Dağlık Havzalarda Uydu Kar Verisi ve Dalgacık Sinir Ağı Tabanlı Olasılıklı Akım Modelleme Yaklaşımı

Öz

Kar baskın havzalardaki akarsu akım tahminleri, uygun arazi kar verilerinin sınırlı oluşu ve kar fiziğinin oldukça karmaşık olması nedeniyle genellikle zorlayıcı bir konudur. Bu çalışmanın temel amacı hem girdilerin erişilebilirliğini hem de model yapısının basitliğini göz önünde bulundurarak alternatif bir modelleme çözümü önermektir. Önerilen Dalgacık Sinir Ağı (DSA) modeli yaklaşımı, nehir akımları üretmek için olasılıklı karla kaplı alanları girdi alarak dağlık havzalarda olasılıklı akım tahminleri üretebilmektedir. Girdi verilerinin erişilebilirliği adına, MODIS'in bulutsuz görüntülerinden kar olasılığı haritaları üretilmektedir. DSA modeli, gözlenmiş hidro-meteorolojik verilerle eğitilmiş ve test edilmiştir. Ayrıca, Çok-Katmanlı Perseptron Modeli (ÇKPM) de kıyaslama modeli olarak kullanılmıştır. Yaklaşım, Fırat Nehri'nin ana kolu olarak büyük önem taşıyan Murat Nehri'nin kar baskın üst havzasında (1559 ila 3508 m yükseklikte) test edilmiştir. Sonuçlara göre, DSA yaklaşımı ilgi alanındaki kar dağılımını tespit ederek olasılıklı akım tahminleri üretme imkânı sağlamaktadır.

Anahtar Kelimeler

• Kar erimesi modelleme
• Dalgacık Sinir Ağı
• Fırat Nehri havzası
• Akım tahmini
• Uydu kar verisi

PROBABILISTIC RUNOFF MODELING APPROACH IN MOUNTAINOUS BASINS BASED ON SATELLITE SNOW DATA AND WAVELET NEURAL NETWORK

Öz

Streamflow prediction is often a challenging issue for snow dominated basins where proper in-situ snow data might be limited and the snow physics is highly complex. The main aim of this study is to propose an alternative modeling solution by considering both accessibility of the inputs and simplicity of the model structure. We propose Wavelet Neural Network (WNN) model approach which takes probabilistic snow cover area in order to produce probabilistic streamflow in the mountainous basins. For the sake of the accessibility of the input data, snow probability maps are produced from cloud-free images of MODIS. The WNN model is trained and tested with observed hydro-meteorological data. Also, MultiLayer Perceptron Model (MLP) is used as a benchmark model. The approach is tested in a snow-dominated headwater (in altitude from 1559 to 3508 m) of Murat River which has a great importance as being one of the main tributaries of Euphrates River. According to the results, the approach is capable of detecting snow distribution in the area of interest and WNN is promising to generate probabilistic streamflow predictions. 

Anahtar Kelimeler

• Snowmelt modeling
• Wavelet Neural Network
• Euphrates River Basin
• Streamflow forecasting
• Satellite snow data

Kaynakça

1. 1. Adamowski, J., Chan, H.F. (2011) A wavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology, 407(1-4), 28-40. doi:10.1016/j.jhydrol.2011.06.013
2. 2. Adeli, H., Jiang, X. (2006) Dynamic fuzzy wavelet neural network model for structural system identification. Journal of Structural Engineering, 132(1), 102-111. doi: 10.1061/(ASCE)0733-9445(2006)132:1(102)
3. 3. Al-geelani, N.A., Piah, M.A.M., Shaddad, R.Q. (2012) Characterization of acoustic signals due to surface discharges on HV glass insulators using wavelet radial basis function neural networks, Applied Soft Computing, 12(4), 1239-1246. doi:10.1016/j.asoc.2011.12.018
4. 4. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000) Artificial neural networks in hydrology. I: Preliminary concepts, Journal of Hydrologic Engineering, 5(2), 115-123. doi:10.1061/(ASCE)1084-0699(2000)5:2(115)
5. 5. Chen, Y., Yang, B., Dong, J. (2006). Time-series prediction using a local linear wavelet neural network. Neurocomputing, 69(4-6), 449-465. doi:10.1016/j.neucom.2005.02.006
6. 6. Dale, M., Wicks, J., Mylne, K., Pappenberger, F., Laeger, S., Taylor, S. (2014) Probabilistic flood forecasting and decision-making: an innovative risk-based approach, Natural Hazards, 70(1), 159-172. doi:10.1007/s11069-012-0483-z
7. 7. Daliakopoulos, I.N., Tsanis, I.K. (2016) Comparison of an artificial neural network and a conceptual rainfall–runoff model in the simulation of ephemeral streamflow, Hydrological Sciences Journal, 61(15), 2763-2774. doi:10.1080/02626667.2016.1154151
8. 8. Daubechies, I. (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics, Philadelphia, Pennsylvania.

