Groundwater Level Prediction Research Articles

A secondary modal decomposition ensemble deep learning model for groundwater level prediction using multi-data

Groundwater level (GWL) prediction is important for ecological protection and resource utilization; it helps in formulating policies for artificial groundwater recharge, modifying the number of extraction wells, etc., and can support sustainable human development as well as inform water resource management decisions. However, climate change, anthropogenic impacts, and the complex coupling between surface water and groundwater increase the difficulty of predicting groundwater levels. The model proposed in this paper combines external data as well as multiple models. The method leverages long and short-term memory (LSTM) and convolutional neural network (CNN) models, combined with secondary modal decomposition and slime mould algorithm (SMA), together with an adaptive weight module (AWM). The study applies this method to predict GWL for three different hydrological conditions in China, specifically for the Jinan Baotu Spring, Heihu Spring, and Zhongtianshe watershed of Taihu Lake. A comparison of metrics such as mean absolute error and Nash efficiency coefficient for single and hybrid models shows that the model in this paper is more advantageous than the single model and other hybrid models. The interpretability of the model is enhanced by SHAP values that demonstrate the degree of contribution of the input variables. This paper uses SHAP analyses to identify the key drivers affecting groundwater levels. These factors must be detected in order to develop groundwater resource protection measures.

Potential of machine learning algorithms in groundwater level prediction using temporal gravity data

Prediction of groundwater levels with precision and dependability is crucial for effective water resource development and management. This study was carried out to establish the relationship between groundwater level (GWL) and temporal gravity variation through five nonlinear machine learning (ML) models: Polynomial Regression (PR), Random Forest, XG- Boost, K-Nearest Neighbourhood (KNN), and support vector machine - radial basic function (SVM-RBF). These models were employed to predict GWL at a specific well located at the Hydrology Department, IIT Roorkee, India. The models were trained and tested using a dataset that includes gravity, time, and relevant hydro-meteorological factors like precipitation (P), temperature (T), evaporation (E), relative humidity (RH), and wind speed (WS). The study is organized into three groups of model runs: the first group considers gravity as the sole input parameter, the second group includes both gravity and time, and the third incorporates all hydro-meteorological parameters. Comparative evaluation of the models was done using four different evaluation metrics, i.e., coefficient of determination (R2), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Nash-Sutcliffe Efficiency (NSE). Results highlight XG-Boost as the most efficient model for predicting groundwater levels, demonstrating exceptional performance, particularly when gravity and time are the input parameters, yielding a minimum MAE of 0.11 and a maximum R2 of 0.97.

Shannon entropy of performance metrics to choose the best novel hybrid algorithm to predict groundwater level (case study: Tabriz plain, Iran).

Predicting groundwater level (GWL) fluctuations, which act as a reserve water reservoir, particularly in arid and semi-arid climates, is vital in water resources management and planning. Within the scope of current research, a novel hybrid algorithm is proposed for estimating GWL values in the Tabriz plain of Iran by combining the artificial neural network (ANN) algorithm with newly developed nature-inspired Coot and Honey Badger metaheuristic optimization algorithms. Various combinations of meteorological data such as temperature, evaporation, and precipitation, previous GWL values, and the month and year values of the data were used to evaluate the algorithm's success. Furthermore, the Shannon entropy of model performance was assessed according to 44 different statistical indicators, classified into two classes: accuracy and error. Hence, based on the high value of Shannon entropy, the best statistical indicator was selected. The results of the best model and the best scenario were analyzed. Results indicated that value of Shannon entropy is higher for the accuracy class than error class. Also, for accuracy and error class, respectively, Akaike information criterion (AIC) and residual sum of squares (RSS) indexes with the highest entropy value which is equal to 12.72 and 7.3 are the best indicators of both classes, and Legate-McCabe efficiency (LME) and normalized root mean square error-mean (NRMSE-Mean) indexes with the lowest entropy value which is equal to 3.7 and - 8.3 are the worst indicators of both classes. According to the evaluation best indicator results in the testing phase, the AIC indicator value for HBA-ANN, COOT-ANN, and the standalone ANN models is equal to - 344, - 332.8, and - 175.8, respectively. Furthermore, it was revealed that the proposed metaheuristic algorithms significantly improve the performance of the standalone ANN model and offer satisfactory GWL prediction results. Finally, it was concluded that the Honey Badger optimization algorithm showed superior results than the Coot optimization algorithm in GWL prediction.

