Monthly Groundwater Level Research Articles

Correction: Prediction of monthly groundwater level using a new hybrid intelligent approach in the Tabriz plain, Iran

Correction: Prediction of monthly groundwater level using a new hybrid intelligent approach in the Tabriz plain, Iran

Prediction of monthly groundwater level using a new hybrid intelligent approach in the Tabriz plain, Iran

Prediction of monthly groundwater level using a new hybrid intelligent approach in the Tabriz plain, Iran

Hybrid machine learning models for groundwater level prediction in a snow‐dominated region: An evaluation of EEMD, VMD and EWT decomposition techniques

Hybrid machine learning models for groundwater level prediction in a <scp>snow‐dominated</scp> region: An evaluation of <scp>EEMD</scp>, <scp>VMD</scp> and <scp>EWT</scp> decomposition techniques

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.

Land subsidence prediction in Zhengzhou's main urban area using the GTWR and LSTM models combined with the Attention Mechanism

In recent years, due to urbanization and human activities, groundwater overexploitation has become increasingly severe, resulting in some degrees of land subsidence and, consequently, causing a series of geological disasters and other environmental issues. Therefore, large-scale and high-precision land subsidence prediction is of great importance for the prevention and control of geological disasters. However, the existing prediction models and methods ignore the effects of the spatiotemporal non-stationary relationships between the influencing factors and the accumulated land subsidence, causing the poor accuracy of the predicted land subsidence results. In this context, a Geographically and Temporally Weighted Regression combined with the Long Short-Term Memory (LSTM)-multivariable and Attention Mechanism (AM) (GTWR-LSTMm-AM) was proposed to more accurately predict the deformation of time series land subsidence in this study. The small baseline subset-interferometric synthetic aperture radar (SBAS-InSAR) was used to reveal the temporal deformation information of Zhengzhou's main urban area, then the GTWR model was used to assess the spatiotemporal non-stationarity relationships between the accumulated land subsidence and its influencing factors monthly groundwater stability level, monthly precipitation and Normalized Difference Vegetation Index (NDVI) data, and to determine the corresponding weight matrix. In addition, we introduced an LSTM model with AM to extract key information from the time-series land subsidence data and adjusted the dynamic weights of the three selected influencing factors to predict the land subsidence in Zhengzhou's main urban area. The prediction accuracy R2 of the GTWR-LSTMm-AM model reaches 0.972, which is higher than 0.929 of the LSTMm model. The prediction accuracy RMSE is less than 3 mm and reaches 2.403 mm. In addition, we determined the importance of the impact factor on the subsidence results by randomly interrupting the impact factor time series, disclosuring that the monthly groundwater level contributed the most to the land subsidence in Zhengzhou's main urban area.

Converting Seasonal Measurements to Monthly Groundwater Levels through GRACE Data Fusion

Groundwater depletion occurs when the extraction exceeds its recharge and further impacts water resource management around the world, especially in developing countries. In India, most groundwater level observations are only available on a seasonal scale, i.e., January (late post-monsoon), May (pre-monsoon), August (monsoon), and November (early post-monsoon). The Gravity Recovery and Climate Experiment (GRACE) data are available to estimate the monthly variation in groundwater storage (GWS) by subtracting precipitation runoff, canopy water, soil moisture, and solid water (snow and ice) from the GLDAS model. Considering GRACE-based GWS data, the data fusion is further used to estimate monthly spatial maps of groundwater levels using time-varying spatial regression. Seasonal groundwater monitoring data are used in the training stage to identify spatial relations between groundwater level and GWS changes. Estimation of unknown groundwater levels through data fusion is accomplished by utilizing spatial coefficients that remain consistent with the nearest observed months. Monthly groundwater level maps show that the lowest groundwater level is 50 to 55 m below the earth’s surface in the state of Rajasthan. The accuracy of the estimated groundwater level is validated against observations, yielding an average RMSE of 2.37 m. The use of the GWS information enables identification of monthly spatial patterns of groundwater levels. The results will be employed to identify hotspots of groundwater depletion in India, facilitating efforts to mitigate the adverse effects of excessive groundwater extraction.

