ارزیابی عملکرد رهیافت‌های برنامه‌ریزی ژنتیک و ماشین بردار پشتیبان در بازسازی داده‌های گمشده بارش

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی منابع آب، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه شهرکرد

2 استادیار گروه مهندسی آب، دانشکده کشاورزی، دانشگاه شهرکرد

3 استادیار گروه مهندسی آب، دانشکده کشاورزی، دانشگاه بوعلی سینا همدان

4 دانشجوی کارشناسی ارشد مهندسی منابع آب، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز

چکیده

فقدان یا گسست در سری زمانی داده‌های بارش در بسیاری از ایستگاه‌های هواشناسی، یکی از محدودیت‌های اصلی در مطالعات اقلیم‌شناسی و منابع آب است. در پژوهش حاضر از دو رهیافت هوشمند برنامه‌ریزی ژنتیک و ماشین بردار پشتیبان به منظور بازسازی داده‌های بارش ماهانه چهار ایستگاه باران‌سنجی واقع در استان همدان، در دوره آماری 1370 تا 1389 استفاده شد. خلاء آماری ابتدا به کمک اطلاعات یک ایستگاه، سپس دو ایستگاه و در نهایت داده‌های سه ایستگاه، بازسازی گردید. نتایج نشان داد که با افزایش حافظه و تعداد ایستگاه‌های دخیل در مرحله آموزش، عملکرد مدل‌ها بهبود می‌یابد. همچنین رهیافت ماشین بردار پشتیبان در بازسازی داده‌های بارش ماهانه ایستگاه سرابی و مریانج به ترتیب با ریشه میانگین مربعات خطا 9/12 و 4/11 میلی‌متر و ضریب همبستگی 93/0 و 95/0 نسبت به روش برنامه‌ریزی ژنتیک با ریشه میانگین مربعات خطای 13 و 2/12 میلی‌متر و ضریب همبستگی 93/0 و 95/0 از عملکرد بهتری برخوردار بوده است.

کلیدواژه‌ها


عنوان مقاله [English]

Performance evaluation of the genetic programming and support vector machine models in reconstruction of missing precipitation data

نویسندگان [English]

  • M. Kadkhodahosseini 1
  • R. Mirabbasi-Najafabadi 2
  • H. Nozari 3
  • A. Rostami 4
1 Ph. D. Student of Water Resources Engineering, Department of Water Engineering, College of Agriculture, Shahrekord University, Shahrekord, Iran
2 Assistant Professor, Department of Water Engineering, College of Agriculture, Shahrekord University, Shahrekord, Iran
3 Assistant Professor, Department of Water Engineering, College of Agriculture, Buali Sina University, Hamedan, Iran
4 M. Sc. Student of Water Resources Engineering, Department of Water Engineering, College of Agriculture, Tabriz University, Tabriz, Iran
چکیده [English]

Incomplete rainfall datasets with missing gaps is a major challenge in climatology and water resource studies. In the present study, two intelligent models, namely Genetic Programing (GP) and Support Vector Machines (SVM) were used to reconstruct the monthly rainfall data of four rain-gauges located in Hamedan province, Iran during the period of 1992 to 2011. The incomplete rainfall data was reconstructed first by using the data of one, two and three stations respectively. The results showed that increasing the memory and the number of stations involved in the training phase, will improve the performance of the models. In reconstruction of monthly precipitation data of Sarabi and Maryanj stations, the Support Vector Machine method showed better performance with RMSE of 12.9 mm and 11.4 mm, and correlation coefficients (r) of 0.93 and 0.95, respectively. The corresponding values of RMSE for GP approach were 13 mm and 12.21 mm, which indicated the superior performance of SVM.

کلیدواژه‌ها [English]

  • Rainfall
  • Missing data
  • intelligent methods
  • Hamedan

Ahmadi, F., Radmanesh, F., Abadi, R. M. N. 2015. Comparison between Genetic Programming and Support Vector Machine methods for daily river flow forecasting (Case Study: Barandoozchay River). Journal of Water and Soil, 28(6), 1162-1171. (In Farsi)

Acock, M. C., Pachepsky, Y. A. 2000. Estimating missing weather data for agricultural simulations using group method of data handling. Journal of Applied Meteorology, 39(7): 1176–1184.

Che-Ghani, N., Abu Hasan, Z., Liang, L. 2014. Estimation of missing rainfall data using GEP: Case Study of Raja River, Alor Setar, Kedah. Lecture Notes Artificul Inteligence, Article ID 716398: 1-5.

Coulibaly, P., Evora, N. D. 2007. Comparison of neural network methods for infilling missing daily weather records. Journal of Hydrology, 341(1–2): 27–41.

Dastorani, T. M., Moghadamnia, A., Piri, J., Ramirez, M. R. 2010. Application of ANN and ANFIS models for reconstructing missing flow data. Environmental Monitoring and Assessment, 166: 421-434.

Dorado, J., Rabunal, J. R., Pazos, Rivero, A., Santos, D., Puertas, J. 2003. Prediction and modeling of the rainfall–runoff transformation of a typical urban basin using ANN and GP. Applied Artificial Intelligence, 17: 329–343.

Geerts, B. 2003. Empirical estimation of the monthly-mean daily temperature range. Theoretical and Applied Climatology, 74(3–4): 145–165.

