate models does not have the desired accuracy and spatial and temporal resolution, so it is necessary to downscale the output of CMIP5 models for the study area. In this study, using Change Factor Method (CFM), the data of two FLO_ESM and CNRM_CM5 models were downscaled under the RCP8.5 scenario and the monthly temperature and precipitation parameters of Jamshan dam were produced for the period 2021-2050. To evaluate the effect of climate change on runoff in the region, SVM, GEP and IHACRES models were studied and compared. The results of climate model indicate an increase in temperature between 0.1 to 1.4 degrees of Celsius for both FLO_ESM and CNRM_CM5 models. Also, the results of simulated precipitation in FLO_ESM and CNRM_CM5 models show that the monthly long-term average under the RCP8.5 scenario in the next period decreased 1.1 and 5.8%, respectively, as compared to the baseline period. In general, the results show a reduction in runoff in all three models (SVM, GEP and IHACRES), which the highest reduction (28.9%) is corresponded to SVM in FLO_ESM model and the lowest reduction (14.1%) is corresponded to GEP in CNRM_CM5 model. In this study, GEP and IHACRES models are more accurate than the SVM model.

کلیدواژه‌ها [English]

  • "Climate Change"
  • "Rainfall-Runoff"
  • "svr"
  • "GEP"
  • "IHACRES"
Aghakhani Afshar, A., Hasanzade, Y., Basalatpour, A. and Pourrezabilandi, M. (2016). Annual evaluation of climatic components of Kashfar River Basin in future courses using the Fifth Report of the Intergovernmental Panel on Climate Change. Journal of Soil and Water Conservation Research, 23(6), 217-233. (In Farsi)
Ahmadi, F., Radmanesh, F. and Mirabbasi, R. (2016). Comparison of the performance of support vector machine methods and business networks in predicting daily river flow (Case study: Barandoozchay River). Journal of Soil and Water Conservation Research, (6)22, 186-171. (In Farsi)
Aytak, A., Asce, M. and Alp, M. (2008). An Application of Artificial Intelligence for Rainfall-Runoff Modeling. Journal of Earth System Science. 117: 145-155.
Botsis, D., Latinopoulos, P., and Diamantaras, K. (2011). Rainfall- Runoff modeling using support vector regression and artificial neural networks, J. Rhodes, Greece
Dehghani, R., Ghorbani, M. Teshnehlab, M. Rikhtegae, A. and Asadi, E. (2015). Comparison and evaluation of business neural network models; gene expression planning; support vector machine and linear regression in flow estimation (Case study: Sufi Chay Basin). Iranian Journal of Irrigation and Water Engineering Research, (4)5, 65-85. (In Farsi)
Dehghani, T., Saligheh, M. and Alijani, B. (2017). The effect of climate change on rainfall in the northern coasts of the Persian Gulf. Journal of Applied Research in Geographical Sciences. 18(49),75-91. (In: Farsi)
Dibike, Y.B., Velickov, S., Solomatine, D.P. and Abbott, M.B. (2001). Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering. 15(3), 208-216.
Farboudfam, N., Ghorbani, MA., and Alami, MT. (2009) River Flow Prediction Using Genetic Programming ( Case Study : Lighvan River Watershed ).Water and soil science.19(1),108-123(In Farsi)
Ferreira, C. (2001). Gene expression programming: A new adaptive algorithm for solving problems. Complex Systems, 13(2), 87-129.
Goudarzi, M., Salahi, B. and Hoseini, B. (2018). Assessment of IHACRES model in simulation of river flow in Urmia Lake watershed. Iranian Journal of Watershed Management and Engineering. 12(43), 1-10. (In Farsi)
Guven, A. 2009. Linear genetic programming for time-series modelling of daily flow rate. Journal Earth System Science, vol 118: 157-173
Hafezparast, M., Bafkar, A. and Panahi, E. (2016). Assessing the uncertainty of climate change and its effects on the likelihood of frequent flooding of the entrance to the Jamishan Dam. Journal of Water and Soil Conservation, 6(3), 42-19. (In Farsi)
He, Z., Wen, X. Liu, H. and Du, J. (2014). A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. Journal of Hydrology 509: 379–386. 
IPCC, (2001).The Scientific Basis of Climate Change. Contribution of Working Grop I to the Third Assessment Report of the Intergovernmental Panel on Climate Change, Cambridge University Press, and Cambridge.
