ارزیابی توانایی یک روش آموزش ماشین در تخمین حداکثر دبی سیلاب ناشی از شکست سد

نویسندگان

1 دانشجوی دکتری سازه‌های آبی، گروه علوم و مهندسی آب دانشگاه فردوسی مشهد، ایران

2 گروه علوم و مهندسی آب دانشگاه فردوسی مشهد، ایران.

چکیده

در این مقاله توانایی روش آموزش ماشین Support Vector Machine (SVM) در پیش بینی حداکثر دبی خروجی سیلاب ناشی از شکست سدهای خاکی بررسی  شده است. پارامترهای ورودی مدل مورد نظر، دو پارامتر مخزن در زمان شکست یعنی ارتفاع آب و حجم آب پشت سد انتخاب شد که برای آموزش این مدل‌ها از داده‌های جمع آوری شده در منابع مختلف استفاده شده است. از مجموع 112 داده، 70 درصد آن جهت آموزش مدل‌ها و 30 درصد آن جهت صحت‌سنجی، به نحوی‌که این دو زیرمجموعه از لحاظ آماری اختلاف معنی داری نداشته باشند، انتخاب شد.  بعد از بررسی چهار مدل SVM، مشخص شد که استفاده از کرنل تابع پایه شعاعی بهترین نتیجه را در تخمین این پدیده حاصل می‌دهد (نتایج آماری این روش در تخمین پدیده مورد نظر با 96/0=R2، 03/0=RMSE و 94/0=R2 و 05/0=RMSE به ترتیب در فاز آموزش و آزمون). مقایسه‌ای نیز بین 6 رابطه تجربی کلاسیک و مدل توصیه شده صورت گرفت که نتایج نشانگر عملکرد ضعیف روابط تجربی در مقایسه با مدل‌ پیشنهادی است. در نهایت با توجه به اهمیت مدیریت هنگام شکست سد استفاده از روش آموزش ماشین پیشنهادی برای تخمین مقدار ماکسیمم دبی خروجی از سد پیشنهاد می‌شود.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluation of PredictivePotential of a learning Machine Method on Peak Outflow Due to Embankment Dam Failure

نویسندگان [English]

  • Hamed Farhadi 1
  • kazem Esmaili 2
1 PhD student of hydraulic structures, water science and engineering department, Ferdowsi University Of Mashhad
2 - Associate Professor, water science and engineering department, Ferdowsi University of Mashhad,
چکیده [English]

In this study, the potential of Support Vector Machine (SVM (in the prediction of peak outflow due to dam failure was evaluated. Huge volume deposited behind dam may cause a large casualty in case of sudden release of it to downstream. Head and volume of water at the time of failure were considered as inputs to SVM model. To train these models, 70% of 112 gathered data from literature was used as training subset and the rest 30% was used to test the model as test subset, at the same time these two subsets were selected in a way to be statistically similar. After studying four SVM models with different kernel functions, i.e. Linear, Polynomial, Radial Basis Function and Sigmoid, it was found that SVM with Radial Basis Kernel function outperforms other models. Results of the statistical evaluation of the proposed model are satisfying with R2=0.96, RMSE=0.03 for training phase and R2=0.94, RMSE=0.05 for the test phase. A comparison was made between some conventional empirical equations and the proposed model in which results shows proposed SVM model surpasses empirical equations in predicting peak outflow due to embankment dam failure.

کلیدواژه‌ها [English]

  • Learning Machine
  • Artificial Intelligence
  • Dam break
  • Earth dam
  • Flood peak outflow