9. 9. Jiang, X., Adeli, H. (2005) Dynamic wavelet neural network model for traffic flow forecasting. Journal of Transportation Engineering, 131(10), 771-779. doi:10.1061/(ASCE)0733-947X(2005)131:10(771)
10. 10. Graf, R., Zhu, S., Sivakumar, B. (2019) Forecasting river water temperature time series using a wavelet–neural network hybrid modelling approach. Journal of Hydrology, 578, 124115. doi:10.1016/j.jhydrol.2019.124115
11. 11. Fahimi, F., Yaseen, Z.M., El-shafie, A. (2017) Application of soft computing based hybrid models in hydrological variables modeling: a comprehensive review, Theoretical and Applied Climatology, 128(3-4), 875-903. doi: 10.1007/s00704-016-1735-8
12. 12. Finger, D., Vis, M., Huss, M., Seibert, J. (2015) The value of multiple data set calibration versus model complexity for improving the performance of hydrological models in mountain catchments, Water Resources Research, 51(4), 1939–1958. doi:10.1002/2014WR015712
13. 13. Fundel, F., Zappa, M. (2011) Hydrological ensemble forecasting in mesoscale catchments: Sensitivity to initial conditions and value of reforecasts, Water Resources Research, 47(9), W09520. doi:10.1029/2010WR009996
14. 14. Hagan, M.T., Menhaj, M.B. (1994) Training feedforward networks with the Marquardt algorithm, IEEE Transactions on Neural Networks, 5(6), 989-993. doi:10.1109/72.329697
15. 15. Hall, D.K., Riggs, G.A., Salomonson, V.V., DiGirolamo, N.E., Bayr, K.J. (2002) MODIS snow-cover products, Remote Sensing of Environment, 83(1-2), 181-194. doi:10.1016/S0034-4257(02)00095-0
16. 16. Hall, D.K., Riggs, G.A., Salomonson, V.V. (2006) MODIS snow and sea ice products. Editors: Qu JJ, Gao W, Kafatos M, Murphy RE, Salomonson VV. Earth Science Satellite Remote Sensing, 154-181, Springer-Verlag Press, Berlin, Heidelberg, Germany.
17. 17. Hall, D.K., Riggs, G.A. (2007) Accuracy assessment of the MODIS snow products, Hydrological Processes, 21(12), 1534-1547. doi:10.1002/hyp.6715
18. 18. Haykins, S. (2009) Neural Networks and Learning Machines. 3rd Ed., Pearson Prentice Hall USA.
19. 19. Jörg-Hess, S., Griessinger, N., Zappa, M. (2015) Probabilistic forecasts of snow water equivalent and runoff in mountainous areas, Journal of Hydrometeorology, 16(5), 2169-2186. doi:10.1175/JHM-D-14-0193.1
20. 20. Krajčí, P., Holko, L., Perdigão, R.A., Parajka, J. (2014) Estimation of regional snowline elevation (RSLE) from MODIS images for seasonally snow covered mountain basins, Journal of Hydrology, 519, 1769–1778. doi:10.1016/j.jhydrol.2014.08.064
21. 21. Maier, H.R., Dandy, G.C. (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications, Environmental Modelling & Software, 15(1), 101-124. doi:10.1016/S1364-8152(99)00007-9
22. 22. Maier, H.R., Jain, A., Dandy, G.C., Sudheer, K.P. (2010) Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions, Environmental Modelling & Software, 25(8), 891-909. doi:10.1016/j.envsoft.2010.02.003
23. 23. Pappenberger, F., Beven, K.J., Hunter, N.M., Bates, P.D., Gouweleeuw, B.T., Thielen, J., De Roo, A.P.J. (2005) Cascading model uncertainty from medium range weather forecasts (10 days) through a rainfall-runoff model to flood inundation predictions within the European Flood Forecasting System (EFFS), Hydrology & Earth System Sciences, 9, 381–393. doi:10.5194/hess-9-381-2005
