College of Hydrology and Water Resources, Hohai University, Nanjing 210098, Jiangsu, China.
College of Hydrology and Water Resources, Hohai University, Nanjing 210098, Jiangsu, China.
Sci Total Environ. 2021 Aug 20;783:146948. doi: 10.1016/j.scitotenv.2021.146948. Epub 2021 Apr 8.
Developing models that can accurately simulate groundwater level is important for water resource management and aquifer protection. In particular, machine learning tools provide a new and promising approach to efficiently forecast long-term groundwater table fluctuations without the computational burden of building a detailed flow model. This study proposes a multistep modeling framework for simulating groundwater levels by combining the wavelet transform (WT) with the long short-term memory (LSTM) network; the framework is named the combined WT-multivariate LSTM (WT-MLSTM) method. First, the WT decomposes the groundwater level time series (i.e., the training stage) into a self-control term and a set of external-control terms. Second, Pearson correlation analysis reveals the correlations between the influencing factors (i.e., river stage) and the groundwater table, and the multivariate LSTM model incorporating external factors is built to simulate the external-control terms. Third, the spatiotemporal evolution of the groundwater level is modeled by reconstructing the sequence of each term of the groundwater level time series. Methodological applications in the Liangshui River Basin, Beijing, China and the Cibola National Wildlife Refuge along the lower Colorado River, United States, show that the combined WT-MLSTM model has a higher simulation accuracy than the standard LSTM, MLSTM, and WT-LSTM models. A comparison between the combined WT-MLSTM model and support vector machine (SVM) also demonstrates the advantage of the proposed model. Additional comparison between model forecasts and observed groundwater levels shows the model predictability for short-term time series. Further analysis reveals that the applicability of the combined WT-MLSTM model decreases with increasing distance between the groundwater well and adjacent river channel, or with the increasing complexity of the changing groundwater level patterns, which may be driven by additional controlling factors. This study therefore provides a new methodology/approach for the rapid and accurate simulation and prediction of groundwater level.
开发能够准确模拟地下水位的模型对于水资源管理和含水层保护至关重要。特别是，机器学习工具提供了一种新的有前途的方法，可以在不构建详细流动模型的计算负担的情况下，有效地预测长期地下水位波动。本研究提出了一种结合小波变换 (WT) 和长短时记忆 (LSTM) 网络的多步骤建模框架来模拟地下水位，该框架命名为组合 WT-多变量 LSTM (WT-MLSTM) 方法。首先，WT 将地下水位时间序列（即训练阶段）分解为自控制项和一组外部控制项。其次，皮尔逊相关分析揭示了影响因素（即河水位）与地下水位之间的相关性，并建立了包含外部因素的多变量 LSTM 模型来模拟外部控制项。第三，通过重建地下水位时间序列中每个项的序列来模拟地下水位的时空演变。在中国北京凉水河流域和美国科罗拉多河下游的奇博拉国家野生动物保护区的方法应用表明，组合 WT-MLSTM 模型的模拟精度高于标准 LSTM、MLSTM 和 WT-LSTM 模型。组合 WT-MLSTM 模型与支持向量机 (SVM) 的比较也证明了该模型的优势。模型预测与观测地下水位的进一步比较表明了该模型对短期时间序列的可预测性。进一步的分析表明，组合 WT-MLSTM 模型的适用性随着地下水井与相邻河道之间的距离增加或地下水位变化模式的复杂性增加而降低，这可能是由附加控制因素驱动的。因此，本研究为快速准确地模拟和预测地下水位提供了一种新的方法/方法。
