Report
BibTex RIS Cite

Akim Tahmini Için Yapay Zeka Modeller: Alara Çayi Örneği

Year 2010, Volume: 1 Issue: 1, 8 - 13, 01.03.2010

Abstract

Su yapılarının projelendirilmesinde, akım miktarı ile ilgili bilgilere ihtiyaç duyulur. Akım miktarının gelecekte, belli bir tarihte ne olacağının tahmini, taşkın kontrolü amaçlı haznelerin işletilmesinde, akarsudaki su potansiyelinin belirlenmesinde, bir hidroelektrik santral için kurak dönemlerde üretimin nasıl etkileneceğinin bilinmesinde, içme ve sulama suyunun dağıtımında ve akarsulardaki ulaşımın planlanmasında önem taşımaktadır. Akım tahminin de kullanılan metotlar, kısa süreli akım tahmini için, yağış akış modelleri ya da akım öteleme modelleri; uzun süreli akım tahmini için ise indis değişkeni modelleri, su bütçesi modelleri, yağış akış modelleri ve zaman serisi modelleri olarak sayılabilmektedir. Çalışmada Akdeniz Bölgesi içerisinde yer alan, Alara Çayına ait akımların tahmininde mevcut tahmin metotlarına alternatif olarak, son zamanlarda hidrolojik problemlerin çözümünde yaygın kullanıma sahip olan yapay zeka yöntemlerden yapay sinir ağları (YSA) ve adaptif ağ temelli bulanık çıkarım sistemleri (ANFIS) yöntemleri kullanılmıştır. Yapay zeka yöntemlerde kullanılan akım miktarları 9-17 nolu akım gözlem istasyonuna ait aylık ortalama akım değerleridir. Zaman serileri akım tahmini çalışması sonucunda Markov modelleri ile mertebesi belirlenen Alara Çayı için, yapay zeka yöntemlerle akım tahmin yaklaşımında girdi değişkenleri olarak önceki yılların akım değerleri ve periyodiklik için de cos(2πi/12), sin(2πi/12) değerleri seçilmişlerdir. Karşılaştırma sonucunda, YSA ile elde edilen tahminlerin geçmiş akım verileri ile daha uyumlu sonuçlar verdiği görülmüştür. 

