Modeling of annual maximum flows with geographic data components and artificial neural networks

Yıl 2023, , 200 - 211, 05.07.2023

Esra Aslı Çubukçu , Vahdettin Demir , Mehmet Faik Sevimli

https://doi.org/10.26833/ijeg.1125412

Cited By: 2

Öz

The flow rate at which the instantaneous maximum flow is recorded throughout the year is called the Annual Maximum Flow (AMF). These flow rates often cause disasters such as floods. Snow melts and extreme precipitation associated with temperature fluctuations are the two most important factors that occurred flooding. The deluge that follows kills people and destroys property in communities and agricultural lands. As a result, it's critical to predict the flow that causes flooding and take appropriate precautions to limit the damage. The prediction of the probability of a flood event in advance is very important for the safety of life and property of large masses and agricultural lands. Early warning systems, disaster management plans and minimizing these losses are among the important goals of the country's administration. This study was used in five Current Observation Stations (COS) located in Yeşilırmak Basin in Turkey. By using 8 input data including geographical location, altitude and area information of these stations, AMF data were tried to be estimated for each COS. A total of 240 input data was used in the study. The data period covers the years 1964-2012. Unfortunately, AMF values cannot be monitored for all 5 stations used after 2012. Therefore, the data period was stopped in 2012. In this study, Multilayer Artificial Neural Networks (MANN), Generalized Artificial Neural Networks (GANN), Radial Based Artificial Neural Networks (RBANN) and Multiple Linear Regulation (MLR) methods were used. Input data sets were made into 4 packets and these packages were used respectively in both training and testing stages. In these packages, the AMF data measured for the 5 stations mentioned above between 1965 and 2012 were divided into 4 and used by creating 25% (test) and 75% (training) packages. Root Means Square Error (RMSE), Mean Absolute Error (MAE) and correlation coefficient (R) were used as the comparison criteria. The results are as follow; MANN (RMSE = 119.118, MAE = 93.213, R = 0.808), and RBANN (RMSE = 111.559, MAE = 81.114, R = 0.900). These results show that AMF can be predicted with artificial intelligence techniques and can be used as an alternative method.  

Anahtar Kelimeler

Modeling, Flood, Artificial Neural Networks, Annual Maximum Flow, Geographical Information Systems

