Groundwater Level Prediction Research Articles

Groundwater level prediction using modified recurrent neural network combined with meta-heuristic optimization algorithm

Groundwater level prediction using modified recurrent neural network combined with meta-heuristic optimization algorithm

Application of HP-LSTM Models for Groundwater Level Prediction in Karst Regions: A Case Study in Qingzhen City

Groundwater serves as an indispensable global resource, essential for agriculture, industry, and the urban water supply. Predicting the groundwater level in karst regions presents notable challenges due to the intricate geological structures and fluctuating climatic conditions. This study examines Qingzhen City, China, introducing an innovative hybrid model, the Hodrick–Prescott (HP) filter–Long Short-Term Memory (LSTM) network (HP-LSTM), which integrates the HP filter with the LSTM network to enhance the precision of groundwater level forecasting. By attenuating short-term noise, the HP-LSTM model improves the long-term trend prediction accuracy. Findings reveal that the HP-LSTM model significantly outperformed the conventional LSTM, attaining R2 values of 0.99, 0.96, and 0.98 on the training, validation, and test datasets, respectively, in contrast to LSTM values of 0.92, 0.76, and 0.95. The HP-LSTM model achieved an RMSE of 0.0276 and a MAPE of 2.92% on the test set, significantly outperforming the LSTM model (RMSE: 0.1149; MAPE: 9.14%) in capturing long-term patterns and reducing short-term fluctuations. While the LSTM model is effective at modeling short-term dynamics, it is more prone to noise, resulting in greater prediction errors. Overall, the HP-LSTM model demonstrates superior robustness for long-term groundwater level prediction, whereas the LSTM model may be better suited for scenarios requiring rapid adaptation to short-term variations. Selecting an appropriate model tailored to specific predictive needs can thus optimize groundwater management strategies.

Prediction of Groundwater Level Based on the Integration of Electromagnetic Induction, Satellite Data, and Artificial Intelligent

Groundwater level (GWL) in dry areas is an important parameter for understanding groundwater resources and environmental sustainability. Remote sensing data combined with machine learning algorithms have become one of the important tools for groundwater level modeling. However, the effectiveness of the above-based model in the plains of the arid zone remains underexplored. Fortunately, soil salinity and soil moisture may provide an optimized solution for GWL prediction based on the application of apparent conductivity (ECa, mS/m) using electromagnetic induction (EMI). This has not been attempted in previous studies in oases in arid regions. The study proposed two strategies to predict GWL, included an ECa-based GWL model and a remote sensing-based GWL model (RS_GWL), and then compared and explored their performances and cooperation possibilities. To this end, this study first constructed the ECa prediction model and the RS_GWL with ensemble machine learning algorithms using environmental variables and field observations (474 ECa reads and 436 groundwater level observations from a mountain–oasis–desert system, respectively). Subsequently, a strategy to improve the prediction accuracy of GWL was proposed by comparing the correlation between GWL observations and the two models. The results showed that the RS_GWL prediction model explains 30% and 90% of the spatial variability in the two value domain intervals, GWL < 10 m and GWL > 10 m, respectively. The R2 of the modeling and the validation of the ECa was 79% and 73%, respectively. Careful analysis of the scatter plots between predicted ECa and GWL revealed that when ECa varies between 0–600 mS/m, 600–800 mS/m, 800–1100 mS/m, and >1100 mS/m, the fluctuation ranges of the corresponding GWL correspond to 0–31 m, 0–15 m, 0–10 m, and 0–5 m. Finally, combining the spatial variability of ECa and RS_GWL spatial distribution map, the following optimization strategies were finally established: GWL < 5 m (in natural land with ECa > 1100 mS/m), GWL < 5 m (occupied by farmland from RS_GWL) and GWL > 10 m (from RS_GWL), and 3 < GWL < 10 m (speculated). In conclusion, this study has demonstrated that the integration of EMI technology has significantly improved the precision of forecasting shallow GWL in oasis plain regions, outperforming the outcomes achieved by the use of remote sensing data alone.

An improved support vector machine model for groundwater level prediction: a case study

An improved support vector machine model for groundwater level prediction: a case study

Assessment of climate change uncertainty effects on groundwater level prediction using Bayesian analysis

Assessment of climate change uncertainty effects on groundwater level prediction using Bayesian analysis

Insight into groundwater level prediction with feature effectiveness: comparison of machine learning and numerical methods

ABSTRACT Reliable simulation of groundwater fluctuation is imperative for implementing sustainable groundwater management so that not only local people will be covered, but also environmental threats are going to be restrained in the future. This research aims to scrutinize the accuracy of numerical model (NM) and machine learning (ML) methods for groundwater level prediction (GWLP) for Yazd-Ardakan Plain from 2012 to 2019 in monthly steps. Additionally, principal component analysis (PCA) is applied to investigate the impact of each ML input feature on GWLP. The study area's aquifer data were analyzed and prepared to develop the conceptual model of MODFLOW and train ML algorithms for GWLP. Considering observation wells (OBWs), operation wells (OPWs), and their latitude and longitude as input features in convolutional neural networks (CNN), support vector machine (SVM), and decision tree (DT) algorithms, GWLP was performed. The results demonstrate that although MODFLOW considers the unique features of the aquifer, the most accurate GWLP was achieved by SVM, with root mean square errors (RMSE), correlation coefficient (), and area under the receiver operating characteristics (ROC) curve (AUC) values of 0.12, 0.90, and 0.94, respectively. Furthermore, PCA presented that the observed groundwater level (GWL) was the most effective feature with 71%.

Investigating the role of ENSO in groundwater temporal variability across Abu Dhabi Emirate, United Arab Emirates using machine learning algorithms

Accurate prediction of groundwater levels is crucial for managing groundwater resources efficiently. The complex aquifer heterogeneity and groundwater abstraction variation present challenges to have accurate groundwater level models over Abu Dhabi emirate, United Arab Emirates. In the present study, two data-driven models are employed, which are the Long Short-Term Memory (LSTM) and the Random Forest (RF) to develop a model for the prediction of monthly groundwater level in the Abu Dhabi Emirate. The incorporated data in the models are precipitation, terrestrial water storage, soil moisture, evapotranspiration, and the El Niño-Southern Oscillation (ENSO) 3.4 index. The groundwater monitoring wells data are obtained for 263 monitoring wells distributed over Abu Dhabi emirate for the period 2000-2023 in a monthly temporal scale. The models’ performance was assessed using the Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) the coefficient of determination (R2) and Percent bias (PBIAS). An optimization technique was also applied to address the impact of the lags on enhancing the groundwater level model. The LSTM model outperformed the RF model during the testing period, achieving R2 =0.79, NSE=0.70, RMSE=0.38 meters and PBIAS= 0.2% with a 3-month lag. The global sensitivity analysis was applied to understand the importance of each parameter and its influence on the models’ output. This study highlights the potential use of data-driven models for the prediction of groundwater level which could aid water managers to monitor the groundwater resources at a regional scale. The developed model can serve as an alternative approach for predicting groundwater level change over the Abu Dhabi Emirate.

Identification of potential groundwater zone for urban development

Abstract An accurate groundwater level prediction approach is needed for more efficient and ideal planning when using groundwater resources, especially during dry and low water periods. Groundwater levels are highly nonlinear and complex due to the influence of topography, meteorology, geomorphology, hydrology, geology, and human activities. A strategy and in-depth knowledge of groundwater potential availability are prerequisites for planned sustainable urban development. This study used a Geographic Information System (GIS) and Analytical Hierarchy Process (AHP). Four thematic layers were used in GIS to identify groundwater potential zones: slope gradient, rainfall, soil type, and land use/cover. Using weighted analysis in ArcGIS software, all thematic layers were combined to provide a combined groundwater potential map of the study area. Groundwater potential zones were created using ArcGIS 10.8 spatial analysis tools on an overlay of all thematic maps. Groundwater conditions were used to determine the GIS analysis criteria, and each information layer was ranked and weighted accordingly. Finally, groundwater recharge zones were selected and classified into very high, high, moderate, low, and very low based on the cumulative weighted values. The results of the study showed that around 0.2% (4.7 ha) of the area was in the deficient category, 45.8% (1,392 ha) was in the high category, 28.4% (463 ha) was in the medium category, 1.7% (52 ha) was in the low category, and 23.9% (725 ha) was in the very high category.

Groundwater level predictions in the Thames Basin, London over extended horizons using Transformers and advanced machine learning models

This study breaks new ground by using the Temporal Fusion Transformer (TFT) method for groundwater level prediction, addressing the complex dynamics of the Thames Basin aquifer in England. Our research combines extensive hydrological data collected from the Thames Basin with advanced machine learning, where a complex network of rivers and streams substantially affects groundwater dynamics. Unlike previous studies, this research focuses on long-term forecasting with deep learning, offering, for the first time, a 60-day prediction horizon based on daily data. To rigorously examine the model performance and robustness on new, unseen data, we applied the walk-forward validation method and other matrices such as RMSE and R2 coupled with the Holdout technique. The models used were Long Short-Term Memory (LSTM), Attention-based LSTM, LSTM with Bayesian optimisation, Attention-based LSTM with Bayesian optimisation and TFT. They were used on the basin's Chalk, Jurassic Limestone, and Lower greensand aquifers. Whilst both LSTM models were optimised using the Bayesian technique, TFT was applied for its inherent capability in complex time series. Our methodology processed historical groundwater and rainfall data from 2001 to 2023, accounting for the potential lag in aquifer response to the proximity of the river system. The dataset served as training, validation, and holdout for each model, focusing on capturing the dynamic temporal fluctuation. The results clearly showed the superiority of the TFT model in all aquifer types compared to other models across all horizons. The Limestone had the greatest result in the 7-day projections, with an RMSE of 0.02 and R2 of 0.98; Whilst the Chalk and Lower greensand, had RMSEs of 0.03 with R2 values of 0.75 and 0.95, respectively. The Limestone aquifer performed best for the 30-day horizon again (RMSE = 0.06, R2 = 0.85), with the Chalk and Lower greensand aquifer yielding RMSE of 0.04 and 0.12 and R2 values of 0.64 and 0.74, respectively. In the 60 days predictions, the best results were observed in the limestone aquifer with RMSE of 0.09 and R2 of 0.65 in holdout validation. However, in chalk and lower greensand aquifers, the TFT showed RMSEs of 0.05 and 0.15 and R2s of 0.45 and 0.58, respectively. Traditional LSTM models demonstrated limited predictive power compared to the main model TFT, while the attention mechanism slightly improved the accuracy. This study not only sets a new benchmark in hydrological modelling accuracy but also highlights the potential of advanced machine learning in managing complex aquifers and predicting the water table.

The Landsat Data-Based Monitoring of Groundwater Depth and Its Influencing Factors in the Oasis Area of the Weigan River

Using the Weigan River oasis as the research area and based on Landsat and measured groundwater depth data, the temperature vegetation drought index (TVDI) was calculated, and the groundwater depth that was measured in the field was used to establish a groundwater level prediction model (R2 = 0.644). Groundwater distribution in the Weigan River oasis was monitored from 2007 to 2020, and the model was verified using data from September 2013 and June 2015. The results indicate the following: (1) From 2000 to 2015, the groundwater depth of the Weigan River oasis was increased in a fluctuating manner and increased from 2.80 m to 5.79 m, and these values fluctuated sharply with a range of change of 106.79%. (2) The correlation coefficient R2 between the measured and predicted water levels in the two periods is 0.67 and 0.61, and the verification effect is good. (3) In the period from 2007 to 2020, the groundwater depth in the irrigated area exhibited a declining trend, where it decreased from the northwest and northeast to the southwest and southeast. (4) In irrigated areas, the GDP, population, and grain yield exerted a greater impact on groundwater depth. However, precipitation and evaporation were not significantly correlated with groundwater depth.

A Comparative Analysis of ANN, LSTM and Hybrid PSO-LSTM Algorithms for Groundwater Level Prediction

A Comparative Analysis of ANN, LSTM and Hybrid PSO-LSTM Algorithms for Groundwater Level Prediction

Analysis of Ground Water Level and Ground Water Pollution Using Machine Learning Algorithms

Groundwater plays a crucial role in sustaining human life, agriculture, and ecosystems. However, due to increasing demand, pollution, and climatic variations, monitoring and analyzing groundwater levels and quality has become imperative. In this paper, we explore the use of machine learning algorithms to analyze groundwater levels and groundwater pollution, aiming to develop predictive models for sustainable groundwater management. The study investigates the application of supervised and unsupervised learning techniques to predict groundwater levels, identify pollution sources, and assess contamination risks. By integrating environmental data, including rainfall patterns, land use, and pollution levels, the paper demonstrates how machine learning can provide more accurate, scalable, and real-time analysis for groundwater management.

A groundwater level spatiotemporal prediction model based on graph convolutional networks with a long short-term memory

ABSTRACT The performance of regional groundwater level (GWL) prediction model hinges on understanding intricate spatiotemporal correlations among monitoring wells. In this study, a graph convolutional network (GCN) with a long short-term memory (LSTM) (GCN–LSTM) model is introduced for GWL prediction utilizing data from 16 wells located in the northeastern Xiangtan City, China. This model is designed to account for both the hybrid temporal dependencies and spatial autocorrelations among wells. It consists of two parts: the spatial part employs GCNs to extract spatial characteristics from a spatial self-similarity weight matrix and an attribute self-similarity weight matrix among wells; the temporal part utilizes a LSTM module to capture the temporal patterns of GWL sequences, along with monthly precipitation and temperature data. This model dynamically predicts changes in groundwater levels, achieving higher accuracy on average compared to single-well predictions using LSTM. By incorporating both temporal dependencies and spatial autocorrelations, the GCN–LSTM model demonstrated an average improvement in goodness-of-fit of approximately 11.21% over the LSTM-based model for individual wells. Its application holds significant reference value for the sustainable utilization and development of groundwater resources in Xiangtan City.

Advanced machine vision techniques for groundwater level prediction modeling geospatial and statistical research

This study utilizes three models, namely Weight of Evidence (WOE), Frequency Ratio (FR), and Index of Vulnerability (IV), to identify groundwater potential zones (GWPZ) in southern Khyber Pakhtunkhwa, Nowshera District, Pakistan. We incorporated a total of twelve variables, encompassing elevation, slope, distance to the rivers, rainfall, curvature, drainage density, land use/land cover, topographic wetness index, height above the nearest drainage, NDVI, distance to the roads, and soil type, utilizing ArcGIS 10.8. The AUROC (Area Under the Receiver Operating Characteristic) assessed the dependability of the models. GWPZ was categorized into five classifications: very low, low, moderate, high, and very high. The WOE model produced distributions of 10.14 % (262.09 km2), 19.58 % (506.00 km2), 26.75 % (691.10 km2), 27.10 % (700.18 km2), and 16.40 % (423.75 km2) respectively. The FR yielded 20.93 % (538.90 km2), 32.38 % (833.53 km2), 18.92 % (487.14 km2), 13.13 % (337.94 km2), and 14.61 % (376.07 km2). The IV model resulted in 14.41 % (372.46 km2), 17.17 % (443.67 km2), 29.01 % (749.52 km2), 25.85 % (667.97 km2), and 13.53 % (349.50 km2). The AUC-ROC for WOE, FR, and IV were 58.06%, 87.53%, and 84.98%, respectively. All models accurately defined the GWPZ, with the FR approach demonstrating notable potential. These findings provide vital information for managing groundwater resources and the design of metropolitan areas. Our developed methodology can be used in places with comparable characteristics. It is a valuable tool for policymakers interested in sustainable groundwater management.

Applying Transfer Learning to Improve the Performance of Deep Learning–based Groundwater Level Prediction Model with Insufficient Training Data

Applying Transfer Learning to Improve the Performance of Deep Learning–based Groundwater Level Prediction Model with Insufficient Training Data

A robust multi-model framework for groundwater level prediction: The BFSA-MVMD-GRU-RVM model

Groundwater level prediction is critical for environmental protection and agricultural planning. Accurate predictions help manage risks associated with excessive groundwater extraction and land subsidence. This study introduces a novel model combining multivariate variational mode decomposition (MVMD), gated recurrent unit (GRU), and relevance vector machine (RVM), along with the Boruta feature selection algorithm (BFSA), for precise groundwater level forecasting. The model operates in several stages. First, BFSA selects the most informative features as input data. Next, the MVMD method decomposes the time series of these features. The GRU model then extracts crucial information from these decompositions. Finally, the extracted data is fed into the RVM model to predict groundwater levels one month ahead in Iran's Bastam Plain. To assess the model's accuracy, multiple error indices were employed. The MVMD-GRU-RVM model outperformed other models, improving the testing Nash–Sutcliffe Efficiency and mean absolute error by 24–31 % and 6–61 %, respectively. Additionally, it enhanced R2 values of the MVMD-CNN, MVMD-RNN, MVMD-MLP, and MVMD-RBFNN models by 1.0–3.33 %. These results demonstrate that the MVMD-GRU-RVM model significantly improves groundwater level prediction accuracy. The key points of the paper are the successful effectiveness of MVMD in processing non-stationary time series and improving the predictive performance of the models, as well as the high ability of the GRU model in data feature extraction. The study also shows that the novel model can provide outputs with lower uncertainty.

Research on a Non-Stationary Groundwater Level Prediction Model Based on VMD-iTransformer and Its Application in Sustainable Water Resource Management of Ecological Reserves

The precise forecasting of groundwater levels significantly influences plant growth and the sustainable management of ecosystems. Nonetheless, the non-stationary characteristics of groundwater level data often hinder the current deep learning algorithms from precisely capturing variations in groundwater levels. We used Variational Mode Decomposition (VMD) and an enhanced Transformer model to address this issue. Our objective was to develop a deep learning model called VMD-iTransformer, which aims to forecast variations in the groundwater level. This research used nine groundwater level monitoring stations located in Hangjinqi Ecological Reserve in Kubuqi Desert, China, as case studies to forecast the groundwater level over four months. To enhance the predictive performance of VMD-iTransformer, we introduced a novel approach to model the fluctuations in groundwater levels in the Kubuqi Desert region. This technique aims to achieve precise predictions of the non-stationary groundwater level conditions. Compared with the classic Transformer model, our deep learning model more effectively captured the non-stationarity of groundwater level variations and enhanced the prediction accuracy by 70% in the test set. The novelty of this deep learning model lies in its initial decomposition of multimodal signals using an adaptive approach, followed by the reconfiguration of the conventional Transformer model’s structure (via self-attention and inversion of a feed-forward neural network (FNN)) to effectively address the challenge of multivariate time prediction. Through the evaluation of the prediction results, we determined that the method had a mean absolute error (MAE) of 0.0251, a root mean square error (RMSE) of 0.0262, a mean absolute percentage error (MAPE) of 1.2811%, and a coefficient of determination (R2) of 0.9287. This study validated VMD and the iTransformer deep learning model, offering a novel modeling approach for precisely predicting fluctuations in groundwater levels in a non-stationary context, thereby aiding sustainable water resource management in ecological reserves. The VMD-iTransformer model enhances projections of the water level, facilitating the reasonable distribution of water resources and the long-term preservation of ecosystems, providing technical assistance for ecosystems’ vitality and sustainable regional development.

Spatial-temporal graph neural networks for groundwater data.

This paper introduces a novel application of spatial-temporal graph neural networks (ST-GNNs) to predict groundwater levels. Groundwater level prediction is inherently complex, influenced by various hydrological, meteorological, and anthropogenic factors. Traditional prediction models often struggle with the nonlinearity and non-stationary characteristics of groundwater data. Our study leverages the capabilities of ST-GNNs to address these challenges in the Overbetuwe area, Netherlands. We utilize a comprehensive dataset encompassing 395 groundwater level time series and auxiliary data such as precipitation, evaporation, river stages, and pumping well data. The graph-based framework of our ST-GNN model facilitates the integration of spatial interconnectivity and temporal dynamics, capturing the complex interactions within the groundwater system. Our modified Multivariate Time Graph Neural Network model shows significant improvements over traditional methods, particularly in handling missing data and forecasting future groundwater levels with minimal bias. The model's performance is rigorously evaluated when trained and applied with both synthetic and measured data, demonstrating superior accuracy and robustness in comparison to traditional numerical models in long-term forecasting. The study's findings highlight the potential of ST-GNNs in environmental modeling, offering a significant step forward in predictive modeling of groundwater levels.

Utility of Certain AI Models in Climate-Induced Disasters

To address the current challenge of climate change at the local and global levels, this article discusses a few important water resources engineering topics, such as estimating the energy dissipation of flowing waters over hilly areas through the provision of regulated stepped channels, predicting the removal of silt deposition in the irrigation canal, and predicting groundwater level. Artificial intelligence (AI) in water resource engineering is now one of the most active study topics. As a result, multiple AI tools such as Random Forest (RF), Random Tree (RT), M5P (M5 model trees), M5Rules, Feed-Forward Neural Networks (FFNNs), Gradient Boosting Machine (GBM), Adaptive Boosting (AdaBoost), and Support Vector Machines kernel-based model (SVM-Pearson VII Universal Kernel, Radial Basis Function) are tested in the present study using various combinations of datasets. However, in various circumstances, including predicting energy dissipation of stepped channels and silt deposition in rivers, AI techniques outperformed the traditional approach in the literature. Out of all the models, the GBM model performed better than other AI tools in both the field of energy dissipation of stepped channels with a coefficient of determination (R2) of 0.998, root mean square error (RMSE) of 0.00182, and mean absolute error (MAE) of 0.0016 and sediment trapping efficiency of vortex tube ejector with an R2 of 0.997, RMSE of 0.769, and MAE of 0.531 during testing. On the other hand, the AI technique could not adequately understand the diversity in groundwater level datasets using field data from various stations. According to the current study, the AI tool works well in some fields of water resource engineering, but it has difficulty in other domains in capturing the diversity of datasets.

Research on Groundwater Level Prediction Method in Karst Areas Based on Improved Attention Mechanism Fusion Time Convolutional Network

Research on Groundwater Level Prediction Method in Karst Areas Based on Improved Attention Mechanism Fusion Time Convolutional Network