References

  • C.E. Imrie, S. Durucan, A. Korre, “Stream flow prediction using artificial neural networks: generalisation beyond the calibration range” Journal of Hydrology, 233, 138-153 2000.
  • C.M. Zealand, D.H. Burn, S.P. Simonovic, “Short term streamflow forecasting using artificial neural networks” Journal of Hydrology, 214, 32-48, 1999.
  • K.C. Luk, J.E. Ball, A. Sharma, “A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting” Journal of Hydrology, Vol.227, pp. 56-65, 2000.
  • J.A. Jervase, A. Al-Lawati, A.S.S. Dorvlo, “Contour maps for sunshine ratio for Oman using radial basis function generated data” Renewable Energy, Vol.28, pp.487-497, 2002.
  • Y.B. Dibike, D.P. Solomatine, “Stream flow forecasting using artificial neural networks” Phys. Chem. Earth (B), Vol.26, pp.1-7, 2001.
  • R.D. Braddock, M.L. Kremmer, L. Sanzogni, “Feed-forward artificial neural network model for forecasting rainfall run-off” Environmetrics, Vol.9, pp.419-432, 1998.
  • M.E. Keskin, Ö. Terzi, “Artificial Neural Network models of Daily pan Evaporation” Journal of Hydrologic Engineering, Vol.11(1), pp. 65-70, 2006.
  • S.-H. Chen, Y.-H. Lin, L.-C. Chang, F.-J. Chang, “The strategy of building a flood forecast model by neuro-fuzzy network” Hydrol. Processes, Vol.20, pp.1525–1540, 2006.
  • T. Tingsanchali, M. R. Gautam, “Application of tank, NAM, ARMA and neural network models to flood forecasting” Hydrol. Process., Vol.14, pp. 2473-2487, 2000.
  • R. J. Frank, N. Davey, S.P. Hunt, “Time series prediction and Neural networks” Journal of Intelligent and Robotic Systems,
  • Vol.31, pp.91-103 , 2001.
  • K.P. Sudheer, P.C. Nayak, K.S. Ramasastri, “Improving peak flow
  • estimates in artificial neural network river flow models” Hydrological
  • Processes, Vol.17, pp.677-686, 2003.
  • L.C. Chang, F.J. Chang, Y.M. Chiang, “A two-step-ahead recurrent neural network for stream-flow forecasting” Hydrological Processes, Vol.18, pp.81-92, 2004.
  • M.P. Rajurkar, U.C. Kothyari, U.C. Chaube, “Modeling of the daily rainfall-runoff relationship with artificial neural network” Journal of Hydrology, Vol.285, pp. 96-113, 2004.
  • Tingsanchali, T., Gautam, M. R., 2000. “Application of tank, NAM, ARMA and neural network models to flood forecasting” Hydrol. Process, Vol.14, pp. 2473-2487.
  • J. S. R. Jang, “Self-learning fuzzy controllers based on temporal back propagation” IEEE Trans. Neural Networks, Vol.3(5), pp.714–723, 1992.
  • L.-C. Chang, F. J. Chang, “Intelligent control for modelling of real- time reservoir operation” Hydrol. Processes, Vol.15, pp. 1621– 1634, 2001.
  • W.S. McCulloch, W. Pitts, “A logical calculus of ideas immanent in nervous activity” Bull. Math. Biophys., Vol.5, pp.115-133, 1943.
  • EİE, Su Akımları Aylık Ortalamaları, Elektrik İşleri Etüt İdaresi Genel Müdürlüğü, Ankara,2003.
  • C.T. Lin, C.S.G. Lee, Neural Fuzzy Systems, Prentice Hall P.T.R., Upper Saddle Stream, NJ 07458, 1996.
  • L. H. Tsoukalas, R. E. Uhrig, Fuzzy and Neural Approaches in Engineering, Wiley-Interscience, John Wiley & Sons. Inc., New York, USA, 1997.

Artificial Intelligent Models For Flow Prediction: A Case Study On Alara Stream

Year 2010, Volume: 1 Issue: 1, 8 - 13, 01.03.2010

Abstract

For designing of water resources structures, information interesting in volume and rate of water is needed. Forecasting of flow in future is important for operating of flood control reservoirs, determining of potential flow in stream, amount of flow in drought periods evaluating of electric generation in a power plant, delivering of domestic and irrigation water, and planning of navigation in streams. A number of methods are used in flow forecasting. Predictionrunoff models or flood routing models are used for short time forecasting whereas water budget models, flood routing models and time series models are used for long time periods. In this study, for flow prediction of Alara Stream in Mediterranean Region artificial intelligent models used in solving of hydrological problems recently are developed as alternative conventional methods. Artificial Neural Networks (ANN) and Adaptive Neural Based Inference Systems (ANFIS) are selected for modeling. Monthly mean flow data from the 9–17 station on the Alara Stream is used for artificial intelligence models. After determining model degree using Markov models, the input layer consisted of previous flows and cos (2πi/12), sin (2πi/12) (i =1, 2, ..., 12) for the effect of monthly periodicity, and the output layer contained a single flow value for time t for artificial models. When predicting results are compared for two modeling techniques, both low and high flows are better predicted by ANN than ANFIS. 