Golabi,  M.,  Akhondi,  A.  Radmanesh,  F. 2013.  Comparison of performance of different artificial neural network algorithms in seasonal modeling Case study; Selected stations in Khuzestan province. Applied Geosciences Research, 30: 169-151. (In Farsi)

Ghorbani, M., Khatibi, R., Aytek, A., Makarynskyy, O. 2010. Sea water level forecasting using genetic programming and artificial neural networks. Computer and Geoscience, 36 (5): 620- 627.

Hamel, L. 2009. Knowledge Discovery with Support Vector Machines, Hoboken, N.J. John Wiley.

Hong, W. C., Pai, P. F. 2007. Potential assessment of the support vector regression technique in rainfall forecasting. Water Resources Managment, 21(2): 495–513.

Isazadeh, M., Ahmadzadeh, H., Ghorbani, M. A. 2016. Assessment of kernel functions performance in river flow estimation using support vector machine. Journal of Water and Soil Conservation, 23(3): 89- 69.

Jeffrey, S. J., Carter, J. O., Moodie, K. B., Beswick, A. R. 2001. Using spatial interpolation to construct a comprehensive archive of Australian climate data. Environment Modell Softwere, 16(4): 309–330.

Kalra, R., Deo, M. C. 2007. Genetic programming to retrieve missing information in wave records along the west coast of India. Applied Ocean Research, 29(3): 99-111.

Kashani, M. H., Dinpashoh, Y. 2012. Evaluation of efficiency of different estimation methods for  missing  climatological data.  Stochastic Environmental Research and Risk Assessment A, 26: 59–71.

Khorsandi, Z., Mahdavi, M., Salajeghe, A., Eslamian, S. S. 2011. Neural network application for monthly precipitation data reconstruction. Journal of Environmental Hydrology, 19: 1-12.

Koza, J. R. 1992. Genetic programming: On the programming of computers by means of natural selection. Cambridge, MA: MIT Press.

Li, X., Li, L., Wang, X., Jiang, F. 2013. Reconstruction of hydrometeorological time series and its uncertainties for the Kaidu River Basin using multiple data sources. Theoretical and Applied Climatology, 113: 45–62.

Lin, G. F., Chen, G. R., Huang, P. Y. 2010. Effective typhoon characteristics and their effects on hourly reservoir inflow forecasting. Advance Water Resource, 33(8): 887– 898.

Lin, G. F., Chou, Y. C., Wu, M. C. 2013. Typhoon flood forecasting using integrated two-stage support vector machine approach. Journal of Hydrology, 486: 334– 342.

Linacre, E. 1992. Climate Data and Resources – A Reference and Guide, Routledge. Lon and NY.

Maity, R., Bhagwat, P. P., Bhatnagar, A. 2010. Potential of support vector regression for prediction of monthly streamflow using endogenous property. Hydrological Processes, 24(7): 917–923.

Nourani, V., Kisi, O., Komasi, M. 2011. Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Jouranl of Hydrology, 402: 41– 59.

Rabunal, J. R., Puertas, J., Suarez, J., Rivero, D. 2007. Determination of the unit hydrograph of a typical urban basin using genetic programming and artificial neural networks. Hydrological Processes, 21: 476– 485.

Ramos-Calzado, P., Gomez-Camacho, J., Perez-Bernal, F., Pita-Lopez, M.F. 2008. A novel approach to precipitation series completion in climatological datasets: application to Andalusia. International of Journal Climatology, 28(11): 1525–1534.

Sette, S., Boullart, L. 2001. Genetic programming: principles and applications. Engineering Applications of Artificul Intelligence, 14: 727– 736.

Solgi, A., Zarei, H., Shehnidarabi, M., Alidadis, A. 2017. Monthly precipitation forecast using gene expression and backup vector machine programming models. Journal of Applied Geosciences Research, 50: 91-103:

Sivapragasam, C., Maheswaran, R., Veena, V. 2008. Genetic programming approach for flood routing in natural channels. Hydrolgy Processes, 22: 623–628.

Tardivo, G., Berti, A. 2012. A dynamic method for gap filling in daily temperature datasets. Journal of Applied Meteorology and Climate, 51: 1079–1086.

Teegavarapua, R. S. V., Chandramouli, V. 2005. Improved weighting methods, deterministic and stochastic data-driven models for estimation of missing. Journal of Hydrology, 312: 191-206.

Ustoorikar, K., Deo, M. C. 2008. Filling up gaps in wave data with genetic programming. Marine Structure, 21:177-195.

Vapnik, V. N. 1998. Statistical Learning Theory. Wiley, NY, 740 p.

Vicente-Serrano, S. M., Beguería, S., López-Moreno, J. I., García-Vera, M. I., Stepanek, P. 2010. A complete daily precipitation database for northeast Spain: reconstruction, quality control, and homogeneity. International of Journal Climatology, 30(8): 1146-1163.

Vieux, B. E. 2001. Distributed Hydrologic Modeling using GIS. In: Distributed Hydrologic Modeling Using GIS. Water, Science and Technology Library, 38: 217-238.

Whigham, P. A, Crapper, P. F. 2001. Modelling rainfall runoff using genetic programming. Math Computing, 33: 707–721.

Wu, J., Liu, M., Jin, L. 2010. Least square support vector machine ensemble for daily rainfall forecasting based on linear and nonlinear regression. Advances in Neural Network Research and Applications. Lecture Notes of Electrnic Engineer, 67(1): 55–64.

Xia, Y. L., Fabian, P., Stohl, A., Winterhalter, M. 1999. Forest climatology: Estimation of missing values for Bavaria, Germany. Agriculture Forest Meteorology, 96 (1–3): 131–144.

Yu, P. S., Chen, S. T., Chang, I. F. 2006. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328: 704-716.