مدلسازی جریان روزانه رودخانه با استفاده از فرامدلهای شبیهساز (مطالعه موردی:رودخانه گاماسیاب)
محورهای موضوعی : مدیریت منابع آبمعصومه زینعلی 1 , محمدرضا گلابی 2 , محمد حسین نیک سخن 3 , محمد رضا شریفی 4
1 - دانشجوی دکتری منابع آب، گروه مهندسی آبیاری و آبادانی؛ پردیس کشاورزی و منابع طبیعی دانشگاه تهران؛ کرج؛ ایران.
2 - دکترای منابع آب، دانشکده مهندسی علوم آب، دانشگاه شهید چمران اهواز، ایران. (نویسنده مسئول)
3 - دانشیار دانشکده محیط زیست، دانشگاه تهران، ایران.
4 - استادیار دانشکده مهندسی علوم آب، دانشگاه شهید چمران اهواز، ایران.
کلید واژه: مدلBN, مدل GEP, گاماسیاب, مدل ANFIS, مدلسازی جریان,
چکیده مقاله :
زمینه و هدف: هدف در ابتدا بیان نمودن تفاوت ها و شناسایی3 مدل به نام های، برنامه ریزی بیان ژن (GEP)، شبکه عصبی فازی (ANFIS) و شبکه بیزین (BN) است و مقایسه آنها با یکدیگر و سوال اساسی تحقیق این است که ایا فرامدل شبیه ساز برتر در این مطالعه می تواند در شرایط کمبود داده و اطلاعات، جایگزین مناسبی برای مدل های مفهومی باشد. روش بررسی: داده های مورد استفاده برای این پژوهش، داده های بارش و جریان روزانه رودخانه گاماسیاب نهاوند در یک دوره 10 ساله 1391-1381 می باشد. برای مرحله پیش بینی یا شبیه سازی از داده های سال آبی 1391-1390 استفاده شده است. یافته ها: در مرحله آموزش و با توجه به ضریب تبیین و پارامتر جذر میانگین مربعات خطا و معیار AIC، مشاهده میشود که در هر 3 مدل، هم در مرحله آموزش و هم در مرحله تست شاهد اختلاف بسیار اندک در مقدار این پارامتر ها هستیم و نتایج هر 3مدل تقریبا با اختلاف بسیار اندک، نزدیک به هم است و تقریبا برتری نسبی مدل GEP را می توان مشاهده کرد. بحث و نتیجه گیری: نتایج بیانگر آن است که فرامدل[1] شبیهساز بیان ژن توانایی خوبی برای شبیهسازی و پیش بینی جریان روزانه رودخانه دارد و این فرامدل شبیه ساز، می تواند در شرایط کمبود داده و اطلاعات، جایگزین مناسبی برای مدل های مفهومی باشد. علاوه بر این سرعت اجرای مدل برنامه ریزی بیان ژن نسبت به بقیه مدلها بیشتر بوده و در زمان کوتاهی قادر به ارائه نتایج بوده است. [1]- Meta Model
Background and Aim: The aim is first to express the differences and identify three models, namely, Gene Expression Programming (GEP), Neural-Fuzzy Network (ANFIS), and Bayesian Network (BN), and compare them with each other. Furthermore, the research's central question is whether the superior simulation meta-modal in this study can be a suitable alternative to conceptual models in the conditions of lack of data and information. Methods: The data used for this study are the daily rainfall and flow data of the Gamasiab Nahavand River in 10 years from 2002 to 2012. For the prediction or simulation stage, the data of the blue year 2012-2011 have been used. Results: In the training phase and according to the coefficient of explanation and the square root of the mean squares error and the AIC criterion, it is observed that in all three models, both in the training phase and in the test phase, we see a minimal difference in the amount of these parameters. Moreover, all three models' results are close to each other with almost a minimal difference, and almost the relative superiority of the GEP model can be seen. Discussion & Conclusion: The results indicate that the simulator meta-model of gene expression has an excellent ability to simulate and predict the river's daily flow, this simulation meta-model can be a suitable alternative to models in the absence of data and information. Be conceptual. Also, the speed of implementation of the gene expression programming model was faster than other models and was able to provide results in a short time.
- Ghorbani, M, A., Kisi, O., Aalinezhad, M, A., 2010. A probe into the chaotic nature of daily stream flow time series by correlation dimension and largest Lyapunov methods. Applied Mathematical Modelling. 34(12):4050-4057.
- DanandehMehr, A., Kahya, E. and Yerdelen, C., 2014. Linear Genetic Programming Application for Successive-Station Monthly Stream Flow Prediction, Journal of Computers and Geosciences, 70: 63-72.
- Shoaib, M., Shamseldin, A. Y., Melville, B. W., and Khan, M. M., 2015. Runoff forecasting using hybrid wavelet gene expression programming (WGEP) approach; J. Hydrol.527: 326–344.
- Karimi, S., Shiri, J., Kisi, O., and Shiri, A.A., 2015. Short-term and long-term streamflow prediction by using 'wavelet–gene expression' programming approach. ISH Journal of HydraulIc EngIneerIng 1-15.
- Singh, G., Panda, R. K., and Lamers, M., 2015. Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques, J. of hydroinformatics. vol.17 (1). 56-74.
- Noori, N., Kalin, L., 2016. Coupling SWAT and ANN models for enhanced daily streamflow prediction, J. of Hydrology. 533: 141–151.