References

  • C.E. Imrie, S. Durucan, A. Korre, “Stream flow prediction using artificial neural networks: generalisation beyond the calibration range” Journal of Hydrology, 233, 138-153 2000.
  • C.M. Zealand, D.H. Burn, S.P. Simonovic, “Short term streamflow forecasting using artificial neural networks” Journal of Hydrology, 214, 32-48, 1999.
  • K.C. Luk, J.E. Ball, A. Sharma, “A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting” Journal of Hydrology, Vol.227, pp. 56-65, 2000.
  • J.A. Jervase, A. Al-Lawati, A.S.S. Dorvlo, “Contour maps for sunshine ratio for Oman using radial basis function generated data” Renewable Energy, Vol.28, pp.487-497, 2002.
  • Y.B. Dibike, D.P. Solomatine, “Stream flow forecasting using artificial neural networks” Phys. Chem. Earth (B), Vol.26, pp.1-7, 2001.
  • R.D. Braddock, M.L. Kremmer, L. Sanzogni, “Feed-forward artificial neural network model for forecasting rainfall run-off” Environmetrics, Vol.9, pp.419-432, 1998.
  • M.E. Keskin, Ö. Terzi, “Artificial Neural Network models of Daily pan Evaporation” Journal of Hydrologic Engineering, Vol.11(1), pp. 65-70, 2006.
  • S.-H. Chen, Y.-H. Lin, L.-C. Chang, F.-J. Chang, “The strategy of building a flood forecast model by neuro-fuzzy network” Hydrol. Processes, Vol.20, pp.1525–1540, 2006.
  • T. Tingsanchali, M. R. Gautam, “Application of tank, NAM, ARMA and neural network models to flood forecasting” Hydrol. Process., Vol.14, pp. 2473-2487, 2000.
  • R. J. Frank, N. Davey, S.P. Hunt, “Time series prediction and Neural networks” Journal of Intelligent and Robotic Systems,
  • Vol.31, pp.91-103 , 2001.
  • K.P. Sudheer, P.C. Nayak, K.S. Ramasastri, “Improving peak flow
  • estimates in artificial neural network river flow models” Hydrological
  • Processes, Vol.17, pp.677-686, 2003.
  • L.C. Chang, F.J. Chang, Y.M. Chiang, “A two-step-ahead recurrent neural network for stream-flow forecasting” Hydrological Processes, Vol.18, pp.81-92, 2004.
  • M.P. Rajurkar, U.C. Kothyari, U.C. Chaube, “Modeling of the daily rainfall-runoff relationship with artificial neural network” Journal of Hydrology, Vol.285, pp. 96-113, 2004.
  • Tingsanchali, T., Gautam, M. R., 2000. “Application of tank, NAM, ARMA and neural network models to flood forecasting” Hydrol. Process, Vol.14, pp. 2473-2487.
  • J. S. R. Jang, “Self-learning fuzzy controllers based on temporal back propagation” IEEE Trans. Neural Networks, Vol.3(5), pp.714–723, 1992.
  • L.-C. Chang, F. J. Chang, “Intelligent control for modelling of real- time reservoir operation” Hydrol. Processes, Vol.15, pp. 1621– 1634, 2001.
  • W.S. McCulloch, W. Pitts, “A logical calculus of ideas immanent in nervous activity” Bull. Math. Biophys., Vol.5, pp.115-133, 1943.
  • EİE, Su Akımları Aylık Ortalamaları, Elektrik İşleri Etüt İdaresi Genel Müdürlüğü, Ankara,2003.
  • C.T. Lin, C.S.G. Lee, Neural Fuzzy Systems, Prentice Hall P.T.R., Upper Saddle Stream, NJ 07458, 1996.
  • L. H. Tsoukalas, R. E. Uhrig, Fuzzy and Neural Approaches in Engineering, Wiley-Interscience, John Wiley & Sons. Inc., New York, USA, 1997.
There are 23 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section İnşaat Mühendisliği
Authors

Mustafa Keskin This is me

Emine Taylan

Publication Date March 1, 2010
Submission Date December 21, 2009
Published in Issue Year 2010 Volume: 1 Issue: 1

Cite

APA Keskin, M., & Taylan, E. (2010). Artificial Intelligent Models For Flow Prediction: A Case Study On Alara Stream. Mühendislik Bilimleri Ve Tasarım Dergisi, 1(1), 8-13.