Artificial Intelligent Models For Flow Prediction: A Case Study On Alara Stream
Öz
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.
Anahtar Kelimeler
Kaynakça
- 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.
Ayrıntılar
Birincil Dil
İngilizce
Konular
Mühendislik
Bölüm
Rapor
Yayımlanma Tarihi
1 Mart 2010
Gönderilme Tarihi
21 Aralık 2009
Kabul Tarihi
-
Yayımlandığı Sayı
Yıl 2010 Cilt: 1 Sayı: 1