http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Tugce Anilan*,,Ugur Satilmis,Murat Kankal,Omer Yuksek 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.5
This study presents the use of L-moments based regression analysis and Artificial Neural Networks (ANN) for forecasting maximum annual flows of Eastern Black Sea Basin, Turkey. Homogeneity of the region is determined by discordancy (Di) and heterogeneity (Hi) measures based on L-moments. Several distributions are fitted to the data of the 33 stream gauging stations. Return periods (T) corresponding to each flow rates are calculated using the probability density functions of best fit distribution of the region. Using these T values and also drainage area, main stream slope, elevation, stream density, and mean annual rainfall values as independent variables, regression and ANN models are adopted to the data. Mean relative error, mean absolute error and root mean square error are applied for evaluating the performance of the models. Error values indicate that ANN method yields better results for estimation of maximum flows.
Forecasting Daily Streamflow Discharges Using Various Neural Network Models and Training Algorithms
Sinan Nacar,M. Ali Hınıs,Murat Kankal 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.9
Streamflow forecasting based on past records is an important issue in both hydrologic engineering and hydropower reservoir management. In the study, three artificial Neural Network (NN) models, namely NN with well-known multi-layer perceptron (MLPNN), NN with principal component analyses (PCA-NN), and NN with time lagged recurrent (TLR-NN), were used to 1, 3, 5, 7, and 14 ahead of daily streamflow forecast. Daily flow discharges of Haldizen River, located in the Eastern Black Sea Region, Turkey the time period of 1998-2009 was used to forecast discharges. Backpropagation (BP), Conjugate Gradient (CG), and Levenberg- Marquardt (LM) were applied to the models as training algorithm. The result demonstrated that, firstly, the forecast ability of CG algorithm much better than BP and LM algorithms in the models; secondly, the best performance was obtained by PCA-NN and MLP-NN for short time (1, 3, and 5 day-ahead) forecast and TLR-NN for long time (7 and 14 day-ahead) forecast.