Research Article
BibTex RIS Cite

Estimation of Streamflow Using Different Artificial Neural Network Models

Year 2022, Volume: 5 Issue: 3, 1141 - 1154, 12.12.2022
https://doi.org/10.47495/okufbed.1037242

Abstract

Accurate estimation of streamflow is crucial for water resources planning, design and management, determining of flood and drought management strategies, and minimizing their adverse effects. In this study, the usability of Artificial Neural Network (ANN) models to estimate of monthly streamflow was investigated. For this purpose, monthly data of two stations located in the Seyhan Basin in the south of Turkey were used. The data of Sarız River-Şarköy observation station (No: D18A032) for the streamflow and Sarız meteorology station (No: 17840) for precipitation were used. The precipitation and flow data used belong to the period 1990-2017. Nine input combinations consisting of lags of streamflow and precipitation data were obtained and used in ANN models. We used two ANN techniques, namely Multilayer Perceptron (MLP) and Radial Basis Neural Networks (RBNN) to estimate the monthly streamflow. In the MLP technique, three learning algorithms with gradient descent with momentum and adaptive learning rule backpropagation (GDX), Levenberg-Marquardt (LM) and resilient backpropagation (RBP) were used. The parameters of each different ANN model obtained by using nine input combinations were obtained by trial and error. The success of the models used was evaluated using five different performance metrics. Which of the input combinations used in the streamflow estimation was more successful was decided according to the combination with the highest Nash Sutcliffe efficiency coefficient (NSE) value of the test period. Although similar results were obtained in MLP-GDX, MLP-RBP, MLP-LM and RBNN models, MLP models (except MLP-LM) were slightly more successful than RBNN models. The most successful streamflow estimation model was the MLP-GDX-M6 model. In the MLP-GDX-M6 model, MAE=1.148 m3/s, RMSE=1.815 m3/s, R2=0.724, NSE=0.717, and CA=1.069 were obtained for the testing period. The novelty of the study is that we have examined the credibility of ANN models, including the MLP-GDX, MLP-RBP, MLP-LM and RBNN for predicting the monthly streamflow in natural rivers.

References

  • Abdollahi S., Raeisi J., Khalilianpour M., Ahmadi F., Kisi O. Daily mean streamflow prediction in perennial and non-perennial rivers using four data driven techniques. Water Resources Management 2017; 31, 4855–4874.
  • Adamowski J., Chan HF., Prasher SO, Sharda VN. Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics 2012; 14(3): 731-744.
  • Broomhead D., Lowe D. Multivariable functional interpolation and adaptive networks. Complex Systems 1988; 2, 321-355.
  • Cheng CT., Feng ZK., Niu WJ., Liao SL. Heuristic methods for reservoir monthly inflow forecasting: A case study of Xinfengjiang Reservoir in Pearl River, China. Water 2015; 7, 4477-4495.
  • Cui F., Salih SQ., Choubin B., Bhagat SK., Samui P., Yaseen ZM. Newly explored machine learning model for river flow time series forecasting at Mary River, Australia. Environmental Monitoring and Assessment 2020; 192, 761.
  • Hadi SJ., Tombul M. Monthly streamflow forecasting using continuous wavelet and multi-gene genetic programming combination. Journal of Hydrology 2018; 516, 674–687.
  • Haykin S. Neural networks and learning machines. Pearson Education Inc., Upper Saddle River, New Jersey, USA, 2009.
  • Latifoğlu L., Nuralan KB. Tekil Spektrum Analizi ve Uzun-Kısa Süreli Bellek Ağları ile Nehir Akım Tahmini. Avrupa Bilim ve Teknoloji Dergisi 2020; 376-381.
  • Latt ZZ., Wittenberg H. Improving flood forecasting in a developing country: a comparative study of stepwise multiple linear regression and artificial neural network. Water Resources Management 2014; 28(8): 2109-2128.
  • Liu D., Jiang W., Mu L., Wang S. Streamflow prediction using deep learning neural network: Case study of Yangtze River. IEEE Access, 2020; 8, 90069-90086.
  • Liu Y., Sang YF., Li X., Hu J., Liang K. Long-term streamflow forecasting based on relevance vector machine model. Water 2016; 9 (1): 9.
  • Mohammadi, B., Moazenzadeh, R., Christian, K., & Duan, Z. (2021). Improving streamflow simulation by combining hydrological process-driven and artificial intelligence-based models. Environmental Science and Pollution Research 2021; 28, 65752–65768.
  • Nourani V, Davanlou Tajbakhsh A, Molajou A, Gokcekus H. Hybrid Wavelet-M5 Model tree for rainfall-runoff modeling. Journal of Hydrologic Engineering 2019; 24(5): 04019012.
  • Şen Z. Yapay Sinir Ağları İlkeleri. Su Vakfı Yayınları,183 p., İstanbul.2004.
  • Xu W., Jiang Y., Zhang X., Li Y., Zhang R., Fu G. Using long short-term memory networks for river flow prediction. Hydrology Research 2020; 51(6): 1358-1376.
  • Zhang X., Peng Y., Zhang C., Wang B. Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences. Journal of Hydrology 2015; 530, 137-152.

Farklı Yapay Sinir Ağı Modelleri Kullanarak Nehir Akımı Tahmini

Year 2022, Volume: 5 Issue: 3, 1141 - 1154, 12.12.2022
https://doi.org/10.47495/okufbed.1037242

Abstract

Su kaynaklarının planlanması, tasarımı ve yönetimi, taşkın ve kuraklık yönetim stratejilerinin belirlenmesi ve olumsuz etkilerinin minimize edilebilmesi nedeniyle nehir akımının doğru bir şekilde tahmin edilmesi hayati önem taşımaktadır. Bu çalışmada, Yapay Sinir Ağları (YSA) modellerinin aylık nehir akımı tahmininde kullanılabilirliği araştırılmıştır. Bu amaçla, Türkiye'nin güneyinde Seyhan Havzasında yer alan iki istasyonun aylık verileri kullanılmıştır. Nehir akımı için Sarız Nehri-Şarköy gözlem istasyonu (No: D18A032), yağış için Sarız meteoroloji istasyonu (No: 17840) verilerinden faydalanılmıştır. Kullanılan yağış ve akış verileri 1990-2017 periyoduna aittir. Akım ve yağış verilerinin gecikmelerinden oluşan dokuz giriş kombinasyonu elde edilmiş ve YSA modellerinde kullanılmıştır. Aylık nehir akımını tahmin etmek için Çok Katmanlı Algılayıcı (MLP) ve Radyal Temelli Sinir Ağları (RBNN) olmak üzere iki YSA tekniği kullanılmıştır. MLP tekniğinde adaptif öğrenmeli ve momentum özellikli en dik iniş (GDX),esnek geriyayılım (RBP) ve Levenberg-Marquardt (LM)olmak üzere üçadet öğrenme algoritması kullanılmıştır. Farklı giriş kombinasyonları kullanılarak elde edilen her bir farklı YSA modelinin parametreleri deneme yanılma yoluyla belirlenmiştir. Kullanılan modellerin başarısı beş farklı performans ölçütü kullanılarak değerlendirilmiştir. Akarsu tahmininde kullanılan giriş kombinasyonlarından hangisinin daha başarılı olduğuna, test döneminin Nash Sutcliffe verimlilik katsayısı (NSE) değeri en yüksek olan kombinasyona göre karar verilmiştir. MLP-GDX, MLP-RBP, MLP-LM ve RBNN modellerinde benzer sonuçlar elde edilmiş olmasına rağmen MLP modelleri (LM hariç) az da olsa RBNN modellerinden daha başarılı olmuştur. En başarılı akım tahmin modeli MLP-GDX-M6 modeli olmuştur. MLP-GDX-M6 modelinde test periyodu için MAE=1.148 m3/s, RMSE=1.815 m3/s, R2=0.724, NSE=0.717 ve CA=1.069 olarak elde edilmiştir. Çalışmanın yeniliği, doğal nehirlerdeki aylık akış akışını tahmin etmek için MLP-GDX, MLP-RBP, MLP-LM ve RBNN dahil olmak üzere YSA modellerinin güvenilirliğini incelemiş olmamızdır.

