Günlük Ortalama Akımların Yapay Sinir Ağları Metodu ile Taşkın Öteleme Hesabında Kullanılması

Yıl 2021, Cilt: 9 Sayı: 5, 2052 - 2066, 31.10.2021

Metin Sarıgöl

https://doi.org/10.29130/dubited.877756

Cited By: 1

Öz

Bu çalışmada, Büyük Menderes Havzası’ndaki Menderes Nehri üzerinde yer alan E07A043 Ertuğrul ve D07A115 Yenice Regülatör Girişi Akım Gözlem İstasyonlarına (AGİ) ait günlük ortalama hidrograf verileri kullanılmıştır. Bu veriler Yapay Sinir Ağları Metodu kullanılarak eğitim ve test aşamalarından geçirilmiş, kurulan bu modele 2015 yılındaki taşkın verileri uygulanarak Taşkın Öteleme hesapları yapılmıştır. Elde edilen sonuçlar, hem ölçülmüş değerlerle hem de Yapay Sinir Ağları Metodu sonuçları ile karşılaştırılmıştır. Karşılaştırma analizinde Belirlilik Katsayısı (R2), Hataların Ortalama Karekökü (HOK) değerleri hesaplanmıştır. Sonuçta, günlük akım verilerinin uygulandığı Yapay Sinir Ağları Metodu ile yapılan tahmin sonuçlarının oldukça iyi sonuçlar verdiği, bir sonraki yıla ait taşkın öteleme sonuçlarının ise iyi sayılabilecek bir düzeyde olduğu tespit edilmiştir.

Anahtar Kelimeler

Taşkın Ötelenmesi, Yapay Sinir Ağları, Taşkın, Büyük Menderes

Use of Daily Average Flows in Flood Routing Calculation with Arficial Neural Network Method

Öz

In this study, daily mean hydrograph data of E07A043 Ertuğrul and D07A115 Yenice Regulator Girişi Stream Gauging Stations (SGS) located on Menderes River in Buyuk Menderes Basin were used. These data were passed through the training and testing stages using the Artificial Neural Networks Method, Flood Routing calculations were made by applying the flood data of 2015 to this model. The results were compared with both Artificial Neural Networks Method and the measured values results. At the end of comparative analysis, Root Mean Square Errors (RMSE) and Coefficient of Determination (R2) values were calculated. In conclusion, it has been determined that the results of the predictions performed by Artificial Neural Networks Method, where the daily mean hydrograph data is applied, yielded very good results, and the flood routing results for the next year are at a level that can be considered good.

