22 Jul 2022
22 Jul 2022
Status: a revised version of this preprint was accepted for the journal HESS.

Advance prediction of coastal groundwater levels with temporal convolutional network

Xiaoying Zhang1,2, Fan Dong1,2, Guangquan Chen3, and Zhenxue Dai1,2 Xiaoying Zhang et al.
  • 1Institute of Intelligent Simulation and Early Warning for Subsurface Environment, Jilin University, Changchun, China
  • 2College of Construction Engineering, Jilin University, Changchun, China
  • 3Key Laboratory of Marine Sedimentology and Environmental Geology, First Institute of Oceanography, State Oceanic Administration, Qingdao, China

Abstract. Prediction of groundwater level is of immense importance and challenges for the coastal aquifer management with rapidly increasing climatic change. With the development of artificial intelligence, the data driven models have been widely adopted in predicting hydrological processes. However, due to the limitation of network framework and construction, they are mostly adopted to produce only one-time step in advance. Here, a TCN-based model is developed to predict groundwater level variations with different leading periods in a coastal aquifer. The historical precipitation and tidal level data are incorporated as input data. The first hourly-monitored ten-month data were used for model training and testing, and the data of the following three months were predicted with 24, 72, 18 and 360 time steps in advance. For one-step prediction of the two wells, the calculated R2 are higher than 0.999 in the prediction stage. The performance is meanwhile compared with a powerful network in the field of time-series prediction, long short-term memory (LSTM) recurrent network. The corresponding R2 of the LSTM-based model are 0.996 and 0.998. While the RMSE values of TCN-based model are less than that of LSTM-based model with shorter running times. For the advanced prediction, the model accuracy greatly decreases with the increase of advancing period from 1-day to 3-, 7- and 15-days. Overall, the TCN- and LSTM-based models show great ability to learn complex patterns in advance using historical data within the time series. Considering the simulation accuracy and efficiency, the TCN-based model outperforms the LSTM-based model and has been proved to be a valid localized groundwater prediction tool in the subsurface environment.

Xiaoying Zhang et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-236', Anonymous Referee #1, 20 Aug 2022
    • AC1: 'Reply on RC1', Zhenxue Dai, 18 Sep 2022
  • RC2: 'Comment on hess-2022-236', Anonymous Referee #2, 14 Sep 2022
    • AC2: 'Reply on RC2', Zhenxue Dai, 18 Sep 2022

Xiaoying Zhang et al.

Xiaoying Zhang et al.


Total article views: 405 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
294 97 14 405 6 9
  • HTML: 294
  • PDF: 97
  • XML: 14
  • Total: 405
  • BibTeX: 6
  • EndNote: 9
Views and downloads (calculated since 22 Jul 2022)
Cumulative views and downloads (calculated since 22 Jul 2022)

Viewed (geographical distribution)

Total article views: 372 (including HTML, PDF, and XML) Thereof 372 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 01 Dec 2022
Short summary
Under data-drive framework, the groundwater levels generally can be only calculated in one time-step ahead. The paper discussed the advance prediction with longer forecast periods rather than single time-step by constructing a TCN-based model. The model accuracy and efficiency were further compared with a LSTM-based model. The two models derived in this study can help people to cope with uncertainty of what will might occur in hydrological scenarios under threat of climate change.