Su yapılarının planlanması ve yönetiminde nehir akım tahminleri önemli bir yere sahiptir. Lineer olmayan ve durağan olmayan karaktere sahip nehir akım verilerinin doğru tahmini zorlu bir problemdir. Son yıllarda veri tabanlı teknikler, nehir akım problemlerinde yoğun olarak kullanılmaktadır. Önerilen çalışmada popüler olarak kullanılmaya başlanan Derin Sinir Ağlarından Uzun – Kısa Süreli Bellek (Long-Short Term Memory, LSTM) Ağları ile nehir akım tahmini gerçekleştirilmiştir. Tahmin performansını artırmak üzere zaman serilerinin analizinde önemli bir yer tutan Tekil Spektrum Analizi (TSA) kullanılarak alt bant verileri elde edilmiştir. Nehir akım tahmin verisine ait TSA alt bant verilerinin LSTM ağları ile tahmini sonucu bir ileri adım tahmin çalışması gerçekleştirilmiştir. Önerilen TSA-LSTM modeli kullanılarak 0.0021 Ortalama Karesel Hata (MSE) değeri, 0.0361 Ortalama Mutlak Hata (MAE) değeri ve 0.9710 Korelasyon (R) değeri ile yüksek performanslı tahmin verisi elde edilmiştir.
In the planning and management of water structures, river flow forecasts play an important role. The correct prediction of the river flow data with non-linear and non-stable characters is a difficult problem. In recent years, data-based techniques have been widely used in the river flow problems. In the proposed study, the river flow forecast was carried out with the Long-Short Term Memory (LSTM) networks from deep nerve networks, which began to be popularly used. Subband data have been obtained using Single Spectrum Analysis (TSA), which holds an important place in time series analysis to improve predictive performance. A forward-step forecast work was carried out as a result of the forecast of the TSA subband data of the river flow forecast data with LSTM networks. Using the recommended TSA-LSTM model, high performance forecast data were obtained with 0.0021 average square error (MSE) value, 0.0361 average absolute error (MAE) value and 0.9710 correlation (R) value.
Stream flow estimation has an important role in the planning and management of water resources. Accurate estimation of stream flow data, that is characterised ny non-linear and non-stationary, is a challenging problem. In recent years, data-based techniques have been used extensively in forecasting of stream flow. In this study, stream flow estimation was made with the Long-Short Term Memory (LSTM) Networks from Deep Neural Networks, which were used as popular. Subband data was obtained by using Single Spectrum Analysis (SSA), which plays an important role in the analysis of time series in order to increase the forecast performance. As a result of estimation of SSA subband data of stream flow forecasting data with LSTM network, one ahead forecasting study was carried out. Using this proposed SSA-LSTM model, high performance forecasted data was obtained with 0.0021 Mean Square Error (MSE) value, 0.0361 Mean Absolute Error (MAE) value and 0.9710 Correlation (R) coefficient value.
Alan : Fen Bilimleri ve Matematik; Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|