بررسی کارایی روش‌های ناپارامتریک مبتنی بر تجزیه و تحلیل باقیمانده‌ها و پارامتریک در برآورد عدم قطعیت مدل هیدرولوژیکی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 عضو هیات علمی، دانشگاه گنبد کاووس

2 دانشگاه گنبد کاووس

3 دانشگاه گنبدکاووس

چکیده

به منظور تصمیم‌گیری مناسب جهت اجرای اقدامات مدیریتی نیاز است تا علاوه بر خروجی مدل دامنه عدم قطعیت آن نیز برآورد گردد. در تحقیق حاضر کارایی روش‌های ناپارامتریک LEC (Local Errors and Clustering)، رگرسیون چندک و جنگل تصادفی در برآورد عدم قطعیت مدل یکپارچه HBV در حوضه چهل‌چای استان گلستان بررسی گردید. پس از بهینه‌‌سازی پارامترهای مدل HBV با استفاده از روش تکامل تصادفی جوامع، مدل برای دوره‌های واسنجی و صحت سنجی اجرا و مقادیر باقیمانده‌ها محاسبه گردید. نتایج نشان داد با در نظر گرفتن متغیرهای دبی برآوردی، دبی مشاهداتی، مقدار بارش و مقادیر باقیمانده‌ها در حوضه مورد مطالعه داده‌های ورودی در چهار خوشه فازی قرار می‌گیرند. نتایج برآورد عدم قطعیت نشان داد بزرگترین و کوچکترین مقدار دامنه عدم قطعیت به ترتیب توسط روش‌های LEC در حالتی که توسط ماشین بردار رگرسیون آموزش دیده باشد و روش جنگل تصادفی، بدست آمده است. با توجه به مقادیر شاخص‌های ارزیابی PICP (Prediction Interval Coverage Probability)، MPI (Mean Prediction Interval) و(Average Relative Interval Length) ARIL بهترین عملکرد مربوط به روش رگرسیون چندک و سپس روش LEC در حالتی که آموزش داده نشده است، بود. در مقایسه با روش‌های ناپارامتریک، روش(Generalized Liklihod Uncertainty Estimation)  GLUE با توجه به مقادیر هر سه معیار ارزیابی عملکرد مناسبی نداشت.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The efficiency of nonparametric methods based on residual analizes and parametric method to estimate hydrological model uncertainty

نویسندگان [English]

  • Abolhasan FathAbadi 1
  • Hamed Ruohani 2
  • Seyed Morteza Seyedian 3
1 University of Gonbad Kavoos
2 University of Gonbad Kavoos
3 University of Gonbad Kavoos
چکیده [English]

Despite modern scientific knowledge and computational power in hydrology, the key to properly addressing hydrologic uncertainty remains a critical and challenging one. Here, we applied lumped HBV hydrological model to describe the uncertainty in runoff prediction in Chehl-Chay watershed in Golestan province. We applied a new framework for uncertainty analysis that is rooted on ideas from predicting model residual uncertainty. The uncertainty calculated by local Errors and Clustering (EEC) is compared with estimates from two non parametric methods (quantile regression (QR) and random forest (RF)) and a parametric method (GLUE). Firstly, the model parameters were optimized by Shuffled Complex Evolution approach and model residuals of test data were computed. Fuzzy clustering in EEC is carried out by the fuzzy c-means method and employs four clusters, predictive discharges, observed discharges, rainfall values and residuals in study basin. The results of this case study show that the uncertainty estimates obtained by EES which is trained by SVM gives wider uncertainty band and RF gives narrower uncertainty band. The best overall uncertainty estimates according to the PICP, MPI and ARIL indices were obtained with QR and then EEC. In comparison with non-parametric, with respct to all indices nonparametric methods had better performance than GLUE method.

کلیدواژه‌ها [English]