수치해석 접근법에 따른 지하수 공간분포 예측

This study applied the MODFLOW model using finite difference method and the NNRK model combining neural network and residual kriging for spatial groundwater level prediction in Jeju Island, South Korea. For the MODFLOW model, the differences between observed and predicted groundwater levels were 0.014-4.327 m and the relative errors were 0.50-50.82 %. For the NNRK model, the differences between observed and predicted groundwater levels were 0.022-6.185 m and the relative errors were 0.66-49.35 %. Based on MSRE, IDW model, which is a non-spatial statistical model, showed better spatial prediction results than SK and OK models, whereas RK and NNRK models outperformed the IDW model. The MODFLOW model showed relatively better results than the NNRK model in dense areas considering recharge and geological structure although the MODFLOW and NNRK models produced similar results. Furthermore, the MODFLOW model was found to effectively reflect groundwater flow by strata and temporal groundwater head fluctuations due to pumping compared to the NNRK model.

Deep learning models for groundwater level prediction based on delay penalty

Abstract In irrigation agriculture, predicting groundwater level (GWL) using deep learning models can help decision-makers coordinate surface water and groundwater usage, thus aiding in the sustainable development and utilization of groundwater. However, when making a long sequence prediction, prediction sequences often have severe delays affecting the availability of prediction results. In this paper, a new loss function is proposed to minimize the lag and oversmoothing on the prediction of GWLs. GWL, meteorology, and pumping data are collected via an irrigation Internet of Things system in Hutubi County, Xinjiang. Through Pearson's correlation analysis, historical potential evapotranspiration (ET0), groundwater extraction, and GWL were chosen to predict GWLs. Datasets were constructed through the proposed spatiotemporal data fusion method; then, the best model from the six deep learning models was selected by comparing the prediction capability of the datasets. Finally, the mean-squared error (MSE) loss function is replaced by the proposed loss function. Compared to the mean absolute error, MSE, and predicted sequence graphs, the new loss function significantly depresses the time delay with similar prediction accuracy.

Groundwater level prediction using an improved SVR model integrated with hybrid particle swarm optimization and firefly algorithm

The demand for water resources has increased due to rapid increase of metropolitan areas brought on by growth in population and industrialisation. In addition, the groundwater recharge is being afftected by shifting land use pattern caused by urban development. Using precise and trustworthy estimates of groundwater level is vital for the sustainable groundwater resources management in the face of changing climatic circumstances. In this context, machine learning (ML) methods offer a new and promising approach for accurately forecasting long-term changes in the groundwater level (GWL) without computational effort of developing a comprehensive flow model. In order to simulate GWL, five data-driven (DD) models, including the hybridization of support vector regression (SVR) with two optimisation algorithms i.e., firefly algorithm and particle swarm optimisation (FFAPSO), SVR-FFA, SVR-PSO, SVR and Multilayer perception (MLP), have been examined in the present study. Spatial clustering was utilised to choose four observation wells within Cuttack district in order to study and assess the water levels. Six scenarios were created by incorporating numerous variables, such as GWL in the previous months, evapotranspiration, temperature, precipitation, and river discharge. The goal was to identify the variables that were most efficient in predicting GWL. The SVR-FFAPSO model performs best in GWL forecasting for Khuntuni station, according to the quantitative analysis with correlation coefficient (R) = 0.9978, Nash–Sutcliffe efficiency (NSE) = 0.9933, mean absolute error (MAE) = 0.00025 (m), root mean squared error (RMSE) = 0.00775 (m) during the training phase. It is advised that groundwater monitoring network and data collecting system are strengthen in India for ensuring effective modelling of long-term management of groundwater resources.