高寒内陆河流域植被覆盖增加对地下水补给的影响

PDF HTML阅读 XML下载 导出引用 引用提醒 高寒内陆河流域植被覆盖增加对地下水补给的影响 DOI: 10.5846/stxb202207212098 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学基金项目（42161020）；青海省科技厅应用基础研究项目（2021-ZJ-705） Impacts of the increasing vegetation coverage on groundwater recharge in an alpine and arid endorheic river watershed Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:地下水是干旱区内陆河流域的主要基础性资源，对流域生态安全、可持续发展等具有重要意义。干旱/半干旱区的地下水补给比湿润地区更易受到地表覆盖条件的影响。为揭示干旱区内陆河流域植被覆盖增加对地下水补给的影响，以巴音河中下游为例，针对土壤和水评价工具（SWAT）模型未有效考虑降水、地形等因素对植被覆盖影响的缺陷，改进SWAT模型，采用全球地表卫星叶面积指数（GLASS LAI）数据代替其LAI计算模块，再结合SWAT土地利用更新模块，准确刻画区域植被覆盖变化。将改进后的SWAT模型与模块化有限拆分地下水流耦合（MODFLOW）模型耦合，准确模拟并分析植被覆盖增加对流域地下水补给的影响。结果表明：基于植被动态变化的土壤和水评价工具与模块化有限拆分地下水流耦合模型（DVSWAT-MODFLOW）模型的月蒸散发及月地下水位模拟效果较好；巴音河中下游2019年林地及草地面积以及LAI较2001年明显增加；2019年植被覆盖情况对应的年际及月际尺度地下水补给量较2001年分别减少了6.1-26.52 mm以及0-15.03 mm；植被覆盖增加对年际尺度地下水补给量的影响强弱在一定程度上取决于年降水量，对月际尺度地下水补给量影响较强的月份集中于植物生长旺盛且降水较多时期。 Abstract:The groundwater is one of the most important basic resources in arid land. The groundwater recharge is easier to be affected by vegetation coverage in the arid and semi-arid areas than the wet areas. Bayin River Basin, a typical alpine and arid endorheic river watershed is located in the northeast of the Qaidam Basin. In the past 20 years, because of the warmer and more humid climate and human activities, the vegetation coverage condition of the watershed was becoming better. Calculation of the groundwater recharge in endorheic watershed is difficult. Soil and Water Assessment Tool (SWAT) is one of the most important tools that can simulate the watershed hydrological processes and its impact factors. However, it has considerable limitations in vegetation coverage and groundwater processes simulation. For the vegetation coverage simulation (leaf area index, LAI), it neglects the precipitation and terrain, which is important in arid land; For the groundwater simulation, it only is based on a simple linear mathematical formula without consideration of the physical processes. To better reveal the impacts of the vegetation coverage increasing on groundwater recharge in arid inland river, this research modified the SWAT model by replacing the LAI module with Global Land Surface Satellite (GLASS) based on LAI. The land use/cover change of the Middle and Lower Reaches of the Bayin River was further considered to better simulate the vegetation dynamics. After that, the modified SWAT model (named Dynamic Vegetation SWAT, DVSWAT) was coupled with the MODFLOW (MODular finite difference groundwater FLOW model), a professional groundwater processes simulation model. The latest GLEAM (Global Land Evaporation Amsterdam Model) v3 based on monthly evapotranspiration data and the observed groundwater level data were used to calibrate the DVSWAT-MODFLOW. We further used the variable-controlling approach to analyze the impacts of the vegetation coverage increasing on groundwater recharge based on the simulation results of the calibrated DVSWAT-MODFLOW. The results showed that the performance of the DVSWAT-MODFLOW in modelling the monthly evapotranspiration was good, with the R2 value of over 0.83, NSE value of over 0.68, and PBIAS value within -22%-22% for each subbasin. The performance of the DVSWAT-MODFLOW in modelling the monthly groundwater level was good as well, with the R2 value of over 0.95 and absolute bias of below 1 m for each groundwater level observation well. The area of the forest land and grassland in the study area increased 5.41 times and 98.96%, respectively, in 2019 compared to 2001. In addition, the annually average LAI of the study in 2019 increased 28.83% than 2001. The yearly and monthly groundwater recharge reduced about 6.1-26.52 mm and 0-15.03 mm, respectively, under the impacts of the increased vegetation coverage. The influence of the increasing vegetation coverage on the annual groundwater recharge depends on the annual precipitation to a certain extent. The months with strong influence on the monthly groundwater recharge are concentrated in the period of vigorous plant growth and more precipitation. 参考文献 相似文献 引证文献

Lag response of groundwater to changes in water and sediment characteristics in the lower Yellow River, China