24. 24. Parajka, J., Blöschl, G. (2008) The value of MODIS snow cover data in validating and calibrating conceptual hydrologic models, Journal of Hydrology, 358(3-4), 240-258. doi:10.1016/j.jhydrol.2008.06.006
25. 25. Parisi, R., Di Claudio, E.D., Orlandi, G., Rao, B.D. (1996) A generalized learning paradigm exploiting the structure of feedforward neural networks, IEEE Transactions on Neural Networks, 7(6), 1450-1460. doi:10.1109/72.548172
26. 26. Ramos, M.H., van Andel, S.J., Pappenberger, F. (2013) Do probabilistic forecasts lead to better decisions?, Hydrology & Earth System Sciences, 17, 2219–2232. doi:10.5194/hess-17-2219-2013
27. 27. Ritter, A., Muñoz-Carpena, R. (2013) Performance evaluation of hydrological models: Statistical significance for reducing subjectivity in goodness-of-fit assessments, Journal of Hydrology, 480, 33-45. doi:10.1016/j.jhydrol.2012.12.004
28. 28. Solomatine, D.P. (2002) Data-driven modelling: paradigm, methods, experiences, 5th International Conference on Hydroinformatics, 01-05 July, Cardiff, United Kingdom.
29. 29. Şensoy, A., Uysal, G. (2012) The value of snow depletion forecasting methods towards operational snowmelt runoff estimation using MODIS and Numerical Weather Prediction Data, Water Resources Management, 26(12), 3415-3440. doi:10.1007/s11269-012-0079-0
30. 30. Şorman, A.A., Şensoy, A., Tekeli, A.E., Şorman, A.Ü., Akyürek, Z. (2009) Modelling and forecasting snowmelt runoff process using the HBV model in the eastern part of Turkey, Hydrological Processes, 23(7), 1031-1040. doi:10.1002/hyp.7204
31. 31. Şorman, A.A., Uysal, G., Şensoy, A. (2019) Probabilistic snow cover and ensemble streamflow estimations in the Upper Euphrates Basin, Journal of Hydrology and Hydromechanics, 67(1), 82-92. doi:10.2478/johh-2018-0025
32. 32. Şorman, A.A., Yamankurt, E. (2011) Modified satellite products on snow covered area in upper Euphrates basin, Turkey, European Geosciences Union General Assembly 2011, 03 – 08 April, Vienna, Austria.
33. 33. Tekeli, A.E., Akyürek, Z., Şorman, A.A., Şensoy, A., Şorman, A.Ü. (2005) Using MODIS snow cover maps in modeling snowmelt runoff process in the eastern part of Turkey, Remote Sensing of Environment, 97(2), 216-230. doi:10.1016/j.rse.2005.03.013
34. 34. Uysal, G., Şensoy, A., Şorman, A.A. (2016) Improving daily streamflow forecasts in mountainous Upper Euphrates basin by multi-layer perceptron model with satellite snow products, Journal of Hydrology, 543, 630-650. doi:10.1016/j.jhydrol.2016.10.037
35. 35. Verbunt, M., Walser, A., Gurtz, J., Montani, A., Schär, C. (2007) Probabilistic flood forecasting with a limited-area ensemble prediction system: Selected case studies, Journal of Hydrometeorology, 8(4), 897-909. doi:0.1175/JHM594.1
36. 36. World Meteorological Organization (2008) Guide to Hydrological Practices. Volume I: Hydrology–From Measurement to Hydrological Information, WMO-No. 168, Geneva, Switzerland.
37. 37. Zhao, Y., Taylor, J.S., Chellam, S. (2005) Predicting RO/NF water quality by modified solution diffusion model and artificial neural networks, Journal of Membrane Science, 263(1-2), 38-46. doi:10.1016/j.memsci.2005.04.004