Comparison of Multiple Machine Learning Methods for Correcting Groundwater Levels Predicted by Physics-Based Models

Accurate groundwater level (GWL) prediction is crucial in groundwater resource management. Currently, it relies mainly on physics-based models for prediction and quantitative analysis. However, physics-based models used for prediction often have errors in structure, parameters, and data, resulting in inaccurate GWL predictions. In this study, machine learning algorithms were used to correct the prediction errors of physics-based models. First, a MODFLOW groundwater flow model was created for the Hutuo River alluvial fan in the North China Plain. Then, using the observed GWLs from 10 monitoring wells located in the upper, middle, and lower parts of the alluvial fan as the test standard, three algorithms—random forest (RF), extreme gradient boosting (XGBoost), and long short-term memory (LSTM)—were compared for their abilities to correct MODFLOW’s predicted GWLs of these 10 wells under two sets of feature variables. The results show that the RF and XGBoost algorithms are not suitable for correcting predicted GWLs that exhibit continuous rising or falling trends, but the LSTM algorithm has the ability to correct them. During the prediction period, the LSTM2 model, which incorporates additional source–sink feature variables based on MODFLOW’s predicted GWLs, can improve the Pearson correlation coefficient (PR) for 80% of wells, with a maximum increase of 1.26 and a minimum increase of 0.02, and can reduce the root mean square error (RMSE) for 100% of the wells with a maximum decrease of 1.59 m and a minimum decrease of 0.17 m. And it also outperforms the MODFLOW model in capturing the long-term trends and short-term seasonal fluctuations of GWLs. However, the correction effect of the LSTM1 model (using only MODFLOW’s predicted GWLs as a feature variable) is inferior to that of the LSTM2 model, indicating that multiple feature variables are superior to a single feature variable. Temporally and spatially, the greater the prediction error of the MODFLOW model, the larger the correction magnitude of the LSTM2 model.

Evaluating the Impact of Pumping on Groundwater Level Prediction in the Chuoshui River Alluvial Fan Using Artificial Intelligence Techniques

Evaluating the Impact of Pumping on Groundwater Level Prediction in the Chuoshui River Alluvial Fan Using Artificial Intelligence Techniques

Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network

Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network

Research on Groundwater Level Prediction Model of Leizhuang Well in Hubei Province Based on BP Neural Network

Research on Groundwater Level Prediction Model of Leizhuang Well in Hubei Province Based on BP Neural Network

An Overview of Deep Learning Applications in Groundwater Level Modeling: Bridging the Gap between Academic Research and Industry Applications

As a critical component of sustainable water management, groundwater level prediction plays a vital role in mitigating droughts and ensuring adequate water supply. For decades, groundwater level dynamics have been primarily studied through physics‐based models, solving partial differential equations. However, interest has increased over the past few years in using Machine Learning (ML) approaches, like Deep Learning (DL) techniques, to study groundwater fluctuation dynamics more efficiently. DL models utilize complex algorithms to identify patterns that may be difficult to observe with traditional physics‐based models, specifically where the underlying physics is complex or poorly understood or where the available physical model is too simple. The article provides an overview of the literature published since 2001, encompassing 91 works that employed ML models to investigate groundwater‐related issues. Within this body of literature, 47 articles employed ML for groundwater level (GWL) modeling. Later, this article delves specifically into the latest advancements in DL for modeling GWL, including recurrent neural network (RNN), long short‐term memory (LSTM), and gated recurrent unit (GRU), and discusses their technical promising performance and advantages. We found that the most used time scale was monthly, which appeared in 18 articles, followed by the daily time scale, which appeared in 13 articles. The authors of the articles used normalization as a feature scaling method in 18 articles, while standardization was used in 3 articles. Python was the predominant programming language used in 18 studies for developing machine learning models, followed by MATLAB, which was used in 5 articles. Most authors divided their data sets into 60–90% for training and 10–40% for testing. Most studies have focused on pure academic research rather than practical industrial applications. Therefore, this article identifies shortcomings in recent literature on DL for GWL studies and suggests addressing these issues to improve practical application in real‐world settings.

