Göl Su Seviyesi Tahmininde Alt Bant Ayrıştırma Tekniklerinin Performanslarının İncelenmesi

Bu çalışmada, doğal bir gölde ortalama su seviyesinin bir aydan altıncı aya kadar olan aylık ileri tahmini için hibrit yöntemler geliştirilmiştir. Göl su seviyesi verileri Ayrık Dalgacık Dönüşümü (DWT), Ampirik Kip Ayrıştırma (EMD), Tekil Spektrum Analiz (SSA) teknikleri kullanılarak ön işleme tabi tutulmuştur ve elde edilen bu alt bant sinyalleri Yapay Sinir Ağlarına (YSA) giriş verileri olarak uygulanmıştır. Böylece üç farklı hibrit model elde edilmiş olup bu modellerin tahmin performansı analiz edilmiştir. Elde edilen sonuçlara göre, su seviyesi verilerine uygulanan ön işleme yöntemleri ile elde edilen hibrit yaklaşımların model performansını iyileştirdiği gözlemlenmiştir ve EMD-ANN ve SSA-ANN hibrit modellerinin bir ila altı aylık bir tahmin dönemi için ortalama aylık göl suyu seviyelerini ANN ve DWT-ANN modeline göre daha iyi tahmin ettiği görülmüştür.

Anahtar Kelimeler:

Göl su seviyesi tahmini, Yapay Sinir Ağları, Ampirik Kip Ayrıştırma, Tekil Spektrum Analizi

Investigation Of Lake Water Level Forecasting Performances Of Subband Decomposition Techniques

In this study, hybrid methods have been developed for estimation of monthly average water level of a natural lake in the coming months from the next one to the sixth month ahead. Lake water level data were preprocessed using Discrete Wavelet Transform (DWT), Empirical Mode Decomposition (EMD), Singular Spectral Analysis (SSA) techniques and these subband signals were applied to the input data of Artificial Neural Networks (ANN). Thus, three different hybrid models were obtained and the prediction performance of these models was analyzed. According to obtained results, it was observed that the hybrid approaches obtained with the preprocessing methods applied to the water level data improved the model performance and EMD-ANN and SSA-ANN hybrid models were found to better predict average monthly lake water levels for a forecast period of one to six months than the ANN and DWT-ANN model

Keywords:

Forecasting of lake water level Artificial Neural Networks, Empirical Mode Decomposition, Singular Spectrum Analysis, Discrete Wavelet Transform,