Kaynakça

• Tonkaz T., Çetin M., Kızıloğlu F., & Fayrap A. (2010). Mixed Eastern Black Sea Water Basin Annual Probabılıty Analysıs of Instant Maxımum Currents. II. National Flood Symposium, 315-321.
• Republic of Turkey Ministry of Agriculture And Forestry General Directorate of Water Management Flood Management (2017). Ministry of Forestry and Water Affairs, Ankara.
• URL1: "Natural disasters, floods" access address: https://www.riob.org/fr/file/272232/download?token=PysGjbkb accessed 6 October 2022.
• Öztemel E. (2012). Artificial Neural Networks, Istanbul.
• Aydoğan B., Ayay B., & Çevik, E. (2011). Ann Current Profile Forecasting in Straits With an Example:Bosphorus. 7th Coastal Engineering Symposium, 403-409.
• URL2: "Artificial Neural Networks" access address:https://www.kimnezamanicatetti.com/yapay-sinir-agi/, accessed May 1, 2019.
• Dibike Y. B., & Solomatine, D. P. (2001). River Flow Forecasting Using Artificial Neural Networks. Physics and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere (B), 26(1), 1-7.
• Dawson, C. W. & Wilby, R. L. (2001). Hydrological Modelling Using Artificial Neural Networks. Prog. Phys. Geogr., 25(1), 80–108. https://doi.org/ 10.1177/030913330102500104.
• Lim, Y. H., & Lye, L. M. (2003). Regional flood estimation for ungauged basins in Sarawak , Malaysia Regional flood estimation for ungauged basins in Sarawak. Malaysia, Hydrological Sciences Journal, 48(1), 79–94.
• Dahamsheh, A. (2008). Forecasting Monthly Precipitation For Arid Regions Using Conditional Artificial Neural Networks Combined With Markov Chain. (Ph.D. Thesis, ITU Institute of Science and Technology, Turkey).
• Hu, T. S., Lam, K. C. & Ng, S. T. A. (2009). Modified Neural Network for Improving River Flow Prediction/Un Réseau de Neurones Modifié pour Améliorer la Prévision de L'Écoulement Fluvial. Hydrological Sciences Journal, 50(2), 298–318.
• Ren, M., Wang, B., Liang, Q. & Fu, G. (2010). Classified Real-Time Flood Forecasting By Coupling Fuzzy Clustering and Neural Network. International Journal of Sediment Research 25(2), 134-148.
• Ahmad, I., Fawad, M. & Mahmood, I. (2015). At-Site Flood Frequency Analysis of Annual Maximum Stream Flows in Pakistan Using Robust Estimation Methods. Polish Journal of Environmental Studies, 24(6), 2345–2353.
• Haktanir, T., Citakoglu, H. & Seckin, N. (2016). Regional frequency analyses of successive-duration annual maximum rainfalls by L-moments method. Hydrological Sciences Journal, 61(4), 647–668. https://doi.org/10.1080/02626667.2014.966722.
• Akkaya, U. & Doğan, E. (2016). Generation of 2D Flood İnundation Maps of Meriç and Tunca Rivers Passing Through Edirne City Center. Geofizika 33(1), 15-34, https://doi.org/10.15233/gfz.2016.33.7
• Çıtakoğlu, H., Demir, V. & Haktanir, T. (2017). Regional Frequency Analysis Of Annual Flood Peaks Of Natural Streams Discharging To The Black Sea By The L-Moments Method. Omer Halisdemir Univercity Journal of Engineering Science, 6(2), 571–580.
• Aghayev, A. (2018). Determining of Different Inundated Land Use in Salyan Plain During 2010 the Kura River Flood Through Gis and Remote Sensing Tools. Journal of Engineering and Geosciences, 3(3) 80–86. https://doi.org/10.26833/ijeg.412348.
• Oyebode, D. & Stretch, O. (2019). Neural Network Modeling Of Hydrologicalsystems: A Review Of İmplementation Techniques. Natural Resource Modeling. 32(1), 1–14. https://doi.org/10.1002/nrm.12189
• Ovcharuk, V., Gopchenko, E., Todorova, O., & Myrza, K. (2020). Calculating the Characteristics of Flash FLoods on Small Rivers in the Mountainous Crimea, Geofizika 37(1), 27-43. https://doi.org/10.15233/gfz.2020.37.3, July.
• Taylan, E. D., Terzi, Ö. & Baykal, T. (2021). Hybrid Wavelet–Artificial İntelligence Models İn Meteorological Drought Estimation. J. Earth Syst. Sci., 130(38), 2021, https://doi.org/10.1007/s12040-020-01488-9.
• Boustani Hezarani, A., Zeybekoğlu, U. & Ülke Keskin, A. (2021). Hydrological And Meteorological Drought Forecasting For The Yesilirmak River Basin, Turkey. Sürdürülebilir Mühendislik Uygulamaları ve Teknol. Gelişmeler Derg., 4(2), 121–135. 2021, https://doi.org/10.51764/smutgd.993792
• Demir, V. & Ülke Keskin, A. (2022). Flood flow calculation and flood modeling in rivers that do not have enough flow measurement (Samsun, Mert River sample). Geomatik, 7(2), pp. 149–162, https://doi.org/10.29128/geomatik.918502