A simplified calculation method for high-steep soil slope stability due to groundwater rise from irrigation

The groundwater is the critical factor impacting the stability of high-steep soil slopes (HsSS) on the loess tableland. In view of the shortcomings of the current commonly used calculation methods for HsSS, based on the Rankine earth pressure, the equilibrium conditions, and the strength failure criterion, a simplified calculation method for HsSS stability is proposed considering the typical characteristic that the failure surface of the high-steep slope is a double-segment line, and the critical groundwater level of the slope of the tableland edge was determined based on the HsSS stability model. The results are consistent with slope and modified the shortcomings of the existing model, such as the relatively concentrated and smaller of the stability coefficient. The critical groundwater level prediction model was applied to the Heifangtai tableland to verify the feasibility of the prediction model and point out the three high-risk points along the Heifangtai tableland.

Towards Groundwater-Level Prediction Using Prophet Forecasting Method by Exploiting a High-Resolution Hydrogeological Monitoring System

Forecasting of water availability has become of increasing interest in recent decades, especially due to growing human pressure and climate change, affecting groundwater resources towards a perceivable depletion. Numerous research papers developed at various spatial scales successfully investigated daily or seasonal groundwater level prediction starting from measured meteorological data (i.e., precipitation and temperature) and observed groundwater levels, by exploiting data-driven approaches. Barely a few research combine the meteorological variables and groundwater level data with unsaturated zone monitored variables (i.e., soil water content, soil temperature, and bulk electric conductivity), and—in most of these—the vadose zone is monitored only at a single depth. Our approach exploits a high spatial-temporal resolution hydrogeological monitoring system developed in the Conero Mt. Regional Park (central Italy) to predict groundwater level trends of a shallow aquifer exploited for drinking purposes. The field equipment consists of a thermo-pluviometric station, three volumetric water content, electric conductivity, and soil temperature probes in the vadose zone at 0.6 m, 0.9 m, and 1.7 m, respectively, and a piezometer instrumented with a permanent water-level probe. The monitored period started in January 2022, and the variables were recorded every fifteen minutes for more than one hydrologic year, except the groundwater level which was recorded on a daily scale. The developed model consists of three “virtual boxes” (i.e., atmosphere, unsaturated zone, and saturated zone) for which the hydrological variables characterizing each box were integrated into a time series forecasting model based on Prophet developed in the Python environment. Each measured parameter was tested for its influence on groundwater level prediction. The model was fine-tuned to an acceptable prediction (roughly 20% ahead of the monitored period). The quantitative analysis reveals that optimal results are achieved by expoiting the hydrological variables collected in the vadose zone at a depth of 1.7 m below ground level, with a Mean Absolute Error (MAE) of 0.189, a Mean Absolute Percentage Error (MAPE) of 0.062, a Root Mean Square Error (RMSE) of 0.244, and a Correlation coefficient of 0.923. This study stresses the importance of calibrating groundwater level prediction methods by exploring the hydrologic variables of the vadose zone in conjunction with those of the saturated zone and meteorological data, thus emphasizing the role of hydrologic time series forecasting as a challenging but vital aspect of optimizing groundwater management.

Predicting Groundwater Level using Temporal Attention Enhanced Graph Neural Network

A revolutionary approach for groundwater management is essential. To predicting the water levels using for integrating IoT sensors, cloud computing, and advanced data analysis methods. IoT sensors are employed for real-time measurement of groundwater levels, creating a robust dataset. The paper focuses on predicting future groundwater levels, a crucial aspect of sustainable resource management. To enhance predictive accuracy, a preprocessing algorithm, such as Min-Max normalization, is introduced to clean and normalize the collected data, ensuring its reliability. Additionally, a feature extraction algorithm, such as Principal Component Analysis (PCA), is implemented to identify relevant patterns and trends within the dataset, enhancing the efficiency of subsequent analysis. A novel classification algorithm, Spatial-Temporal Graph Convolutional Network, is introduced, enabling the identification of potential groundwater recharge areas. This classification algorithm leverages historical data and extracted features to categorize regions based on their suitability for groundwater renewal. Finally, this research uses a Temporal attention-enhanced graph Neural Network machine learning algorithm to predict groundwater levels in the next few years. This algorithm utilizes the preprocessed data and extracted features, identifying intricate patterns and trends in historical data to generate precise predictions for groundwater levels in the upcoming years.

