YSA, KNN ve ANFIS Modellerini Kullanarak Aylık Akım Tahmini: Gediz Nehri Havzası Örneği

Year 2023, Volume: 13 Issue: 2, 42 - 49, 01.08.2023

Naz'm Nazımı , Kemal Saplıoğlu

https://doi.org/10.35354/tbed.1298296

Cited By: 1

Abstract

Akarsu akış tahmini, su temini, sulama, su altyapılarının inşası, taşkınlara karşı önlem alınması gibi birçok konu için çok önemlidir. Gelecekteki nehir akışını tahmin etme yeteneği, yaklaşan selleri tahmin etmemize ve planlamamıza, mülk tahribatını azaltmamıza, ölümleri önlememize ve suyu mümkün olan en iyi şekilde yönetmemize yardımcı olur. Akarsu akışını tahmin etmek için farklı hidrolojik modeller geliştirilmiştir. Bu modeller, araştırma alanı ve mevcut veriler tarafından yönlendirilen farklı özelliklere sahiptirler. Bu çalışmada, K-En Yakın Komşu (KNN), Yapay Sinir Ağı (ANN) ve Uyarlanabilir Nöro Bulanık Çıkarım Sistemi (ANFIS), olarak üç farklı yapay zeka modeli kullanılmıştır. Türkiye'nin batısındaki Ege bölgesinde yer alan Gediz Nehri Havzasının verileri ise eğitim ve test için kullanılmıştır. Sonuçlar, verilerin karmaşıklığı ve çalışma alanının farklı bölümleri ve ayrıca modellerin yapısı nedeniyle değişiklik göstermiştir, genel olarak, Regresyon katsayısı (R²), Ortalama Karesel Hata (RMSE) ve Wilcoxon (WT) değerlerine bakıldığında ANFIS, YSA ve KNN modellerine kıyasla daha doğrudur. Taylor diyagramına göre ise KNN, ANN ve ANFIS'e kıyasla daha doğrudur.

Keywords

Akış Tahmini, ANFIS, ANN, KNN, Gediz Nehri Havzası, Wilcoxon

Monthly Streamflow Prediction Using ANN, KNN and ANFIS models: Example of Gediz River Basin

Abstract

Stream flow forecasting is very important in many aspects such as water supply, irrigation, building water infrastructures, and taking precautions against floods. The ability to forecast future streamflow helps us anticipate and plan for upcoming flooding, decreasing property destruction, preventing deaths and managing water in the best way possible. Different hydrological models have been developed for predicting streamflow and they have different characteristics, driven by the research area and available data. İn this study, three types of Artificial Intelligence models; K-Nearest Neighbor (KNN), Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) have been used to study the Gediz River Basin which is located in the Aegean region of western Turkey. The results varied due to the complication of the data and different parts of the study area as well as the structure of the models, over all, looking at Regression coefficient (R2), Root Mean Square Error (RMSE) and Wilcoxon (WT) values, ANFIS is more accurate compared to ANN and KNN models. Conversely, according to Taylor diagram, KNN is more accurate compared to ANN and ANFIS.

