Combined Wavelet Transform With Long Short-Term Memory Neural Network for Water Table Depth Prediction in Baoding City, North China Plain

被引:12
作者
Liang, Zehua [1 ]
Liu, Yaping [1 ,2 ]
Hu, Hongchang [3 ]
Li, Haoqian [1 ]
Ma, Yuqing [1 ]
Khan, Mohd Yawar Ali [4 ]
机构
[1] Capital Normal Univ, Coll Resource Environm & Tourism, Beijing, Peoples R China
[2] Capital Normal Univ, Beijing Lab Water Resources Secur, Beijing, Peoples R China
[3] Tsinghua Univ, Dept Hydraul Engn, State Key Lab Hydrosci & Engn, Beijing, Peoples R China
[4] King Abdulaziz Univ, Dept Hydrogeol, Fac Earth Sci, Jeddah, Saudi Arabia
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
water table depth; long short-term memory neural network; wavelet transform; over-exploitation area; feedforward neural network; North China Plain; GROUNDWATER-FLOW; AQUIFER SYSTEM; SURFACE-WATER; MODEL; RUNOFF; ANN; SIMULATION; IMPACT; STATE;
D O I
10.3389/fenvs.2021.780434
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate estimation of water table depth dynamics is essential for water resource management, especially in areas where groundwater is overexploited. In recent years, as a data-driven model, artificial neural networks (NNs) have been widely used in hydrological modeling. However, due to the non-stationarity of water table depth data, the performance of NNs in areas of over-exploitation is challenging. Therefore, reducing data noise is an essential step before simulating the water table depth. This research proposed a novel method to model the non-stationary time series data of water table depth through combing the advantages of wavelet analysis and Long Short-Term Memory (LSTM) neural network (NN). A typical groundwater over-exploitation area, Baoding, North China Plain (NCP), was selected as a study area. To reflect the impact of anthropogenic activities, the variables harnessed to develop the model includes temperature, precipitation, evaporation, and some socio-economic data. The results show that decomposing the time series of the water table depth into three sub-temporal components by Meyer wavelets can significantly improve the simulation effect of LSTM on the water table depth. The average NSE (Nash-Sutcliffe efficiency coefficient) value of all the sites increased from 0.432 to 0.819. Additionally, a feedforward neural network (FNN) is used to compare forecasts over 12-months. As expected, wavelet-LSTM outperforms wavelet-FNN. As the prediction time increases, the advantages of wavelet-LSTM become more evident. The wavelet-LSTM is satisfactory for forecasting the water table depth at most in 6 months. Furthermore, the importance of input variables of wavelet-LSTM is analysed by the weights of the model. The results indicate that anthropogenic activities influence the water table depth significantly, especially in the sites close to the Baiyangdian Lake, the largest lake in the North China Plain. This study demonstrates that the wavelet-LSTM model provides an option for water table depth simulation and predicting areas of over-exploitation of groundwater.
引用
收藏
页数:17
相关论文
共 47 条
  • [1] Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds
    Adamowski, Jan
    Sun, Karen
    [J]. JOURNAL OF HYDROLOGY, 2010, 390 (1-2) : 85 - 91
  • [2] Forecasting surface water level fluctuations of lake van by artificial neural networks
    Altunkaynak, Adduesselam
    [J]. WATER RESOURCES MANAGEMENT, 2007, 21 (02) : 399 - 408
  • [3] Long short-term memory
    Hochreiter, S
    Schmidhuber, J
    [J]. NEURAL COMPUTATION, 1997, 9 (08) : 1735 - 1780
  • [4] Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control
    Chang, Fi-John
    Chen, Pin-An
    Lu, Ying-Ray
    Huang, Eric
    Chang, Kai-Yao
    [J]. JOURNAL OF HYDROLOGY, 2014, 517 : 836 - 846
  • [5] Groundwater Level Prediction Using SOM-RBFN Multisite Model
    Chen, Lu-Hsien
    Chen, Ching-Tien
    Pan, Yan-Gu
    [J]. JOURNAL OF HYDROLOGIC ENGINEERING, 2010, 15 (08) : 624 - 631
  • [6] Subsystem-level groundwater footprint assessment in North China Plain - The world's largest groundwater depression cone
    Chen, Xiuzhi
    Wang, Pengxiang
    Muhammad, Tahir
    Xu, Zhenci
    Li, Yunkai
    [J]. ECOLOGICAL INDICATORS, 2020, 117 (117)
  • [7] Wavelets: The mathematical background
    Cohen, A
    Kovacevic, J
    [J]. PROCEEDINGS OF THE IEEE, 1996, 84 (04) : 514 - 522
  • [8] Artificial neural network approach for predicting transient water levels in a multilayered groundwater system under variable state, pumping, and climate conditions
    Coppola, E
    Szidarovszky, F
    Poulton, M
    Charles, E
    [J]. JOURNAL OF HYDROLOGIC ENGINEERING, 2003, 8 (06) : 348 - 360
  • [9] Artificial neural network modeling of water table depth fluctuations
    Coulibaly, P
    Anctil, F
    Aravena, R
    Bobée, B
    [J]. WATER RESOURCES RESEARCH, 2001, 37 (04) : 885 - 896
  • [10] Groundwater level forecasting using artificial neural networks
    Daliakopoulos, IN
    Coulibaly, P
    Tsanis, IK
    [J]. JOURNAL OF HYDROLOGY, 2005, 309 (1-4) : 229 - 240