Anahtar Kelimeler

Flood routing, Artifical neural network, Flood, Büyük Menderes

Kaynakça

• [1] M. R. Hassanvand, H. Karami, and S. F. Mousavi, “Investigation of neural network and fuzzy inference neural network and their optimization using meta-algorithms in river flood routing,” Natural Hazards, vol. 94, pp. 1057–1080, 2018.
• [2] P. K. T. Nguyen and L. H. C. Chua, “The data-driven approach as an operational real-time flood forecasting model,” Hydrol Process, vol. 26, pp. 2878–2893, 2012.
• [3] X. Yuan, X. Zhang and F.Tian, “Research and application of an intelligent networking model for flood forecasting in the arid mountainous basins, ” J Flood Risk Management, vol. 13, pp. e12638, 2020.
• [4] R. Pant, S. Thacker, J. W. Hall, D. Alderson and S. Barr, “Critical infrastructure impact assessment due to flood exposure,” Journal of Flood Risk Management, vol.11, no. 1,pp. 22–33, 2018. [5] M. K. Lindell and C. S. Prater, “Assessing community impacts of natural disasters,” Natural Hazards Review, vol. 4, no. 4, pp. 176–185, 2003.
• [6] W. Du, G. J. FitzGerald, M. Clark and X. Hou, “Health impacts of floods,” Prehospital and Disaster Medicine, vol. 25, no. 3, pp. 265–272, 2010.
• [7] S. N. Jonkman and J. K. Vrijling, “Loss of life due to floods,” Journal of Flood Risk Management, vol.1, no. 1, pp. 43–56, 2008.
• [8] Z. W. Kundzewicz, S.Kanae, S. I. Seneviratne, J. Handmer, N. Nicholls, P. Peduzzi and B. Sherstyukov, “Flood risk and climate change: Global and regional perspectives,” Hydrological Sciences Journal, vol. 59, no. 1, pp. 1–28, 2014.
• [9] Z. Sen, H. A. Khiyami, S. G. Al-Harthy, F. A. Al-Ammawi, A. B. Al- Balkhi, M. I. Al-Zahrani, and H. M. Al-Hawsawy, “Flash flood inundation map preparation for wadis in arid regions,” Arabian Journal of Geosciences, vol. 6, no. 9, pp. 3563–3572, 2013.
• [10] Tu. T Van, D. M Duc, N. M. Tung and V. D. Cong, “Preliminary assessments of debris flow hazard in relation to geological environment changes in mountainous regions, North Vietnam,” Vietnam Journal of Earth Sciences, vol. 38, no. 3, pp. 277–286, 2016.
• [11] A. Guven, “Linear genetic programming for time-series modelling of daily flow rate,” Journal of Earth System Science, vol. 118, no. 2, pp. 137–146, 2009.
• [12] Z. M. Yaseen, A. El-shafie, O. Jaafar, H. A. Afan and K. N. Sayl, “Artificial intelligence based models for stream-flow forecasting: 2000–2015, ” Journal of Hydrology, vol. 530, pp. 829–844, 2015.
• [13] M. Sarıgöl, “Adana İli Karaisalı İlçesi Seyhan Havzası’nda Taşkın Ötelenmesi Yöntemlerinin Karşılaştırılması ve Analizi, Muskingum Yönteminin Sürtünme Katsayısına (n) Bağlı Performans Analizi, ” Bartın University International Journal of Natural and Applied Sciences, vol. 2, no. 2, pp. 129-137, 2019.
• [14] T. A. Birkland, R. J. Burby, D. Conrad, H. Cortner and W. K. Michener, “River ecology and flood hazard mitigation,” Nat Hazards Rev, vol. 4, no. 1, pp. 46–54, 2003.
• [15] S. D. Brody, S. Zahran, P. Maghelal, H. Grover, and W. E. Highfield, “The rising costs of floods: examining the impact of planning and development decisions on property damage in Florida,” J Am Plan As, vol. 73, no. 3, pp. 330–345, 2007.
• [16] N. W. Chan, “Impacts of disasters and disasters risk management in Malaysia: the case of floods,” In: Sawada Y, Oum S (eds) Economic and welfare impacts of disasters in East Asia and Policy responses, ERIA Research Project Report 2011-8, ERIA, Jakarta, pp. 503–551, 2012.
• [17] A. Pashazadeh and M. Javan, “Comparison of the gene expression programming, artificial neural network (ANN), and equivalent Muskingum inflow models in the flood routing of multiple branched rivers,” Theoretical and Applied Climatology, vol. 139, pp. 1349–1362, 2020.
• [18] C. W. Dawson, and R. Wilby, “An artificial neural network approach to rainfall-runoff modeling, ”” Hydrol Sci J, vol. 43, no.1, pp. 47–66, 1998.
• [19] H. R. Maier and G. C. Dandy, “Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications, ” Environ Model Softw, vol. 15, pp. 101–123, 2000.