- Ghorbani, M. A., Dehghani, R., 2015. Application of Bayesian Neural Networks, Support Vector Machines and Gene Expression Programming Analysis of Rainfall - Runoff Monthly (Case Study: Kakarza River). Irrigation Science and Engineering. 39(2), 125-138.
- Naeimi Kalourazi, Z., Ghorbani, Kh., Salarijazi, M., Dehghani, A.A., 2016. Investigation of effect of basin’s physiographic and climatic parameters in seasonal river flow simulation. Ecohydrology. 3(4), 545-556.
- Moatamednia, M., Nohegar, A., Malekian, A., Saberi, M., Karimi, K., 2017. Runoff prediction using intelligent models. Ecohydrology. 4(4), 955-968.
- Ross, T. J., 1995. Fuzzy logic with engineering application. McGraw Hill Inc., USA.
- Jang, J.S.R., Sun, C. T., and Mizutani, E., 1997. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence.Prentice-Hall International.New Jersey.
- Meshkani, A., Nazemi, A., 2009. Introduction to Data Mining. Ferdowsi University Publishing Institute, Mashhad. 456 pages.
- Singh, VIP., Translation: Najafi, M.R., 2002. Hydrological systems of rainfall-runoff modeling. Volume 1. University of Tehran Press. First Edition. 578 pages.
- Danandehmehr, A., Majdzadeh Tabatabai, M. R., 2010. Prediction of Daily Discharge Trend of River Flow Based on Genetic Programming. Journal of Water and Soil. 24(2), 325-333.
- Ferreira, C., 2006. Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence (Studies in Computational Intelligence). ed n, editor. Springer-Verlag New York, Inc. Secaucus, NJ, USA.
- Ferreira, C., 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex Syst, 13:87-129.
- MacKay, D.J.C., 1992. A Practical Bayesian Framework for Backpropagation Networks " Neural Computation. 4: 48-472.
- Kingston, G. B., 2005. Lambert M F and Maier H R. Bayesian training of artificial neural networks used for water resources modeling. Water Resources Research. 41(W12409).
- Nash, J. E., and Sutcliffe, J.V., 1970. River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology. 10 (3), 282–290.
_||_
- Ghorbani, M, A., Kisi, O., Aalinezhad, M, A., 2010. A probe into the chaotic nature of daily stream flow time series by correlation dimension and largest Lyapunov methods. Applied Mathematical Modelling. 34(12):4050-4057.
- DanandehMehr, A., Kahya, E. and Yerdelen, C., 2014. Linear Genetic Programming Application for Successive-Station Monthly Stream Flow Prediction, Journal of Computers and Geosciences, 70: 63-72.
- Shoaib, M., Shamseldin, A. Y., Melville, B. W., and Khan, M. M., 2015. Runoff forecasting using hybrid wavelet gene expression programming (WGEP) approach; J. Hydrol.527: 326–344.
- Karimi, S., Shiri, J., Kisi, O., and Shiri, A.A., 2015. Short-term and long-term streamflow prediction by using 'wavelet–gene expression' programming approach. ISH Journal of HydraulIc EngIneerIng 1-15.
- Singh, G., Panda, R. K., and Lamers, M., 2015. Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques, J. of hydroinformatics. vol.17 (1). 56-74.
- Noori, N., Kalin, L., 2016. Coupling SWAT and ANN models for enhanced daily streamflow prediction, J. of Hydrology. 533: 141–151.
- Ghorbani, M. A., Dehghani, R., 2015. Application of Bayesian Neural Networks, Support Vector Machines and Gene Expression Programming Analysis of Rainfall - Runoff Monthly (Case Study: Kakarza River). Irrigation Science and Engineering. 39(2), 125-138.
- Naeimi Kalourazi, Z., Ghorbani, Kh., Salarijazi, M., Dehghani, A.A., 2016. Investigation of effect of basin’s physiographic and climatic parameters in seasonal river flow simulation. Ecohydrology. 3(4), 545-556.
- Moatamednia, M., Nohegar, A., Malekian, A., Saberi, M., Karimi, K., 2017. Runoff prediction using intelligent models. Ecohydrology. 4(4), 955-968.
- Ross, T. J., 1995. Fuzzy logic with engineering application. McGraw Hill Inc., USA.
- Jang, J.S.R., Sun, C. T., and Mizutani, E., 1997. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence.Prentice-Hall International.New Jersey.
- Meshkani, A., Nazemi, A., 2009. Introduction to Data Mining. Ferdowsi University Publishing Institute, Mashhad. 456 pages.
- Singh, VIP., Translation: Najafi, M.R., 2002. Hydrological systems of rainfall-runoff modeling. Volume 1. University of Tehran Press. First Edition. 578 pages.
- Danandehmehr, A., Majdzadeh Tabatabai, M. R., 2010. Prediction of Daily Discharge Trend of River Flow Based on Genetic Programming. Journal of Water and Soil. 24(2), 325-333.
- Ferreira, C., 2006. Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence (Studies in Computational Intelligence). ed n, editor. Springer-Verlag New York, Inc. Secaucus, NJ, USA.
- Ferreira, C., 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex Syst, 13:87-129.
- MacKay, D.J.C., 1992. A Practical Bayesian Framework for Backpropagation Networks " Neural Computation. 4: 48-472.
- Kingston, G. B., 2005. Lambert M F and Maier H R. Bayesian training of artificial neural networks used for water resources modeling. Water Resources Research. 41(W12409).
- Nash, J. E., and Sutcliffe, J.V., 1970. River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology. 10 (3), 282–290.