• XLD operation decreased groundwater level along the lower Yellow River. • The highest groundwater level was delayed after XLD operation. • Inter-annual changes in groundwater were mainly determined by WL, SSC, and ISC. • Response of groundwater to changes in water–sediment lagged by 2–5 months. The process of water exchange between rivers and groundwater is critical for the circulation of material and energy; however, this process is strongly affected by dam-regulated water and sediment. The lower Yellow River seeps downward throughout its coarse and suspended (perched) riverbed and feeds the surrounding floodplain groundwater. The Xiaolangdi Dam (XLD) and water–sediment regulation scheme (WSRS) have altered the exchange processes between river and groundwater along the lower Yellow River. However, few researchers have examined the response of this river-fed groundwater system to the operation of the XLD and implementation of the WSRS. As such, in this study, we analyzed the responses of groundwater to changes in flow and sediment characteristics based on statistical analysis using historical data, extremely randomized tree models, and distributed lag non-linear models. We found that, since the XLD began operating in 2002, the groundwater level near the lower Yellow River substantially decreased, and the groundwater level in June significantly decreased (at the 0.05 level). The highest groundwater level in the pre-dam period occurred in August, whereas the highest level in the post-dam period occurred in October. Changes in the annual groundwater level and in the mid- and post-WSRS seasons along the lower Yellow River were mainly determined by the water level and incoming sediment coefficient in the river, whereas those in the pre-WSRS season were mainly determined by the water level and suspended sediment concentration. Regarding the changes in groundwater level between the mid- and post-WSRS seasons, we found that suspended sediment concentration was the dominant factor in the pre-dam period, whereas the combined effect of water and sediment was the dominant factor in post-dam period. The response of the monthly groundwater level to changes in water and sediment characteristics lagged by 2–5 months. These results are essential to understanding the interaction between river water and groundwater.

Time series-based groundwater level forecasting using gated recurrent unit deep neural networks

ABSTRACT In this research, the mean monthly groundwater level with a range of 3.78 m in Qoşaçay plain, Iran, is forecast. Regarding three different layers of gated recurrent unit (GRU) structures and a hybrid of variational mode decomposition with gated recurrent unit (VMD-GRU), deep learning-based neural network models are developed. As the base model for performance comparison, the general single-long short-term memory-layer network model is developed. In all models, the module of sequence-to-one is used because of the lack of meteorological variables recorded in the study area. For modeling, 216 monthly datasets of the mean monthly water table depth of 33 different monitoring piezometers in the period April 2002–March 2020 are utilized. To boost the performance of the models and reduce the overfitting problem, an algorithm tuning process using different types of hyperparameter accompanied by a trial-and-error procedure is applied. Based on performance evaluation metrics, the total learnable parameters value and especially the model grading process, the new double-GRU model coupled with multiplication layer (×) (GRU2× model) is chosen as the best model. Under the optimal hyperparameters, the GRU2× model results in an R 2 of 0.86, a root mean square error (RMSE) of 0.18 m, a corrected Akaike’s information criterion (AICc) of −280.75, a running time for model training of 87 s and a total grade (TG) of 6.21 in the validation stage; and the hybrid VMD-GRU model yields an RMSE of 0.16 m, an R 2 of 0.92, an AICc of −310.52, a running time of 185 s and a TG of 3.34.

A new modelling framework to assess changes in groundwater level

Study regionThe Southern African region consists of ten countries including, Angola, Zambia, Malawi, Namibia, Botswana, Zimbabwe, Mozambique, South Africa, Lesotho, and Swaziland. Frequent drought episodes in the arid and semi-arid parts of the region suggest the impact of climate change and the need for a sustainable framework for groundwater level assessments. Study focusIn this study, we developed a machine learning modelling framework based on the deep belief network (DBN) to predict the changes in monthly groundwater levels (CGWLs) at 1–5 month time scales for 27 groundwater wells over the southern Africa region. With a predictor dataset constituted by hydrological parameters, groundwater level estimates, and global climate indices, we ascertain the possibility of forecasting changes in groundwater levels (CGWL) up to 5-month lead times at most locations in the study region. Using the quantile regression technique, the strength of the DBN network at 90% and 95 % confidence levels were tested, and this helped to determine the accuracy of our forecasts at five months lead times over the four representative wells. New hydrological insights for the regionDeep learning offers new capabilities in evaluating non-linear hydrological systems, including groundwater analysis. The re-injection procedure of the DBN network, which allows the prior CGWL estimates to serve as inputs for the next estimate was key in maintaining the forecast accuracy in the 4th and 5th month lead times. This was evidenced in the accuracy of the four representative wells (r = 0.91, 0.87, 0.81, 0.75), which formed part of the test samples in CGWL analysis. We also observed that the DBN is highly susceptible to local climate variables and global climate indices, which are important drivers of climate change, and can have strong impact on groundwater level fluctuations. Therefore, the DBN proved to be a robust algorithm in our general assessments of groundwater level fluctuations.