• [20] O. Kisi, “River flow modeling using artificial neural network, ”ASCE J Hydrol Eng, vol. 9, no. 1, pp. 60–63, 2004.
• [21] A. P. S. Kumar, K. P. Sudheer, S. K. Jain and P. K. Agarwal, “Rainfall-runoff modeling using artificial neural networks: comparison of network types,” Hydrol Process, vol. 19, pp. 1277–1291, 2005.
• [22] E. Mutlu, , I. Chaubey, H. Hexmoor and S. G. Bajwa, “Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed,” Hydrol Process, vol. 22, no.26, pp. 5097–5106. 2008.
• [23] M. R. Zadeh, S. Amin, D. Khalili and V. P .Singh, “Daily outflow prediction by multilayer perceptron with logistic sigmoid and tangent sigmoid activation functions,” Water Resour Manag, vol. 24, no. 11, pp. 2673–2688, 2010.
• [24] O. Kisi, A. M. Nia, M. G. Gosheh, M. R. J Tajabadi and A. Ahmadi, “Intermittent streamflow forecasting by using several data driven techniques,” Water Resour Manage, vol. 26, no. 2, pp.457–474, 2012.
• [25] B. S. Sil and B. Das, “Determination of downtream flood flow considering inputs from different upstream rivers using ANN,”J Urban Environ. Eng. (JUEE), vol. 12, no. 1, 2018.
• [26] K. P. Sudheer, A. K. Gosain and K. S. Ramasastri, “A data-driven algorithm for constructing artificial neural network rainfall–runoff models,” Hydrologic Processes , vol.16, pp. 1325–1330, 2002.
• [27] B. Bharti, A. Pandey, S. K. Tripathi and D. Kumar, “Modelling of runoff and sediment yield using ANN, LS-SVR, REPTree and M5 models, ” Hydrology Research, vol. 48, no. 6, pp. 1489–1507, 2017.
• [28] F. D. Mwale, A. J. Adeloye and R. Rustum, “Application of selforganising maps and multi-layer perceptron-artifici l neural networks for streamflow and water level forecasting in datapoor catchments: the case of the Lower Shire floodplain, Malawi, ” Hydrology Research, vol. 45, no. 6, pp. 838–854, 2014.
• [29] M. Babaei, R. Moeini, and E. Ehsanzadeh, “Artificial neural network and support vector machine models for inflow prediction of dam reservoir case study: Zayandehroud Dam Reservoir,” Water Resources Management, vol. 33, pp. 2203, 2019.
• [30] N. N. Kourgialas and G. P. Karatzas, “A national scale flood hazard mapping methodology: the case of Greece–Protection and adaptation policy approaches,” Science of the Total Environment, vol. 601, pp. 441–452, 2017.
• [31] N. Dehghanian, S. S. M Nadoushani, B. Saghafian and M. R. Damavandi, “Evaluation of coupled ANN-GA model to prioritize flood source areas in ungauged watersheds,” Hydrology Research, vol. 51, no.3, 2020.
• [32] K. Hornik, “Multilayer feed forward networks are universal approximations,” Neur. Networks, vol. 2, no.4, pp. 359–366, 1989.
• [33] J. L. Rogers and W. J. Lamarsh, “Application of a neural network to simulate analysis in an optimization process Proceedings, ” Artificial Intelligence in Design 92, Kluwer Academic, Boston, pp. 739–754, 1992.
• [34] G. Tayfur, V. P. Singh, T. Moramarco and B. Barbetta, “Flood Hydrograph Prediction Using Machine Learning Methods,”Water, vol. 10, pp. 968, 2018.
• [35] H. K. Demissie and P. Bacopoulos, “Parameter Estimation of Anisotropic Manning's n Coefficient for Advanced Circulation (ADCIRC) Modeling of Estuarine River Currents (lower St. Johns River) , ” Journal of Marine Systems vol.169, pp. 1–10, 2017.
• [36] M. Zare and M. Koch, “An Analysis of MLR and NLP for Use in River Flood Routing and Comparison with the Muskingum Method,” IAHR World Congress, 2013.
• [37] Devlet Su İşleri. (2017, 4 Ekim). [Online]. Erişim: http://rasatlar.dsi.gov.tr/.
• [38] Cografyaharita.com (2017, 4 Ekim). [Online]. Erişim: http://cografyaharita.com/haritalarim/2eturkiye-akarsu-havzalari-haritasi.png
• [39] tarimorman.gov.tr, Büyük Menderes Nehir Havzası Yönetim Planı (2021, 12 Haziran). [Online].Erişim:https://www.tarimorman.gov.tr/SYGM/Belgeler/NHYP%20DEN%C4%B0Z/B%C3%9CY%C3%9CK%20MENDERES%20NEH%C4%B0R%20HAVZASI%20Y%C3%96NET%C4%B0M%20PLANI.pdf