• Çay, F. (2018). Determination of Morphological Characteristics Of Basins in Turkey with The Help of GIS. (Master Thesis, KTO Karatay University Institute of Science and Technology, Turkey).
• Akgül, M. A. (2018). Sentetik Açıklıklı Radar verilerinin Taşkın Çalışmalarında Kullanılması: Berdan Ovası Taşkını. Geomatik , 3 (2) , 154-162 . https://doi.org/10.29128/geomatik.378123
• Oğuz, E., Oğuz, K. & Öztürk, K. (2022). Düzce bölgesi taşkın duyarlılık alanlarının belirlenmesi . Geomatik, 7(3) , 220-234 . https://doi.org/10.29128/geomatik.972343
• Tona, A. U. , Demir, V. , Kuşak, L. & Yakar, M. (2022). Su Kaynakları Mühendisliğinde CBS’nin Kullanımı. Türkiye Coğrafi Bilgi Sistemleri Dergisi, 4 (1), 23-33. https://doi.org/10.56130/tucbis.993807
• Yılmaz, O. S. (2023). Frekans oranı yöntemiyle coğrafi bilgi sistemi ortamında heyelan duyarlılık haritasının üretilmesi: Manisa, Demirci, Tekeler Köyü örneği. Geomatik, 8(1), 42-54. https://doi.org/10.29128/geomatik.1108735
• Yılmaz, A. & Erdoğan, M. (2018). Designing high resolution countrywide DEM for Turkey . International Journal of Engineering and Geosciences, 3(3), 98-107. https://doi.org/ 10.26833/ijeg.384822
• Al Kalbani, K. & Rahman, A. A. (2022). 3D city model for monitoring flash flood risks in Salalah, Oman. International Journal of Engineering and Geosciences, 7(1), 17-23. https://doi.org/ 10.26833/ijeg.857971
• Yağmur, N. , Tanık, A. , Tuzcu, A. , Musaoğlu, N. , Erten, E. & Bilgilioglu, B. (2020). Opportunities provided by remote sensing data for watershed management: example of Konya Closed Basin . International Journal of Engineering and Geosciences, 5(3), 120-129. https://doi.org/10.26833/ijeg.638669
• Yakar, M. (2009). Digital elevation model generation by robotic total station instrument. Experimental Techniques, 33(2), 52-59
• Yavuz S. & Deveci M. (2012). The Effect of Statistical Normalization Techniques on The Performance of Artificial Neural Network. Erciyes University Journal of the Faculty of Economics and Administrative Sciences, 167–187.
• Arı, A., & Berberler, M. E. (2017). Prediction and Classification with Artificial Neural Networks Interface Design for Solving Problems. Acta Infologica, 1(2): 55–73.
• Çubukçu, E. A., Sancıoğlu S., Demir, V. & Sevimli, M. F. (2019). Sea Water Level Estimation Using Six Different Artificial Neural Networks Training Algorithm, International Civil Engineering Architecture Conference, 716-725.
• Broomhead, D. D. & Lowe, S. (1988). Multivariable Functional Interpolation and Adaptive Networks. Complex Syst., 2, 321–355.
• Partal, T., Kahya, E. & Cığızoğlu, K. (2008). Prediction of Precipitation Data with Artificial Neural Networks and Wavelet Transformation Methods. ITU Journal of Engineering, 7(3), 73–85.
• Poggio, T. & Girosi, F. (1990). Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks. Science, 247(4945), 978–982.
• Okkan, U. & Dalkılıç, H. Y. (2012). Monthly Runoff Model for Kemer Dam with Radial Based Artificial Neural Networks. IMO Technical Journal, 5957–5966.
• Demir, V., Çubukçu, E. A. & Sevimli, M. F. (2019). Long-Term Month Temperature Forecast With Inverse Distances Weighted, Kriging And Artificial Neural Networks. CISET-2nd Cilicia International Symposium On Engineering And Technology, 10-13.
• Sürel, A., (2006). The Use of Generalized Regression Neural Network in Water Resources Engineering. (Master Thesis, ITU Institute of Science and Technology, Turkey).
• Oral, M., Kartal, S. & Özyıldırım, M. (2017). A Cluster Based Approach to Reduce Pattern Layer Size for Generalized Regression Neural Network. Pamukkale University Journal of Engineering Sciences, 24(5), 857–863.
• Okkan, U. & Mollamahmutoglu, A. (2010). Daily Runoff Modelling of Yiğitler Stream by Using Artificial Neural Networks and Regression Analysis. Dumlupınar University Journal of Science Institute, 23: 33–48.
• Çubukçu, E. A. (2019). Modelıng Of Annual Maxımum Flows Wıth Geographıc Data Components And Artıfıcıal Neural Networks. (Master Thesis, KTO Karatay University Institute of Science and Technology, Turkey).
• Zhang, Q. Yuan, Q. Zeng, C. Li, X. &Wei, Y. (2018). Missing Data Reconstruction In Remote Sensing Image With A Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network. IEEE Trans. Geosci. Remote Sens., 56(8), 4274–4288.