Evaluating the BFAST method to detect and characterise changing trends in water time series: A case study on the impact of droughts on the Mediterranean climate

Mediterranean climate regions are facing increased aridity conditions and water scarcity, thus needing integrated management of water resources. Detecting and characterising changes in water resources over time is the natural first step towards identifying the drivers of these changes and understanding the mechanism of change. The aim of this study is to evaluate the potential of Breaks For Additive Seasonal and Trend (BFAST) method to identify gradual (trend) and abrupt (step- change) changes in the freshwater resources time series over a long-term period. This research shows an alternative to the Pettitt's test, LOESS (locally estimated scatterplot smoothing) filter, Mann–Kendall trend test among other common methods for change detection in hydrological data, and paves the way for further scientific investigation related to climate variability and its influence on water resources. We used the monthly accumulated stored water in three reservoirs, the monthly groundwater levels of three hydrological settings and a standardized precipitation index to show BFAST performance. BFAST was successfully applied, enabling: (1) assessment of the suitability of past management decisions when tackling drought events; (2) detection of recovery and drawdown periods (duration and magnitude values) of accumulated stored water in reservoirs and groundwater bodies after wet and dry periods; 3) measurement of resilience to drought conditions; (4) establishment of similarities/differences in trends between different reservoirs and groundwater bodies with regard to drought events.

Conjunction of cluster ensemble-model ensemble techniques for spatiotemporal assessment of groundwater depletion in semi-arid plains

• The cluster ensemble technique improved the final cluster structures. • The spatiotemporal ensemble clustering revealed four different patterns of GWL. • LSTM was not appropriate for monthly GWL forecasting compared to ensemble methods. • The neural ensemble has the lowest disorder and a large reduction in uncertainty. • The simultaneous clustering-forecasting ensemble techniques enhanced the outcomes. In this study, first to identify the patterns of groundwater level (GWL) over the Ghorveh-Dehgolan plain (GDP) located in western Iran, as a data pre-processing scheme, three different types of clustering algorithms were applied to monthly GWL data sets of the piezometers. Then, the best structures of all clustering methods were integrated by Combining Multiple Clusterings via Similarity Graph (COMUSA) method to obtain the most homogenous patterns of GWL. The final results of the clustering step indicated that applying COMUSA could enhance the homogeneity of the clusters up to 25%. After dividing the GWL of GDP into four patterns, three single artificial intelligence (AI)-based models were applied to forecast multi-step-ahead GWL of centroid piezometer of each cluster. To benefit from the advantages of the single models, the outcomes were then combined with a neural averaging ensemble (NAE) technique as a post-processing step. Additionally, the assessment of the deep learning (DL) -based long-short-term memory (LSTM) application in multi-step ahead forecasting of GWL showed this method is not an appropriate choice compared to ensemble techniques for modeling the process with limited observed data. The comparison of the proposed GWL forecasting models of this study revealed the superiority of the NAE technique that enhanced the accuracy of the single models up to 23% in the testing phase. It could be concluded that the combination of cluster ensemble and model ensemble techniques could improve the performance of the individual method in reliable forecasting of the future GWL condition and the methodology of this study can be applied to the GWL of other plains.

Monthly Dynamic Groundwater Estimation using GRACE over Indonesia

Indonesia is an archipelago with tropical climatic conditions, and part of it has arid areas. Monitoring groundwater dynamics effectively and efficiently is one of the challenges in a large area. GRACE is the Geodesy satellite that collects the sub-surface data. GRACE data is one of the gravity anomaly data that can be used for groundwater dynamics detection. Monthly groundwater monitoring can be used to determine the dynamic pattern of terrestrial water storage. It can be used as a parameter for the detection and prediction of drought in a large area. This study aims to model Indonesia's monthly groundwater levels based on gravity anomaly with GRACE satellite data. Anomaly gravity in GRACE's data is the main parameter in monitoring groundwater dynamics. Based on the results of monitoring during January-December 2020, three groundwater conditions were obtained in Indonesia. These conditions always have high groundwater potential, areas with diverse groundwater dynamics, and low groundwater areas. This low groundwater condition occurs in arid areas. The dynamic groundwater pattern occurred in the same month and had a similar pattern every season observed from 2002-2020. For example, the East Nusa Tenggara region has nine months of low groundwater potential. The potential and prediction of drought can be anticipated following the results of monitoring groundwater dynamics. Monitoring and predicting drought by predicting groundwater dynamics using GRACE's data can be an efficient and effective alternative for mapping, especially in Indonesia's vast and water-dominated territory.

Possibilities of Applying Multivariable Regression in Groundwater Data Series along a Riverbank Area

Abstract Groundwater modelling needs a large number of piezometer well data, which is unfortunately not always available as earlier registered data series are not always continuous. The reconstruction of data series with gaps was previously examined on a small riverside pilot area with the help of multiple regression, this method has now been tested at a 50-times larger environment. The results show that the reconstruction of the data series with this method works with average monthly groundwater levels and that applying multiple regression with the independent variables being one of the wells and the river optimizes the accuracy of the calculated data series, even if the relationships between the river and the wells are weak. The effect of the multiple regression on the accuracy is greater if the data series is sparser.

Potential impacts of climate change on groundwater levels in Golpayegan Plain, Iran

AbstractGroundwater level forecasting is an essential priority for planning and managing groundwater resources. This study aims to investigate the effect of climate change on the monthly groundwater level in the Golpayegan aquifer in the future (2017–2032). After a spatio-temporal analysis, the Least Squares Support Vector Regression (LSSVR) model was used to simulate the monthly groundwater level in the historical period (2002–2017). The input data included precipitation, temperature, pan evaporation, soil moisture (from the ESA CCA SM product), and groundwater level in observation wells on a monthly time-scale. Future climatic data were downloaded from the CanEsm5 model of CMIP6 for the SSP1-2.6 and SSP5-8.5 climate scenarios and then downscaled using the Change Factor Approach (CFA). The spatial analysis of groundwater levels indicated four different behaviors in the observation wells in the Golpayegan aquifer, resulting in four different clusters using the AGNES clustering method. Historical and future period modeling were performed separately for each of the four observation wells from each cluster. The modeling in the historical period demonstrated an average of NRMSE (0.09), MBE (0.030), and R2 (0.94) for the four clusters. The groundwater level in all clusters showed a decreasing trend in the future period, with SSP5-8.5 (average: 3.9 cm/month) showing a greater decrease than the SSP1-2.6 (average: 0.5 cm/month) scenario. The decline in groundwater level under SSP5-8.5 compared with SSP1-2.6 was more, respectively, 4.8, 5.8, 9.9 and 3.7 metres for clusters 1–4. The results indicate the acceptable efficiency and accuracy of the LSSVR model results in evaluating the effects of climate change on groundwater levels.

Summer Drought in 2019 on Polish Territory—A Case Study

The summer 2019 drought in Poland, i.e., the warmest year in observation history, was characterized. Meteorological, agricultural, hydrological, and hydrogeological aspects were taken into account. Meteorological drought in the light of regionally differentiated days of low precipitation frequency lasted the longest, i.e., over 3 months in central-western Poland. In the period between June–August 2019, in the belt of South Baltic Lakes and Central Polish Lowlands, the lowest precipitation sums of 30–60% of the norm were recorded. The values of the climatic water balance (CWB) calculated by the Institute of Soil Science and Plant Cultivation (IUNG) method for individual months of June–August for the Polish area were −129, −64, and −53 mm, respectively. The most threatened were fruit bushes, spring cereals, maize for grain and silage, and leguminous plants. In central-western and south-western Poland, the drought accelerated the date of the lowest flows by two months on average from the turn of September and October to the turn of July and August. In the lowland belt, where the drought was the most intensive, the average monthly groundwater level, both of free and tight groundwater table, was lower than the monthly averages for the whole hydrological year.

Impact of Groundwater Abstraction on Hydrological Responses during Extreme Drought Periods in the Boryeong Dam Catchment, Korea

Groundwater withdrawal results in a significant depletion of groundwater storage due to the frequency and intensity of droughts and increasing irrigation demands. To ensure the sustainable use of groundwater resources, it is necessary to accurately simulate the groundwater behavior of catchments using a surface–groundwater integrated runoff model. Most of the existing catchment runoff models have been applied to surface water management; thus, integrated runoff analysis studies that consider the interaction between surface water and groundwater are required. Due to the intensive agricultural sector in Korea and the position of rice as the staple in the Korean diet, more than 50% of groundwater abstraction is used for irrigation. Therefore, it is very important to understand the hydrological interrelationships between agricultural areas and the entire watershed. This study aimed to compare and analyze the groundwater levels in the mountainous areas and paddy field areas in the Boryeong Dam catchment through a surface–groundwater integrated runoff simulation using the Catchment Hydrologic Cycle Assessment Tool model, and to compare the hydrological responses in wet years (2010–2012) and dry years (2014–2016). The maximum difference in the monthly groundwater level in the dry years compared to the wet years was 1.07 m at the forest catchment and 0.37 m at the paddy catchment. These results indicate that the impact of drought on the groundwater level of paddy catchments is not significant compared to the forest catchments; however, drought slows the recovery of the groundwater level before the rainy season, thereby limiting the agricultural groundwater use in the catchment.

A physically constrained wavelet‐aided statistical model for multi‐decadal groundwater dynamics predictions

AbstractA physically constrained wavelet‐aided statistical model (PCWASM) is presented to analyse and predict monthly groundwater dynamics on multi‐decadal or longer time scales. The approach retains the simplicity of regression modelling but is constrained by temporal scales of processes responsible for groundwater level variation, including aquifer recharge and pumping. The methodology integrates statistical correlations enhanced with wavelet analysis into established principles of groundwater hydraulics including convolution, superposition and the Cooper–Jacob solution. The systematic approach includes (1) identification of hydrologic trends and correlations using cross‐correlation and multi‐time scale wavelet analyses; (2) integrating temperature‐based evapotranspiration and groundwater pumping stresses and (3) assessing model prediction performances using fixed‐block k‐fold cross‐validation and split calibration‐validation methods. The approach is applied at three hydrogeologicaly distinct sites in North Florida in the United States using over 40 years of monthly groundwater levels. The systematic approach identifies two patterns of cross‐correlations between groundwater levels and historical rainfall, indicating low‐frequency variabilities are critical for long‐term predictions. The models performed well for predicting monthly groundwater levels from 7 to 22 years with less than 2.1 ft (0.7 m) errors. Further evaluation by the moving‐block bootstrap regression indicates the PCWASM can be a reliable tool for long‐term groundwater level predictions. This study provides a parsimonious approach to predict multi‐decadal groundwater dynamics with the ability to discern impacts of pumping and climate change on aquifer levels. The PCWASM is computationally efficient and can be implemented using publicly available datasets. Thus, it should provide a versatile tool for managers and researchers for predicting multi‐decadal monthly groundwater levels under changing climatic and pumping impacts over a long time period.

Groundwater level oscillation analysis in shallow alluvial aquifers in Pomurje, NE Slovenia

Systematic hydrologic monitoring of groundwater quantity at the national level in Slovenia has been ongoing since 1952. An insight into long-term groundwater level data enables us to delineate parts of aquifers with similar groundwater level oscillation properties as well as to identify changes of those properties in time. We used variety of statistical methods to identify long-term behaviour of groundwater level oscillation of groundwater body (GWB) Murska kotlina. Results showed that fluctuation of groundwater level in time reflect complex set of events that originate in natural or anthropogenic interferences. Using percentile analysis in combination with cluster analysis, we were able to isolate areas with a related groundwater fluctuation. Results of long-term data trends analyses of monthly groundwater level showed the impact of the research area climate on long-term and seasonal groundwater level fluctuation. In addition to natural causes, by performing trend analysis on groundwater level data, we were able identify some human induced interventions into the environment made in the past.

Spatio-temporal estimation of monthly groundwater levels from GPS-based land deformation

Significant subsidence is susceptible to groundwater level variations in aquifer systems. The relation between groundwater level change and global positioning system (GPS) estimated subsidence is spatially variable. Time-dependent spatial regression can be used for the estimation of groundwater level changes using GPS based deformation data. Furthermore, the model can be validated using observed hydraulic head data from available monitoring stations. This study uses GPS station data to estimate the monthly groundwater levels in the west-central Taiwan for the period: 2016–17.Time-dependent spatial regression provides a more realistic estimation of groundwater level changes in response to highly heterogeneous aquifer properties than other methods. The high correlation (r = 0.95) between observed and estimated groundwater levels shows that GPS estimated deformations represent an alternative approach for estimating seasonal groundwater changes. Due to availability of spatially broad/low cost GPS data (compared to the sparse availability groundwater monitoring stations), the use of GPS data represents a powerful solution for future monitoring of estimated seasonal groundwater level changes in areas where only few groundwater observations are available.