A New Method for Estimating Groundwater Changes Based on Optimized Deep Learning Models—A Case Study of Baiquan Spring Domain in China

Estimating groundwater level (GWL) changes is crucial for the sustainable management of water resources in the face of urbanization and population growth. Existing prediction methods for GWL variations have limitations due to their inability to account for the diverse and irregular patterns of change. This paper introduces an innovative approach to GWL prediction that leverages multisource data and offers a comprehensive analysis of influencing factors. Our methodology goes beyond conventional approaches by incorporating historical GWL data, examining the impacts of precipitation and extraction, as well as considering policy-driven influences, especially in nations like China. The main contribution of this study is the development of a novel hierarchical framework (HGP) for GWL prediction, which progressively integrates correlations among different hierarchical information sources. In our experimental analysis, we make a significant discovery: extraction has a more substantial impact on GWL changes compared to precipitation. Building on this insight, our HGP model demonstrates superior predictive performance when evaluated on real-world datasets. The results show that HGP can increase NSE and R2 scores by 2.8% during the test period compared to the current more accurate deep learning method: ANFIS. This innovative model not only enhances GWL prediction accuracy but also provides valuable insight for effective water resource management. By incorporating multisource data and a novel hierarchical framework, our approach advances the state of the art in GWL prediction, contributing to more sustainable and informed decision making in the context of groundwater resource management.

Enhancing groundwater level prediction accuracy at a daily scale through combined machine learning and physics-based modeling

Study regionYongding River alluvial proluvial fan, a part of North China Plain with intense groundwater withdrawals. Study focusThe objective of this study is to enhance the accuracy of groundwater level (GWL) prediction at a daily scale by combining short-term memory (LSTM) and physics-based (PB) models. Two types of LSTM models were developed: LSTM-H-ORI, which predicts GWL, and LSTM-dH-ORI, which predicts simulated errors of the PB model. These models were subsequently refined into LSTM-H-IMP and LSTM-dH-IMP by incorporating the outputs from the PB model. To investigate the influence of groundwater flow processes, LSTM-H-IMP was further enhanced by considering the time lag properties of precipitation, referred to as LSTM-H-IMP-LAG. New hydrological insights for the regionSignificant improvements were found for LSTM-H-IMP when the performance of LSTM-H-ORI was poor (Nash–Sutcliffe Efficiency Coefficient, NSE<0) or the performance of PB model was not bad (NSE≥0). And the prediction accuracy was improved for over 67% of wells in this case. When the performance of PB model was medium and poor (NSE≤0.6), the improvement of LSTM-dH-IMP was more effective, leading to a prediction accuracy enhancement for over 77% of wells. Additionally, LSTM-H-IMP-LAG exhibited further improvement, with an average NSE increase of 0.1. This study provides scientific methods for accurate prediction of GWL at a daily time scale and the combined application of LSTM and PB models.

Correction to: Groundwater-level prediction in Visakhapatnam district, Andhra Pradesh, India, using Bayesian Neural Networks

Correction to: Groundwater-level prediction in Visakhapatnam district, Andhra Pradesh, India, using Bayesian Neural Networks

A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction

Groundwater level (GLW) prediction is essential for monitoring water resources. Our study introduces a novel model called convolutional neural network (CNN)–long short-term memory neural network (LSTM)–Multiple linear regression (MLR) for groundwater level prediction. We combine two deep learning models with the MLR model to predict GWL and overcome the limitations of the MLR model. The current paper has several innovations. Our study develops an advanced hybrid model for predicting groundwater levels (GWLs). The study also presents a novel feature selection method for selecting optimal input scenarios. Finally, an advanced method is developed to examine the impact of inputs and model parameters on output uncertainty. The current paper introduces the gannet optimization algorithm (GOA) for choosing the optimal input scenario. A CNN-LSTM-MLR model (CLM), CNN, LSTM, MLR model, CNN-MLR model (CNM), LSTM-MLR model (LSM), and CNN-LSTM model (CNL) were built to predict one-month-ahead GWLs using climate data and lagged GWL data. Output uncertainty was also decomposed into parameter uncertainty (PU) and input uncertainty (IU) using the analysis of variance (ANOVA) method. Based on our findings, the CLM model can successfully predict GWLs, reduce the uncertainty of CNN, LSTM, and MLR models, and extract spatial and temporal features. Based on the study’s findings, the combination of linear models and deep learning models can improve the performance of linear models in predicting outcomes. The GOA method can also contribute to feature selection and input selection. The study findings indicated that the CLM model improved the training Nash–Sutcliffe efficiency coefficient (NSE) of the CNL, LSM, CNM, LSTM, CNN, and MLR models by 6.12%, 9.12%, 12%, 18%, 22%, and 30%, respectively. The width intervals (WIs) of the CLM, CNL, LSM, and CNM models were 0.03, 0.04, 0.07, and, 0.12, respectively, based on IU. The WIs of the CLM, CNL, LSM, and CNM models were 0.05, 0.06, 0.09, and 0.14, respectively, based on PU. Our study proposes the CLM model as a reliable model for predicting GWLs in different basins.