PDF

___

[1] Chow, V.T., Maidment, D.R., Mays, L.W. 1988. Applied Hydrology. McGraw-Hill. NY
[2] Ebtehaj, I., Bonakdari, H., Gharabaghi, B. 2019. A reliable linear method for modeling lake level fluctuations. Journal of Hydrology, 570, 236–250.
[3] Muşmal, H. 2015. Beyşehir Regülâtörü (Taş Köprü), Tarih Okulu Dergisi (TOD) Journal of History School (JOHS). 357-373
[4] Degens, E. T., Wong, H. K., Kempe, S., & Kurtman, F. (1984). A geological study of Lake Van, eastern Turkey. Geologische Rundschau, 73(2), 701–734.
[5] Batur, E., Kadıoğlu, M., Özkaya, M., Saban, M., Akın, İ., Kaya, Y. 2008. Water Level Modelling of Lake Van and Estimation of Extrem Levels. Van Lake Hydrology and Pollution Conference, 10-25.
[6] Kılınçaslan, T. 2000. The rising water level in Lake Van: environmental features of the Van basin which increase the destructive effect of the disaster. Water Science and Technology, 42(1–2), 173–177.
[7] Box, G.E.P., Jenkins, G.M. 1970. Time Series Analysis: Forecasting and Control. Holden-Day. San Francisco.
[8] Carlson, R.F., MacCormick, A.J.A., Watts, D. G. 1970. Application of linear random models to four annual streamflow series. Water Resources Research. 6, 1070-1078.
[9] Grimaldi, S. 2004. Linear parametric models applied to daily hydrological series. Journal of Hydrologic Engineering. 9, 383-391.
[10] Noakes, D.J., McLeod, A.I., Hipel, K.W. 1985. Forecasting monthly riverflow time series. International Journal of Forecasting. 1:179-190.
[11] Sifuzzaman, M., Islam, M.R., Ali, M.Z.., 2009. Application of wavelet transform and its advantages compared to fourier transform. J. Phys. Sci.. 13, 121–134.
[12] Cahill, A.T. 2002. Determination of changes in streamflow variance by means of a wavelet‐based test. Water Resources Research, 38, 1065-1078.
[13] Padmanabhan, G., Rao. A.R. 1988. Maximum entropy spectral analysis of hydrologic data. Water Resources Research. 24, 1519-1533.
[14] Smith, L. C., Turcotte, D. L., Isacks, B. L. 1998. Stream flow characterization and feature detection using a discrete wavelet transform. Hydrological processes. 12, 233-249.
[15] Yakowitz, S. J. 1973. A stochastic model for daily river flows in an arid region. Water Resources Research. 9, 1271-1285.
[16] Kentel, E. 2009. Estimation of river flow by artificial neural networks and identification of input vectors susceptible to producing unreliable flow estimates. Journal of hydrology. 375, 481-488.
[17] Hydrology, A. T. C. on A. of A. N. N. in. 2000. Artificial neural networks in hydrology. I: Preliminary concepts. Journal of Hydrologic Engineering, 5(2), 115–123.
[18] Hornik, K., Stinchcombe, M., White, H. 1989, Multilayer feedforward networks are universal approximators. Neural Networks. 2, 359-266. [19] Veintimilla-Reyes, J., Cisneros, F., Vanegas, P. 2016. Artificial Neural Networks applied to flow prediction: A use case for the Tomebamba river. Procedia Engineering. 162, 153-161.
[20] El-Shafie, A., Taha, M. R., & Noureldin, A. 2007. A neuro-fuzzy model for inflow forecasting of the Nile river at Aswan high dam. Water resources management. 21, 533-556.
[21] He, Z., Wen, X., Liu, H., & Du, J. 2014. A comparative study of artificial neural network. adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. Journal of Hydrology. 509, 379-386.
[22] Noori, R., Karbassi, A. R., Moghaddamnia, A., Han, D., Zokaei-Ashtiani, M. H., Farokhnia, A., & Gousheh, M. G. 2011. Assessment of input variables determination on the SVM model performance using PCA. Gamma test. and forward selection techniques for monthly stream flow prediction. Journal of Hydrology. 401, 177-189.
[23] Partal, T. 2008. River flow forecasting using different artificial neural network algorithms and wavelet transform. Canadian Journal of Civil Engineering. 36, 26-38.
[24] De Macedo Machado Freire P.K., Santos C.A.G., Da Silva G.B.L. 2019. Analysis of the use of discrete wavelet transforms coupled with ANN for short-term streamflow forecasting. Applied Soft Computing. 80:494-505, 2019.
[25] Huang, N. E., Shen, Z., & Long, S. R., A new view of nonlinear water waves: the Hilbert spectrum. Annual review of fluid mechanics. 31, 417-457.
[26] Kisi O., Latifoğlu L., Latifoglu F. 2014. Investigation of Empirical Mode Decomposition in Forecasting of Hydrological Time Series. Water Resources Management. 28, 4045-4057.
[27] Rezaie-Balf M., Kim S., Fallah H., Alaghmand S. 2019. Daily river flow forecasting using ensemble empirical mode decomposition based heuristic regression models: Application on the perennial rivers in Iran and South Korea. Journal of Hydrology. 572, 470-485.
[28] Hassani, H., Soofi, A. S., & Zhigljavsky, A. A. 2010. Predicting daily exchange rate with singular spectrum analysis. Nonlinear Analysis: Real World Applications. 11, 2023-2034.
[29] Marques, C. A. F., Ferreira, J. A., Rocha, A., Castanheira, J. M., Melo-Goncalves, P., Vaz, N., Dias, J. M. 2006. Singular spectrum analysis and forecasting of hydrological time series. Physics and Chemistry of the Earth. Parts A/B/C. 31:1172-1179.
[30] Latifoğlu, L., Kis,i O., Latifoglu, F. 2015. Importance of hybrid models for forecasting of hydrological variable. Neural Computing & Applications. 26, 1669-1680.
[31] Latifoğlu, L. July 2017. Forecasting of Hyrological Variables Using New Hybrid Methods, Erciyes University, Graduate School of Natural and Applied Sciences Ph.D. Thesis.
[32] Mehr, D. A., Kahya, E., Bagheri, F., Deliktas, E. 2014. Successive-station monthly streamflow prediction using neuro-wavelet technique. Earth Sci. Informatics. 7, 217–229.
[33] Sahay, R. R., Srivastava, A. 2014. Predicting monsoon floods in rivers embedding wavelet transform. genetic algorithm and neural network. Water resources management. 28, 301-317.
[34] Karthikeyan, L., Kumar, D.N. 2013. Predictability of nonstationary time series using wavelet and EMD based ARMA models. Journal of Hydrology. 502,103–119.
[35] Wang, X., Wu, J., Liu, C., Wang, S., & Niu, W. 2016. A Hybrid Model Based on Singular Spectrum Analysis and Support Vector Machines Regression for Failure Time Series Prediction. Quality and Reliability Engineering International. 32, 2717-2738.
[36] Broughton, S.A., Bryan, K. 2018. Discrete Fourier Analysis and Wavelets: Applications to Signal and Image Processing. Wiley.
[37] Zhang, Z. 201). Artificial neural network. In Multivariate time series analysis in climate and environmental research, 1–35.
[38] Wang, S.-C. 2003. Artificial neural network. In Interdisciplinary computing in java programming. 81–100.
[39] Marquardt, DW. 1963. An algorithm for least-squares estimation of nonlinear parameters. Journal of the society for Industrial and Applied Mathematics. 11, 431-441.