Advance prediction of coastal groundwater levels with temporal convolutional and long short-term memory networks

Abstract

Abstract. Prediction of groundwater level is of immense importance and challenges coastal aquifer management with rapidly increasing climatic change. With the development of artificial intelligence, data-driven models have been widely adopted in hydrological process management. However, due to the limitation of network framework and construction, they are mostly adopted to produce only 1 time step in advance. Here, the temporal convolutional network (TCN) and models based on long short-term memory (LSTM) were developed to predict groundwater levels with different leading periods in a coastal aquifer. The initial data of 10 months, monitored hourly in two monitoring wells, were used for model training and testing, and the data of the following 3 months were used as prediction with 24, 72, 180, and 360 time steps (1, 3, 7, and 15 d) in advance. The historical precipitation and tidal-level data were incorporated as input data. For the one-step prediction of the two wells, the calculated R2 of the TCN-based models' values were higher and the root mean square error (RMSE) values were lower than that of the LSTM-based model in the prediction stage with shorter running times. For the advanced prediction, the model accuracy decreased with the increase in the advancing period from 1 to 3, 7, and 15 d. By comparing the simulation accuracy and efficiency, the TCN-based model slightly outperformed the LSTM-based model but was less efficient in training time. Both models showed great ability to learn complex patterns in advance using historical data with different leading periods and had been proven to be valid localized groundwater-level prediction tools in the subsurface environment.

Wavelet Gated Multiformer for Groundwater Time Series Forecasting

“…Physics-informed neural networks have also been used to simulate the physical process governing aquifers [25][26][27] . Furthermore, advances have been made in deep-learning-based methods for groundwater prediction 28,29 , genetic algorithms 30,31 , support vector machine (SVM) [32][33][34] , convolutional (CNN) and temporal convolutional network 35,36 , recurrent neural network, gated recurrent unit (GRU) and long short-term memory (LSTM) [37][38][39] , and graph neural networks based on Wavenets 40,41 to include spatiotemporal patterns for groundwater forecasting.…”

Wavelet gated multiformer for groundwater time series forecasting

“…Physics-informed neural networks have also been used to simulate the physical process governing aquifers 25 – 27 . Furthermore, advances have been made in deep-learning-based methods for groundwater prediction 28 , 29 , genetic algorithms 30 , 31 , support vector machine (SVM) 32 – 34 , convolutional (CNN) and temporal convolutional network 35 , 36 , recurrent neural network, gated recurrent unit (GRU) and long short-term memory (LSTM) 37 – 39 , and graph neural networks based on Wavenets 40 , 41 to include spatiotemporal patterns for groundwater forecasting.…”

Study on the Variation in Coastal Groundwater Levels under High-Intensity Brine Extraction Conditions

“…Groundwater extraction leads to a decline in the water level [7], which will rise and reach a new equilibrium after the extraction is stopped, while tidal forces can cause daily fluctuations in the water level. By continuously and intermittently observing the water level in coastal aquifers, the tidal effect can be observed [8]. Tidal forces are also an important mechanism for the movement of saturated and intertidal zone pore water [9].…”

“…Rainfall is also an important factor affecting groundwater dynamics in coastal areas [8]. The rising groundwater level with rainfall is a complex phenomenon, as it is influenced by many factors.…”

“…These subsidence areas have changed the original dynamic conditions of groundwater, leading to a decline in water levels. In non-mining areas, based on the continuous monitoring of several nearby wells, tides and rainfall can be used to predict groundwater levels [8]. However, research on the impact of different factors on groundwater level changes in brine mining areas has not yet been conducted.…”