مراجع

فرهادی، ح.، م. زمردیان. 1391. برآورد ماکسیمم دبی شکست سدهای خاکی و زمان شکست با استفاده از روش SVM، یازدهمین کنفرانس هیدرولیک ایران، ارومیه.
Babaeyan-Amini, A., V. Nourani and H. Hakimzadeh. 2011. Application of artificial intelligence tools to estimate peak outflow from earth dam breach. International Journal of Earth Sciences and Engineering, 4: 243-246.
Bray, M. and D. Han. 2004. Identification of support vector machines for runoff modelling. Journal of Hydroinformatics, 6: 265-280.
Burge, T. 2004. Big Bay Dam: Evaluation of failure. Land Partners Limited Partnership, Hattiesburg, Miss.
Carling, P., I. Villanueva, J. Herget, N. Wright, P. Borodavko and H. Morvan. 2010. Unsteady 1D and 2D hydraulic models with ice dam break for Quaternary megaflood, Altai Mountains, southern Siberia. Global and Planetary Change, 70: 24-34.
Chang, F., L. C. Chang and H. L. Huang. 2002. Real‐time recurrent learning neural network for stream‐flow forecasting. Hydrological Processes, 16: 2577-2588.
Chang, L. C. and F. J. Chang. 2001. Intelligent control for modelling of real‐time reservoir operation. Hydrological processes, 15: 1621-1634.
Chen, S. T. and P. S. Yu. 2007. Pruning of support vector networks on flood forecasting. Journal of Hydrology, 347: 67-78.
Chiang, Y. M., L. C. Chang, and F. J. Chang. 2004. Comparison of static-feedforward and dynamic-feedback neural networks for rainfall–runoff modeling. Journal of hydrology, 290: 297-311.
Coleman, S. E., D. P. Andrews and M. G. Webby. 2002. Overtopping breaching of noncohesive homogeneous embankments. Journal of Hydraulic Engineering, 128: 829-838.
Cortes, C. and V. Vapnik. 1995. Support-vector networks. Machine learning, 20: 273-297.
Dawson, C. and R. Wilby. 2001. Hydrological modelling using artificial neural networks. Progress in physical Geography, 25: 80-108.
Dibike, Y. B., S. Velickov, D. Solomatine, and M. B. Abbott. 2001. Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering, 15: 208-216.
Dixon, B. 2005. Groundwater vulnerability mapping: a GIS and fuzzy rule based integrated tool. Applied Geography, 25: 327-347.
Evans, S. G. 1986. The maximum discharge of outburst floods caused by the breaching of man-made and natural dams. Canadian Geotechnical Journal, 23: 385-387.
FERC. 2006. Report of findings on the overtopping and embankment breach of the upper dam – Taum Sauk Pumped Storage Project. FERC No. 2277, April, 239 p.
Froehlich, D. C. 1995. Peak outflow from breached embankment dam. Journal of Water Resources Planning and Management, 121: 90-97.
Gaucher, J., C. Marche and T. F. Mahdi. 2010. Experimental investigation of the hydraulic erosion of noncohesive compacted soils. Journal of Hydraulic Engineering, 136: 901-913.
Han, D., L. Chan and N. Zhu. 2007. Flood forecasting using support vector machines. Journal of hydroinformatics, 9: 267-276.
Hanson, G., K. Cook and S. Hunt. 2005. Physical modeling of overtopping erosion and breach formation of cohesive embankments. Transactions of the ASAE, 48: 1783-1794.
Hassan, M., M. Morris, G. Hanson and K. Lakhal. 2004. Breach formation: Laboratory and numerical modeling of breach formation. Association of State Dam Safety Officials: Dam Safety.
Hooshyaripor, F. and A. Tahershamsi. 2012. Comparing the performance of neural networks for predicting peak outflow from breached embankments when back propagation algorithms meet evolutionary algorithms. International Journal of Hydraulic Engineering, 1: 55-67.
Hooshyaripor, F., A. Tahershamsi, and S. Golian. 2014. Application of copula method and neural networks for predicting peak outflow from breached embankments. Journal of Hydro-environment Research, 8: 292-303.
Johnson, V. M. and L. L. Rogers. 1995. Location Analysis in Ground‐Water Remediation Using Neural Networks. Ground Water, 33: 749-758.
Karunanithi, N., W. J. Grenney, D. Whitley and K. Bovee. 1994. Neural networks for river flow prediction. Journal of Computing in Civil Engineering, 8: 201-220.
Liong, S. Y., T. R. Gautam, S. T. Khu, V. Babovic, M. Keijzer and N. Muttil. 2002. Genetic programming: A new paradigm in rainfall runoff modeling1. Journal of the American Water Resources Association, 38: 705-718.