Keywords

Streamflow Prediction, ANFIS, ANN, KNN, Gediz River Basin, Wilcoxon

References

• [1] Adeogun, A. G., Sule, B. F., Salami, A. W., & Okeola, O. G. (2014). GIS-Based Hydrological Modelling using SWAT: Case study of upstream watershed of Jebba reservoir in Nigeria. Nigerian Journal of Technology, 33(3), 351-358.
• [2] Aksakal, A.., Gündoğay, A. (2022). Determınatıon Of Column Curvature Ductılıty By Multıple Regressıon Analysıs. Ist-International Congress on Modern Sciences Tashkent, Uzbekistan, 395-403.
• [3] Al-Saati, N. H., Omran, I. I., Salman, A. A., Al-Saati, Z., & Hashim, K. S. (2021). Statistical Modeling of Monthly Streamflow Using Time Series and Artificial Neural Network Models: Hindiya Barrage As a Case Study. Water Practice and Technology, 16(2), 681-691.
• [4] Çatal, Y., & Saplıoğlu, K. (2018). Comparison of Adaptive Neuro-Fuzzy Inference System, Artificial Neural Networks and Non-Linear Regression for bark volume estimation in brutian pine (Pinus brutia Ten.). Applied Ecology and Environmental Research, 16(2), 2015-2027.
• [5] Çekmiş, I., Hacihasanoǧlu, M.J. (2014). Ostwald a Computational Model for Accommodating Spatial Uncertainty: Predicting Inhabitation Patterns in Open-Planned Spaces Build. Environ., 73 , 115-126.
• [6] Dastgheib, S. R., Feylizadeh, M. R., Bagherpour, M., & Mahmoudi, A. (2022). Improving Estimate at Completion (EAC) Cost of Construction Projects Using Adaptive Neuro-Fuzzy İnference System (ANFIS). Canadian Journal of Civil Engineering, 49(2), 222-232.
• [7] Dastorani, M. T., Moghadamnia, A., Piri, J., & Rico-Ramirez, M. (2010). Application of ANN and ANFIS Models for Reconstructing Missing Flow Data. Environmental Monitoring and Assessment, 166(1), 421-434.
• [8] Dölling, O. R. (2002). Artificial Neural Networks for Streamflow Prediction. Journal of Hydraulic Research, 40(5), 547-554.
• [9] Elçi, A. R., Şimşek, C., Gündüz, O., Baba, A., Acınan, S., Yıldızer, N & Murathan, A. (2022). Improving Estimate at Completion (EAC) Cost of Construction Projects Using Adaptive Neuro-Fuzzy İnference System (ANFIS). Canadian Journal of Civil Engineering, 49(2), 222-232.
• [10] Ergu, D., Kou, G., Peng, Y., & Zhang, M. (2016). Estimating The Missing Values for the İncomplete Decision Matrix And Consistency Optimization İn Emergency Management. Applied mathematical modelling, 40(1), 254-267 [11] Gholami, A., Bonakdari, H., Ebtehaj, I., Akhtari A. A. (2017). Design of an Adaptive Neuro-Fuzzy Computing Technique for Predicting Flow Variables İn a 90° Sharp Bend. Journal of Hydroinformatics, 19 (4): 572–585.
• [12] Güçlü, Y. S., & Şen, Z. (2016). Hydrograph Estimation with Fuzzy Chain Model. Journal of Hydrology, 538, 587-597.
• [13] Gündoğay, A., Aksakal, A. K. (2022). Betonarme Kolon Eğrilik Sünekliğinin 2007 ve 2018 Deprem Yönetmeliklerine Göre İncelenmesi. Avrupa Bilim ve Teknoloji Dergisi, (34), 202-210.
• [14] Katipoglu, O. M. (2021). Estimation of Incomplete Precipitation Data using the Adaptive Neuro-Fuzzy Inference System (ANFIS) Approach. Data Science and Applications, 4(1), 11-15.
• [15] Kilinc, H. C., & Haznedar, B. (2022). A Hybrid Model for Streamflow Forecasting in the Basin of Euphrates. Water, 14(1), 80.
• [16] Kilinc, H. C., & Yurtsever, A. (2022). Short-Term Streamflow Forecasting Using Hybrid Deep Learning Model Based on Grey Wolf Algorithm for Hydrological Time Series. Sustainability, 14(6), 3352.
• [17] Kim, J. W., & Pachepsky, Y. A. (2010). Reconstructing Missing Daily Precipitation Data Using Regression Trees and Artificial Neural Networks for SWAT Streamflow Simulation. Journal of Hydrology, 394(3-4), 305-314.
• [18] Köyceğiz, C., & Büyükyıldız, M. (2022). Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata University Journal of Graduate School of Natural and Applied Sciences, 5(3), 1141-1154.
• [19] Langhammer, J., & Česák, J. (2016). Applicability of a Nu-Support Vector Regression Model for the Completion of Missing Data in Hydrological Time Series. Water, 8(12), 560.
• [20] Li, X., Song, G., & Du, Z. (2021). Hybrid Model Of Generative Adversarial Network and Takagi‐Sugeno for Multidimensional İncomplete Hydrological Big Data Prediction. Concurrency and Computation. Practice and Experience, 33(15), e5713.
• [21] Poul, A. K., Shourian, M., Ebrahimi, H. (2019) A Comparative Study of MLR, KNN, ANN and ANFIS Models with Wavelet Transform in Monthly Streamflow Prediction. Sringer, 33, 2907–2923.
• [22] Saplıoglu, K., & Kucukerdem, T. (2018). Estımatıon of Mıssıng Streamflow Data Usıng Anfıs Models And Determınatıon of The Number of Datasets For Anfis: The Case of Yeşilırmak River. Applied Ecology And Environmental Research, 16(3), 3583-3594.
• [23] Saplıoğlu, K., Küçükerdem Öztürk, T. S. & Şenel, F. A. (2020). Estimation of Missing Hydrological Data by Symbiotic Organisms Search Algorithm. Çanakkale Onsekiz Mart University Journal of Graduate School of Natural and Applied Sciences, 6 (1) , 93-104 .
• [24] Sudheer, K. P., Nayak, P. C., & Ramasastri, K. S. (2003). Improving Peak Flow Estimates in Artificial Neural Network River Flow Models. Hydrological Processes, 17(3), 677-686.
• [25] Şenel, F. A., Küçükerdem Öztürk, T. S. & Saplıoğlu, K. (2020). Optimization of Time Delay Dimension by Ant Lion Algorithm Using Artificial Neural Networks for Estimation of Yeşilırmak River Flow Data. Afyon Kocatepe University Journal of Science and Engineering, 20 (2) , 310-318 .
• [26] Uzundurukan, S. (2023). Prediction of soil–water characteristic curve for plastic soils using PSO algorithm. Environmental Earth Sciences, 82(1), 37.
• [27] Ünal, A., Saplıoğlu, M., & Böcek, M. (2018). Sinyalizasyonlu Kavşak Yaklaşımında Üstyapı Düzgünsüzlüğü ile Sürücü Davranışı Etkileşiminin Değerlendirilmesi. Academic Perspective Procedia, 1(1), 918-928.
• [28] Williams, D., Liao, X., Xue, Y., Carin, L., & Krishnapuram, B. (2007). On Classification with İncomplete Data. IEEE Transactions on Pattern Analysis and Machine İntelligence, 29(3), 427-436.
• [29] Yaseen, Z. M., Ebtehaj, I., Bonakdari, H., Deo, R. C., Mehr, A. D., Mohtar, W. H. M. W., ... & Singh, V. P. (2017). Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model. Journal of Hydrology, 554, 263-276