A novel method for lake level prediction: deep echo state network
- PDF / 1,976,570 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 191 Views
ORIGINAL PAPER
A novel method for lake level prediction: deep echo state network Meysam Alizamir 1 & Ozgur Kisi 2 & Sungwon Kim 3 & Salim Heddam 4 Received: 24 January 2020 / Accepted: 2 September 2020 # Saudi Society for Geosciences 2020
Abstract Accurately prediction of lake level fluctuations is essential for water resources planning and management. In the present study, the potential of a novel method, deep echo state network (Deep ESN), is investigated for monthly lake level prediction and its results are compared with three data-driven methods, artificial neural networks (ANNs), extreme learning machine (ELM), and regression tree (Reg. Tree). The methods are validated using root mean square errors (RMSE), determination coefficient (R2), and Nash-Sutcliffe efficiency (NSE) criteria. The investigated method (Deep ESN) outperforms the ELM, ANNs, and Reg. Tree by improving accuracies by 61–62–96%, 10–14–84%, and 8–23–80% in prediction 1 month, 2 months, and 3 months ahead lake level fluctuations in terms of RMSE criteria, respectively. Also, accuracy of ELM, ANNs, and Reg. Tree was significantly increased using Deep ESN model by 1.1–1.1–443%, 1.1–1.6–250%, and 1.6–6.5–184% in terms of NSE indicator for different lead-time horizons. Among the ELM, ANNs, and Reg. Tree, the third method provides the worst predictions while the first method performs superior to the second one in all tree time horizons. Keywords Lake level prediction . Deep echo state network . Extreme learning machine . ANNs . Regression tree
Introduction Lake is a local space with water, apart from river basin. It includes land and is larger and deeper than pond and pool. Many lakes are constructed for agricultural drainage, electric generation, drinking water, and waterfront recreations (Hu et al. 2008; Wantzen et al. 2008; Vuglinskiy 2009). Lakes as an important water supply in the world occupy only 0.3% of total surface water. Many countries and government-based Responsible Editor: Broder J. Merkel * Meysam Alizamir [email protected] 1
Department of Civil Engineering, Hamedan Branch, Islamic Azad University, Hamedan, Iran
2
Faculty of Natural Sciences and Engineering, Ilia State University, Tbilisi, Georgia
3
Department of Railroad Construction and Safety Engineering, Dongyang University, Yeongju 36040, Republic of Korea
4
Faculty of Science, Agronomy Department, Hydraulics Division, Laboratory of Research in Biodiversity Interaction Ecosystem and Biotechnology, University 20 Août 1955, Route El Hadaik, 26 Skikda, BP, Algeria
organizations aim to enhance water quality of lakes based on water resources protection strategies by developing sustainable management policies (Giuliani et al. 2019; Teshome 2020; Vasistha and Ganguly 2020). Lake level variation depending on the time series may be resulted from the complex phenomena of hydrologic and climatic characteristics such as rainfall, runoff, evaporation, and temperature. In addition, the lake level prediction using hydrologic variables can provide an important and valuable data f
Data Loading...