  • Rainfall -runoff
  • Random forest
  • quantile regression
  • GLUE
AghaKouchak, A. and Habib, E. (2010). Application of a conceptual hydrologic model in teaching hydrologic processes. Int. J. Eng. Educ. 26,  963–973.
Beven, K.. and Binley. A. (1992). The future of distributed models: Model calibration and uncertainty prediction. Hydrol. Process., 6, 279-298.
Bezdek, J.C. (1974a). Numerical taxonomy with fuzzy sets. Journal of Mathematical Biology, 1: 57–71.
Bezdek, J.C. (1974b). Cluster validity with fuzzy sets. Journal of Cybernetics, 3 (3), 58–72.
Breiman, Leo. (2001). Random forests. Mach. Learn, 45 (1), 5– 32.
Chang, C. H., Yang J.C. and Tung, Y.K. (1993). Sensitivity and uncertainty analysis of a sediment transport models: a global approach. Stochastic Hydrological Hydraulics, 7 (4), 299- 314 .
Dogulu,  N., López López, P., Solomatine, D. P., Weerts, A. H. and Shrestha, D. L. (2015). Estimation of predictive hydrologic uncertainty using the quantile regression and UNEEC methods and their comparison on contrasting catchments. Hydrol. Earth Syst. Sci., 19, 3181–3201.
Evin, G., Thyer, M. Kavetski, D. McInerney D. and Kuczera, G. (2014). Comparison of joint versus postprocessor approaches for hydrological uncertainty estimation accounting for error autocorrelation and hetero-scedasticity. Water Resour. Res, 50 (3), 2350– 2375.
Fukuyama, Y. and Sugeno, M. (1989). A new method of choosing the number of clusters for the fuzzy c-means method. Proceedings of Fifth Fuzzy Systems Symposium, pp. 247–250 (in Japanese)
Houska, T., Multsch, P., Kraft, H., Frede, G. and Breuer, L. (2014). Monte Carlo-Based calibration and uncertainty analysis of a coupled plant growth and hydrological model. Biogeosciences, 11, 2069-2082.
Khu, S.T. and Werner, M.G.F. (2003). Reduction of monte-carlo simulation runs for uncertainty estimation in hydrological modeling. Hydrology and Earth System Sciences. 7 (5),  680-692.
Koenker, R. (2005). Quantile Regression, Cambridge University Press.
Koenker, R. and Bassett, J.r. (1978). Regression Quantiles, Econometrica, 1, 33–50.
López López, P., Verkade, J.S., Weerts, A .H. and Solomatine, D.P. (2014). Alternative configurations of quantile regression for estimating predictive uncertainty in water level forecasts for the Upper Severn River: a comparison. Hydrol. Earth Syst. Sci. Discuss. 11 (4), 3811 – 3855.
Malone, B.P., McBratney, A.B. and Minasny, B. (2011). Empirical estimates of uncertainty for mapping continuous depth functions of soil attributes. Geoderma, 160 (3– 4), 614-626.
Matott, L.S., Babendreier, J.E. and Purucker, S.T. (2009). Evaluating uncertainty in integrated environmental models: A review of concepts and tools. Water Resources Research, 45, W06421.
Montanari, A. (2011). Uncertainty of Hydrological Predictions. In: Peter Wilderer (ed.) Treatise on Water Science, vol 2. pp. 459–478 Oxford: Academic Press.
Rouhani, H. and Farahi Moghadam, M. (2014). Application  of the Genetic  Algorithm Technique  for  Optimization  of the Hydrologic  Tank and  SIMHHYD Models’ Parameters. Journal Of Range and Watershed Management (Iranian Journal Of Natural Resources). 66(4), 521-533.
 In Farsi).
Shrestha, D. L., and D. P. Solomatine (2006). Machine learning approaches for estimation of prediction interval for the model output , Neural Networks , 19 (2), 225 – 235, doi: 10.1016/ j.neunet. 2006. 01. 012.
Siebert, J. and Vis, M. J. P. (2012). Teachinghydrological modeling with a userfriendly catchment runoff-model software package, Earth Syst. Sci. 16, 3315-3325.
Solomatine, D. P. and Siek, M. B. (2006). Modular learning models in forecasting natural phenomena. Neural Networks, 19(2), 215-224.
Solomatine, D. P. and Shrestha, D. L. (2009). A novel method to estimate model uncertainty using machine learning techniques, Water Re-sour. Res., 45, W00B11.
Walker, W.E., Harremoës, P., Rotmans, J., Van der Sluis, J.P., Van Asselt, M.B.A., Janssen, P. and Krayer von Krauss M.P. (2003). Defining uncertainty a conceptual basis for uncertainty management in model-based decision support. Integrated Assessment, 4 (1), 5-17
Weerts, A. H., Winsemius, H. C. and Verkade, J. S. (2011). Estima-tion of predictive hydrological uncertainty using quantile re-gression: examples from the National Flood Forecasting Sys-tem (England and Wales), Hydrol. Earth Syst. Sci., 15, 255–265.
Xu, T., and Valocchi, A .J.(2015). Data-driven methods to improve base flow prediction of a regional groundwater model. Computers & Geosciences. 85(B), 124–13.