Macdonald, T. C. and J. Langridge-Monopolis. 1984. Breaching charateristics of dam failures. Journal of Hydraulic Engineering, 110: 567-586.
Makkeasorn, A., N. B. Chang and X. Zhou. 2008. Short-term streamflow forecasting with global climate change implications–A comparative study between genetic programming and neural network models. Journal of Hydrology, 352: 336-354.
Mattera, D. S. Haykin. 1999. Support vector machines for dynamic reconstruction of a chaotic system. In: S. Bernhard, lkopf, J.C.B. Christopher and J.S. Alexander (eds). Advances in kernel methods. MIT Press: 211-241
Nayak, P. C., K. Sudheer, D. Rangan and K. Ramasastri. 2004. A neuro-fuzzy computing technique for modeling hydrological time series. Journal of Hydrology, 291: 52-66.
Pierce, M. W., C. I. Thornton, and S. R. Abt. 2009. Predicting peak outflow from breached embankment dams. Journal of Hydrologic Engineering, 15: 338-349.
Ponce, V. M., A. Taher-Shamsi and A. V. Shetty. 2003. Dam-breach flood wave propagation using dimensionless parameters. Journal of Hydraulic Engineering, 129: 777-782.
Ranjithan, S., J. Eheart and J. Garrett. 1993. Neural network‐based screening for groundwater reclamation under uncertainty. Water Resources Research, 29: 563-574.
Sattar, A. M. and B. Gharabaghi. 2015. Gene expression models for prediction of longitudinal dispersion coefficient in streams. Journal of Hydrology, 524: 587-596.
Schölkopf, B., C. Burgest and V. Vapnik. 1995. Extracting support data for a given task. In: Fayyad, U. M. and Uthurusamy, R. (eds.) Proceedings, First International Conference on Knowledge Discovery & Data Mining. Menlo Park, CA: AAAI Press.
Service, S. C. 1981. Simplified Dam-breach Routing Procedure, USDA, Washington DC, Technical Release No. 66 (Rev.1).
Singh, V. P. and P. D. Scarlatos. 1988. Analysis of gradual earth-dam failure. Journal of hydraulic engineering, 114: 21-42.
Sivapragasam, C., R. Maheswaran and V. Venkatesh. 2008. Genetic programming approach for flood routing in natural channels. Hydrological processes, 22: 623-628.
Smith, J. and R. N. Eli. 1995. Neural-network models of rainfall-runoff process. Journal of water resources planning and management, 121: 499-508.
Smola, A. J. 1996. Regression estimation with support vector learning machines. Master's thesis, Technische Universit at Munchen.
Soil Conservation Service .1981. Simplified Dam-breach Routing Procedure. Technical Release No. 66 (Rev.1). USDA, Washington, DC, p. 39.
Tokar, A. S. and P. A. Johnson. 1999. Rainfall-runoff modeling using artificial neural networks. Journal of Hydrologic Engineering, 4: 232-239.
Tsai, C. W. 2005. Flood routing in mild-sloped rivers—wave characteristics and downstream backwater effect. Journal of Hydrology, 308, 151-167.
U.S. Bureau of Reclamation .1982. Guidelines for Defining Inundated Areas downstream from Bureau of Reclamation Dams, Reclamation Planning Instruction No. 82-11, June 15, 1982.
Vaskinn, K. A., A. Lovoll, K. Hoeg, M. Morri, G. Hanson and M. Hassan. 2004. Physical modeling of breach formation: Large scale field tests. Proceedings of the Dam safety.
Vapnik, V. 1995. The Nature of Statistical Learning Theory. Springer.
Wahl, T. 1998. Prediction of embankment dam breach parameters—a literature review and needs assessment. Dam Safety Rep No. DSO-98-004, US Dept. of the Interior, Bur of Reclamation, Denver, CO.
Wang, W. C., K. W. Chau, C. T. Cheng and L. Qiu. 2009. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of hydrology, 374: 294-306.
Whigham, P. and P. Crapper. 2001. Modelling rainfall-runoff using genetic programming. Mathematical and Computer Modelling, 33: 707-721.
Xia, J., B. Lin, R. A. Falconer and G. Wang. 2010. Modelling dam-break flows over mobile beds using a 2D coupled approach. Advances in Water Resources, 33: 171-183.
Xu, Y. and L. Zhang. 2009. Breaching parameters for earth and rockfill dams. Journal of Geotechnical and Geoenvironmental Engineering, 135: 1957-1970.
Yu, P. S., S. T. Chen and I. F. Chang. 2006. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328: 704-716.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار