BibTex RIS Cite

Simulation of Savalan Irrigation Reservoir by Using Artificial Neural Networks

Year 2007, Volume: 13 Issue: 04, 337 - 345, 01.11.2007

Abstract

Water resources limitation, aim variety and financial sources inadequacy make the managing of optimum releasing to be a great necessity. The undesired temporal and spatial distribution of rainfall, strategic situation of agricultural crops and complicated systems of water resources all are caused the application of mathematical models to be a necessity. On the other hand the stochastic property of inflow to the reservoir system makes the forecast of operation rules in reservoirs to have great importance for irrigation of farmlands. The aim of simulation technique is to predict a behavior of reservoir system in future operation periods. Decision makers make a good management for system operation by application of different scenarios. Savalan dam reservoir with 90 hm3 active capacity was constructed to irrigate 1200 ha agricultural lands in Ardabil province. The monthly water demand of down stream agricultural lands assumed to be supplied perfectly. In this research to along dam reservoir operation forecast namely storage value, spill, evaporation and precipitation over reservoir lake the multi-layer feed forward back propagation ANN method used for simulation of reservoir inflow. The reservoir continuity equation was solved for both cases historical flow and simulated one for the purpose of reservoir parameters calculation parameters obtained from both cases of inflow were compared. The results showed the best consistency observed and calculated parameters

References

  • Anctil, F., C. Perrin and V., Andreassian. 2004. Impact of the length of observed records on theperformance of ANN and forecasting models. Journal of Environmental Models Software 19:357-368. rainfall-runoff
  • Anonim, 2002. Hydrological report of Savalan Reservoir. Ashnab Consulting Engineers.
  • Brikundavyi, S., R. Labib, H. T Trung and J. Rousselle. 2002. Performance of neural networks indaily streamflow forecasting. Journal of Hydrologic Engineering. 7 (5): 392–398.
  • Campolo, M., P. Andreussi and A. Soldati. 1999. River flood forecasting with a neural network model.Journal of Water Resources Research. 35 (4) : 1191–1197.
  • Cigizoglu, H.K., 2003. Estimation, forecasting and extrapolation of flow data by artificial neuralnetworks. Hydrological Sciences Journal, 48 (3) : 349-361.
  • Cigizoglu, H. K. and M. Alp. 2004. Rainfall-runoff modeling using three neural network methods. Artificial Intelligence and Soft Computing- ICAISC 2004, Lecture Notes in Artificial Intelligence, 3070, 166-171.
  • Cigizoglu, H. K., and O. Kisi. 2005. Flow prediction by two back propagation techniques using k-fold partitioning of neural network training data. Journal of Nordic Hydrology, 36 (1) : 1-16.
  • Coulibaly, P., F. Anctil and B. Bobe´e, 1998. Real time neural network based forecasting system forhydropower reservoirs. Proceedings of the First International Conferenceon New Information. Technologies for Decision Making in Civil Engineering. Quebec, Montreal, Canada, 1001–1011. University of
  • Hsu, K. L., H. V. Gupta and S. Sorooshian. 1995. Artificial neural network modeling of the rainfall-runoffprocess. Journal of Water Resources Research. 31 (10): 2517– 2530.
  • Jain, S. K., D. Das and D. K. Srivastava. 1999. Application of ANN for reservoir inflow prediction and operation. Journal Management. 125 (5): 263–271. Planning and statistical, and artificial neural
  • Kisi, O. 2004. River flow modeling using artificial neural networks. Journal of Hydrologic Engineering. 9 (1): 60- 63.
  • Rumelhart, D. E., G. E. Hinton and R. J. Williams. 1986. Learning internal representation by errorpropagation. In: Rumelhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing:Explorations in the Microstructure of Cognition, vol. 1. MIT Press, Cambridge, MA, 318–362.
  • Shamseldin, A. Y. 1997. Application of a neural network technique to rainfall–runoff modeling. Journal of Hydrology 199: 272–294.
  • Thirumalaiah, K and M. C. Deo. 1998. Real-time flood forecasting using neural networks. Journal of Computer-Aided Civil Infrastructure Engineering, 13 (2): 101–111.
  • Yurtoğlu, H. 2005. Yapay Sinir Ağları Metodolojisi İle Öngörü Modellemesi. Ekonomik Modeller ve Stratejik Araştırmalar Genel Müdürlüğü Yayınları.
  • Zealand, C. M., D. H. Burn and S. P. Simonovic. 1999. Short- term stream flow forecasting usingartificial neural networks. Journal of Hydrology 214: 32–48.

Yapay sinir ağları yöntemi ile savalan sulama rezervuarının simülasyonu

Year 2007, Volume: 13 Issue: 04, 337 - 345, 01.11.2007

Abstract

Su kaynaklarının kısıtlılığı, amaçlardaki çeşitlilikler ve parasal kaynakların yetersizliği, optimum işletmeyi gerektirmektedir. Yağışların zaman ve konum açısından düzgün dağılmaması, tarımsal ürünlerin stratejik önemi ve su kaynakları sistemlerinde bulunan karmaşıklıklar, matematiksel modellerin kullanımını ve gelişmesini giderek artırmaktadır. Öte yandan su depolama yapısına giren akımların rastgelelik özelliğinden dolayı gelecekteki işletme kurallarının tahmini, arazilerin sulamasında önemli rol oynamaktadır. Simülasyon yönteminin amacı rezervuar sisteminin gelecekteki işletme dönemlerinde durumunu tahmin etmektir. Karar vericiler çeşitli senaryolar kullanarak, sistemin işletmesinde iyi bir yönetim sürdürmek isterler. Savalan barajı 90 hm3 aktif kapasite ile 1200 ha tarımsal alanı sulama amacı ile İran’ın Ardabil bölgesinde inşa edilmiştir. Mansapta bulunan tarım alanlarının aylık su taleplerinin tamamen karşılanacağı varsayılmıştır. Bu çalışmada rezervuar işletmesinde depolanan, savaklanan, hazne alanı üzerine düşen yağış ve buradan buharlaşan su miktarları, akımların çok tabakalı ileri beslemeli geriye yayınım yapay sinir ağları simülasyonu yönteminden yararlanarak tahmin edilmiştir. Rezervuar için süreklilik denklemi hem ölçülmüş ve hem de simüle edilmiş akımlarla çözülerek rezervuar parametreleri araştırılmıştır. Sonuçlar, gözlenmiş değerler ve simülasyonundan elde edilen değerler arasında genellikle uyum sağlandığını göstermektedir. AnahtarKelimeler: Rezervuar yönetimi, rezervuar simülasyonu, optimum işletme ve yapay sinir ağları YSA

References

  • Anctil, F., C. Perrin and V., Andreassian. 2004. Impact of the length of observed records on theperformance of ANN and forecasting models. Journal of Environmental Models Software 19:357-368. rainfall-runoff
  • Anonim, 2002. Hydrological report of Savalan Reservoir. Ashnab Consulting Engineers.
  • Brikundavyi, S., R. Labib, H. T Trung and J. Rousselle. 2002. Performance of neural networks indaily streamflow forecasting. Journal of Hydrologic Engineering. 7 (5): 392–398.
  • Campolo, M., P. Andreussi and A. Soldati. 1999. River flood forecasting with a neural network model.Journal of Water Resources Research. 35 (4) : 1191–1197.
  • Cigizoglu, H.K., 2003. Estimation, forecasting and extrapolation of flow data by artificial neuralnetworks. Hydrological Sciences Journal, 48 (3) : 349-361.
  • Cigizoglu, H. K. and M. Alp. 2004. Rainfall-runoff modeling using three neural network methods. Artificial Intelligence and Soft Computing- ICAISC 2004, Lecture Notes in Artificial Intelligence, 3070, 166-171.
  • Cigizoglu, H. K., and O. Kisi. 2005. Flow prediction by two back propagation techniques using k-fold partitioning of neural network training data. Journal of Nordic Hydrology, 36 (1) : 1-16.
  • Coulibaly, P., F. Anctil and B. Bobe´e, 1998. Real time neural network based forecasting system forhydropower reservoirs. Proceedings of the First International Conferenceon New Information. Technologies for Decision Making in Civil Engineering. Quebec, Montreal, Canada, 1001–1011. University of
  • Hsu, K. L., H. V. Gupta and S. Sorooshian. 1995. Artificial neural network modeling of the rainfall-runoffprocess. Journal of Water Resources Research. 31 (10): 2517– 2530.
  • Jain, S. K., D. Das and D. K. Srivastava. 1999. Application of ANN for reservoir inflow prediction and operation. Journal Management. 125 (5): 263–271. Planning and statistical, and artificial neural
  • Kisi, O. 2004. River flow modeling using artificial neural networks. Journal of Hydrologic Engineering. 9 (1): 60- 63.
  • Rumelhart, D. E., G. E. Hinton and R. J. Williams. 1986. Learning internal representation by errorpropagation. In: Rumelhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing:Explorations in the Microstructure of Cognition, vol. 1. MIT Press, Cambridge, MA, 318–362.
  • Shamseldin, A. Y. 1997. Application of a neural network technique to rainfall–runoff modeling. Journal of Hydrology 199: 272–294.
  • Thirumalaiah, K and M. C. Deo. 1998. Real-time flood forecasting using neural networks. Journal of Computer-Aided Civil Infrastructure Engineering, 13 (2): 101–111.
  • Yurtoğlu, H. 2005. Yapay Sinir Ağları Metodolojisi İle Öngörü Modellemesi. Ekonomik Modeller ve Stratejik Araştırmalar Genel Müdürlüğü Yayınları.
  • Zealand, C. M., D. H. Burn and S. P. Simonovic. 1999. Short- term stream flow forecasting usingartificial neural networks. Journal of Hydrology 214: 32–48.
There are 16 citations in total.

Details

Primary Language Turkish
Journal Section Research Article
Authors

Mohammad T. Sattar This is me

A. Fakher Fard This is me

Mohammad Docherkhesaz This is me

Fazlı Öztürk This is me

Publication Date November 1, 2007
Published in Issue Year 2007 Volume: 13 Issue: 04

Cite

APA Sattar, M. T., Fard, A. F., Docherkhesaz, M., Öztürk, F. (2007). Yapay sinir ağları yöntemi ile savalan sulama rezervuarının simülasyonu. Journal of Agricultural Sciences, 13(04), 337-345.

Journal of Agricultural Sciences is published open access journal. All articles are published under the terms of the Creative Commons Attribution License (CC BY).