A two-stage modelling method for multi-station daily water level prediction. (October 2022)

• Record Type: Journal Article
• Authors: Yuan, Zhi; Liu, Jingxian; Liu, Yi; Zhang, Qian; Li, Yue; Li, Zongzhi
• Is Part Of: Environmental modelling & software. Volume 156(2022)
• Publication Date: 2022-10
• Subjects: Water level prediction -- Multi-station -- Clustering -- Deep learning -- Yangtze river; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2022.105468
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Water level prediction is an essential task in inland water transportation and infrastructure operation. In recent years, the level of uncertainty in the water level variation has increased significantly due to the climate change. Therefore, the need to develop more robust and accurate models for multi-station daily water level prediction along the long and volatile inland rivers has greatly increased. This research proposes a two-stage modelling method to enhance the accuracy and efficiency in simultaneous prediction of daily water levels for multiple stations in inland rivers. Furthermore, taking the Yangtze River trunk line as case study, the daily water data of 19 stations are collected and utilised to verify the performance of the models. First, we divide the 19 stations along the Yangtze River trunk line into 6 clusters by dynamic time warping (DTW) and hierarchical clustering algorithm (HCA). Then, the long short-term memory (LSTM) network and seasonal autoregressive integrated moving average (SARIMA) model are tailored to construct a multi-station daily water level prediction (MSDWLP) model for each cluster. Finally, to validate the proposed method, the daily water level data of 912 consecutive days from the 19 stations are employed. The results demonstrate that the proposed approach can yield more reliable forecasts than traditional deterministic models. Insight from the models can be used to predict daily water levels to better inform decision-making about waterborne transportation, water resources management, and water emergency response. Graphical abstract: This research proposes a two-stage modelling method to enhance the accuracy and efficiency in simultaneous prediction of daily water levels for multiple stations in inland rivers. In the first stage, multiple stations were clustered into some clusters according to the similar characteristics of daily water level, which reduced the influence of elevation and waterway topographic changes on daily water level change, thereby reducing the complexity of simultaneous multiple stations' daily water level prediction. In the second stage, a prediction model was constructed for each cluster stations according to the periodic characteristics of daily water level, which reduced the number of prediction models and the hyperparameters that need to be determined, thereby improving the usability and accuracy of the proposed method. The results of the case study of daily water level prediction at 19 stations along the Yangtze River trunk line show that the method proposed in this paper can yield more reliable and efficient forecasting. Image 1 Highlights: A two-stage modelling for multi-station daily water level prediction method was proposed. Clustered stations with similar characteristics, which reduces the calculation cost of modelling for multiple stations. Tailored prediction model for each cluster stations, which improve the accuracy of simultaneous water levels prediction of multiple stations. Developed method was validated using daily water levels from 19 stations along the Yangtze River trunk line.