IPCC, (2014): Annex I: Glossary, Acronyms and Chemical Symbols [Allwood, J. M., V. Bosetti, N. K. Dubash, L. Gómez-Echeverri and C. von Stechow (eds.)]. In: Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change [Edenhofer, O., R. Pichs-Madruga, Y. Sokona, E. Farahani, S. Kadner, K. Seyboth, A. Adler, I. Baum, S. Brunner, P. Eickemeier, B. Kriemann, J. Savolainen, S. Schlömer, C. von Stechow, T. Zwickel and J. C. Minx (eds.)]. Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA, pp. 1251–1274
Jakeman, A, J. and Hornberger, G. M. (1993). How much complexity is warranted in a rainfall-runoff model? Water Resources Research. 29(8), 2637-2649.
Khosravi, M., Esmaiealzadeh, M. and Nazaripour, H. (2010). Climate change and its impact on water resources in the Middle East. In: Fourth International Congress of Geographers of the Islamic World, 14-17 April., University of Sistan and Baluchestan, Zahedan, Iran.
Littlewood, L, G., Clarke, R. T., Collischonn, W, and Croke, B. F.W. (2007). Predicting daily Streamflow using rainfall forecasts, a simple loss module and unit hydrographs: Two Brazilian catchments. Environmental Modelling and Software, 22: 1229-1239.
Lotfirad, M., Adib, A. and Haghighi, A. (2018). Estimation of daily runoff with the help of ihacres semi-conceptual model in Naroud catchment area of Gilan.. 2(5), 460-449.
Mansoori, A., Aminnezhad, B. and Ahmadi,H. (2017). Investigating the effect of climate change on the runoff to the Karun 4 reservoir reservoir based on the fourth and fifth IPCC reports. Journal of Soil and Water Sciences. 22(2), 345-359. (In Farsi) 
Modaresi F., Araghinejad S., Ebrahimi K. (2017). Assessment of Ordered Weighted Averaging Strategies in Combination of Streamflow Forecasting Models. jwmseir. 10 (35):15-25. URL: http://jwmsei.ir/article-1-469-fa.html (In Farsi)
Moharrampour M.,Mehrabi, A. and Katozi, M. (2011). Using SVR for prediction of daily discharge. 4th conference of Iran water resources management (In Farsi)
Nabizadeh, M., Mosaedi, A. and Dehghani, A.A. (2012). Intelligent estimation of stream flow by Adaptive Neuro-Fuzzy Inference System. Water and Irrigation Management. 2(1), 69-80. (In Farsi)
Pourkheirolah, Z., Hafezparast, M. and Fatemi, S.A. (2017). Changes in the parameters of precipitation, temperature and Dubai under the radiation scenario caused the radiation (study area: Dehloran city). In: Second National Conference on Hydrology of Iran. 11-12 July. Shahrekord University, Shahrekord, Iran. (In Farsi)
Pourmohamadi, S., Dastourani, M., Mesahbovani, A. and Jafari, H. (2015). Investigating the effects of climate change and cloud fertility on river runoff (Case study: Qolqol River River Tuyserkan catchment area). In: 10th International River Engineering Seminar, 18-20 January. Chamran University, Ahvaz, Iran.
Sadeghi, S.H., Ghasemieh, H. and Sadatinezhad, S.J. (2015). Performance Evaluation of IHACRES Hydrological Model in Wetlands (Case Study: Navroud Basin, Gilan). Journal of Soil and Water Sciences. 19(73), 73-82. (In: Farsi)
Sette,S. and Boullart. L. (2001). Genetic Programming: Principles and applications. Engineering Applications of Artifical Intelligence. 14, 727- 736.
Seyam, M., Othman, F., & El-Shafie, A. (2017). Prediction of Stream Flow in Humid Tropical Rivers by Support Vector Machines. In MATEC Web of Conferences (Vol. 111, p. 01007). EDP Sciences
Solgi, A., Zarei, H., Shehnidarabi, M. and Alidadi, S. (2017). Predict monthly precipitation using gene expression expression models and support vector machines. Journal of Applied Research in Geographical Sciences. 18(50), 91-103. (In: Farsi)
Soltani, A., Ghorbani, M., Fakherifard, A., Darbandi, S. and Farsadizade, D. (2010). Genetic planning and its application in modeling runoff rainfall process. Journal of Water and Soil Knowledge. 20(4), 62-71. (In Farsi)
Wang, W. C., Chau, K. W., Cheng, C. T., & Qiu, L. 2009. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of hydrology, 374(3), 294-306.