References

  • Abdollahi S., Raeisi J., Khalilianpour M., Ahmadi F., Kisi O. Daily mean streamflow prediction in perennial and non-perennial rivers using four data driven techniques. Water Resources Management 2017; 31, 4855–4874.
  • Adamowski J., Chan HF., Prasher SO, Sharda VN. Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics 2012; 14(3): 731-744.
  • Broomhead D., Lowe D. Multivariable functional interpolation and adaptive networks. Complex Systems 1988; 2, 321-355.
  • Cheng CT., Feng ZK., Niu WJ., Liao SL. Heuristic methods for reservoir monthly inflow forecasting: A case study of Xinfengjiang Reservoir in Pearl River, China. Water 2015; 7, 4477-4495.
  • Cui F., Salih SQ., Choubin B., Bhagat SK., Samui P., Yaseen ZM. Newly explored machine learning model for river flow time series forecasting at Mary River, Australia. Environmental Monitoring and Assessment 2020; 192, 761.
  • Hadi SJ., Tombul M. Monthly streamflow forecasting using continuous wavelet and multi-gene genetic programming combination. Journal of Hydrology 2018; 516, 674–687.
  • Haykin S. Neural networks and learning machines. Pearson Education Inc., Upper Saddle River, New Jersey, USA, 2009.
  • Latifoğlu L., Nuralan KB. Tekil Spektrum Analizi ve Uzun-Kısa Süreli Bellek Ağları ile Nehir Akım Tahmini. Avrupa Bilim ve Teknoloji Dergisi 2020; 376-381.
  • Latt ZZ., Wittenberg H. Improving flood forecasting in a developing country: a comparative study of stepwise multiple linear regression and artificial neural network. Water Resources Management 2014; 28(8): 2109-2128.
  • Liu D., Jiang W., Mu L., Wang S. Streamflow prediction using deep learning neural network: Case study of Yangtze River. IEEE Access, 2020; 8, 90069-90086.
  • Liu Y., Sang YF., Li X., Hu J., Liang K. Long-term streamflow forecasting based on relevance vector machine model. Water 2016; 9 (1): 9.
  • Mohammadi, B., Moazenzadeh, R., Christian, K., & Duan, Z. (2021). Improving streamflow simulation by combining hydrological process-driven and artificial intelligence-based models. Environmental Science and Pollution Research 2021; 28, 65752–65768.
  • Nourani V, Davanlou Tajbakhsh A, Molajou A, Gokcekus H. Hybrid Wavelet-M5 Model tree for rainfall-runoff modeling. Journal of Hydrologic Engineering 2019; 24(5): 04019012.
  • Şen Z. Yapay Sinir Ağları İlkeleri. Su Vakfı Yayınları,183 p., İstanbul.2004.
  • Xu W., Jiang Y., Zhang X., Li Y., Zhang R., Fu G. Using long short-term memory networks for river flow prediction. Hydrology Research 2020; 51(6): 1358-1376.
  • Zhang X., Peng Y., Zhang C., Wang B. Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences. Journal of Hydrology 2015; 530, 137-152.
There are 16 citations in total.

Details

Primary Language English
Subjects Civil Engineering
Journal Section RESEARCH ARTICLES
Authors

Cihangir Köyceğiz 0000-0002-0510-1164

Meral Büyükyıldız 0000-0003-1426-3314

Publication Date December 12, 2022
Submission Date December 16, 2021
Acceptance Date March 10, 2022
Published in Issue Year 2022 Volume: 5 Issue: 3

Cite

APA Köyceğiz, C., & Büyükyıldız, M. (2022). Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 5(3), 1141-1154. https://doi.org/10.47495/okufbed.1037242
AMA Köyceğiz C, Büyükyıldız M. Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata University Journal of The Institute of Science and Techno. December 2022;5(3):1141-1154. doi:10.47495/okufbed.1037242
Chicago Köyceğiz, Cihangir, and Meral Büyükyıldız. “Estimation of Streamflow Using Different Artificial Neural Network Models”. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi 5, no. 3 (December 2022): 1141-54. https://doi.org/10.47495/okufbed.1037242.
EndNote Köyceğiz C, Büyükyıldız M (December 1, 2022) Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi 5 3 1141–1154.
IEEE C. Köyceğiz and M. Büyükyıldız, “Estimation of Streamflow Using Different Artificial Neural Network Models”, Osmaniye Korkut Ata University Journal of The Institute of Science and Techno, vol. 5, no. 3, pp. 1141–1154, 2022, doi: 10.47495/okufbed.1037242.
ISNAD Köyceğiz, Cihangir - Büyükyıldız, Meral. “Estimation of Streamflow Using Different Artificial Neural Network Models”. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi 5/3 (December 2022), 1141-1154. https://doi.org/10.47495/okufbed.1037242.
JAMA Köyceğiz C, Büyükyıldız M. Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata University Journal of The Institute of Science and Techno. 2022;5:1141–1154.
MLA Köyceğiz, Cihangir and Meral Büyükyıldız. “Estimation of Streamflow Using Different Artificial Neural Network Models”. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 5, no. 3, 2022, pp. 1141-54, doi:10.47495/okufbed.1037242.
Vancouver Köyceğiz C, Büyükyıldız M. Estimation of Streamflow Using Different Artificial Neural Network Models. Osmaniye Korkut Ata University Journal of The Institute of Science and Techno. 2022;5(3):1141-54.

23487


196541947019414

19433194341943519436 1960219721 197842261021238 23877

*This journal is an international refereed journal 

*Our journal does not charge any article processing fees over publication process.

* This journal is online publishes 5 issues per year (January, March, June, September, December)

*This journal published in Turkish and English as open access. 

19450 This work is licensed under a Creative Commons Attribution 4.0 International License.