Groundwater level forecasting in a data-scarce region through remote sensing data downscaling, hydrological modeling, and machine learning: A case study from Morocco

Study regionThe upstream part of the Essaouira basin, a data-scare region in Morocco, Northwestern Africa. Study focusThe scarcity of hydro-climate data is a significant challenge found in several regions worldwide, where qualitative and quantitative water resource information remains limited. Estimating and predicting groundwater levels (GWL) in such areas is a significant challenge in producing knowledge for effective water resource management. To address this issue, the present study aimed to use the Soil and Water Assessment Tool (SWAT) model in conjunction with downscaled total water storage (TWS) data (9 km) obtained from Gravity Recovery And Climate Experiment (GRACE) and machine learning techniques, specifically random forest (RF) and support vector machine (SVM), to estimate and predict the variation in GWL. New hydrological insights for the regionThis study constitutes a first of its kind in the study area; the SWAT model was set up for 10 years, with a warm-up period from 2000 to 2001, calibration from 2002 to 2007, and validation from 2008 to 2010. The statistical indices (Coefficient of Determination (R²) ≥ 0.73, R² ≥ 0.78, Nash–Sutcliffe model efficiency coefficient (NSE) ≥ 0.67, NSE ≥ 0.80 respectively for calibration and validation) highlight a significant correlation, implying the model's capability to faithfully reproduce the streamflow. The downscaled TWS demonstrates an impressive ability to identify and monitor fluctuations in GWL. Using machine learning algorithms (RF and SVR), the prediction of GWL yielded satisfactory results, NSE = 0.78 and root mean square error (RMSE) = 0.33, NSE = 0.51 and RMSE = 0.49 for the RF and SVR, respectively. Despite some limitations, our approach provided promising results in GWL prediction, with the possibility of expanding to other data-scarce regions.

Prediction of groundwater level under the influence of groundwater exploitation using a data-driven method with the combination of time series analysis and long short-term memory: a case study of a coastal aquifer in Rizhao City, Northern China

The excessive exploitation of groundwater not only destroys the dynamic balance between coastal aquifer and seawater but also causes a series of geological and environmental problems. Groundwater level prediction provides an efficient way to solve these intractable ecological problems. Although several hydrological numerical models have been employed to conduct prediction, no study has accurately predicted the groundwater level change under the consideration of groundwater exploitation, especially in coastal aquifers. This is due to the characteristics of spatially and temporally complex hydrological processes. This study proposes a novel data-driven method based on the combination of time series analysis and a machine learning method for accurately predicting the variation of groundwater level in a coastal aquifer under the influence of groundwater exploitation. The partial autocorrelation function and continuous wavelet coherence were used to analyze the monitoring data of groundwater level at three wells, which indicated that the historical monitored data and the dataset of precipitation could be considered as the input variables to construct the hydrological model. Then, three models based on the different inputs were constructed, namely, the LSTM, PACF-LSTM, and PACF-WC-LSTM models. The performances of the three models were compared by the calculation of four error metrics. The results showed that the performance of the PACF-LSTM and PACF-WC-LSTM models was better than that of the LSTM model and that the PACF-WC-LSTM model achieved the best prediction performance. Accurately predicting the variation of groundwater level provides the basis for managing groundwater resources and preserving the ecological environment.