Seawater Intrusion Research Articles

Effects of climate variability and change on groundwater impacts of forestry plantations

AbstractQuantifying water use of various water consumers is an essential part of sustainable water management. Annual evapotranspiration (ET) of plantation forests often exceeds that of dryland agriculture, which in South Africa and South Australia has resulted in restrictions on plantation development. In the latter case, water licences are issued to commercial forestry plantations to account for higher ET compared to dryland pasture. Unlike irrigated crops, it is not practicable to measure water use of plantations directly and so in South Australia a set of ‘deemed’ average water use rates has been applied since 2013, based on species and depth to groundwater. Since South Australia's ‘deemed’ rates were calculated, additional plot‐scale measurements of annual ET from plantations <2 years old and post‐canopy closure have been used to quantify various components of ET. This has enabled development of two empirical ET models for plantations in South Australia's Lower Limestone Coast, and facilitated an advanced understanding of the effect of plantations on hydrological processes, particularly in relation to groundwater use. In this study, we applied these models to estimate rotation‐averaged annual ET and net groundwater impacts (net groundwater extraction plus recharge reduction compared to pasture) of plantations, driven by climate and groundwater depth, for comparison with the deemed rates. The modelling suggests that the groundwater impacts of plantations vary in space and time and that the deemed rates over‐estimate these impacts, on average. Accounting for variation in the effects of climate on the various components of ET, both spatially and temporally, may allow for more flexible rules for water resource allocation than using any simple, rule‐of‐thumb approach.

Modeling and analysis of temporal dynamics in groundwater aquifers of New Valley Oases, Egypt

Water scarcity poses a significant challenge in arid and semi-arid regions, necessitating a focused exploration of groundwater resources. Egypt, confronted with various water challenges, particularly in its Western Desert, relies heavily on groundwater as the exclusive water source due to the presence of the Nubian Sandstone aquifer. Effective groundwater management in this region is imperative. This study delves into the hydrogeological characteristics of the Nubian Sandstone aquifer system (NSAS) in the prominent New Valley Oases—Kharga, Dakhla, and Farafra—where agricultural activities heavily depend on groundwater. The primary objective entails a meticulous temporal assessment of the impact of groundwater development on aquifer behavior, groundwater levels, and drawdown. Employing a remote sensing approach, agricultural expansion from 1995 to 2020 was scrutinized. The Visual MODFLOW package served as a robust tool for simulating groundwater flow in the study areas. Noteworthy findings reveal an upward trajectory in agricultural crop areas, escalating by approximately 6% from 1740 km² in 1995 to 1850 km² in 2020. Concurrently, drawdown, influenced by current groundwater extraction, is anticipated to range from 0.5 to 5 meters per year. To ensure the sustainable development of these areas, stringent regulations must be implemented, underscoring the imperative for judicious groundwater management practices. This research underscores the critical need for informed decision-making and proactive measures to address the evolving dynamics of groundwater resources in the New Valley Oases.

Geophysical contribution based on vertical electrical sounding to hydrogeological evaluation in Ras Jebel coastal aquifer, Tunisia

AbstractThe coastal aquifer of Ras Jebel is located in the northeastern governorate of Bizerte. It is formed by a Mio–Plio‐quaternary geological structure. The region of Ras Jebal is considered an important agricultural centre due to intensive groundwater exploitation. This overexploitation results in a decrease in piezometry and an increase in salinity. The groundwater piezometric study shows a decrease in the piezometric level of approximately −3.34 to −1.79 m in 2015. Our study based on vertical electrical sounding had the aim to monitor the salinity of the water table in 2017, which showed that refill transactions in the aquifer of Ras Jebel caused the improvement of the chemical quality of water. In fact, the salinity in the coastal zone is between 2.53 and 4.14 g/L. As for the resistivity, which reached 2 Ω m near the sea, the geophysical study based on the geoelectric method has provided an electrical image of the basement to clarify the basin structure. The use of an electrical prospection method to study the salinization of the water table of Ras Jebel has highlighted the contribution to the most origin of saltwater: natural origin (sea water intrusion) on the northeastern coast of Ras Jebel. This source is the main origin of the degradation of the quality of underground water resources in Ras Jebel.

Analysis of the Data Presented by Tide Gauge Stations in Albania

This study focuses on the comprehensive monitoring of tide gauges along the coastal regions of the Republic ofAlbania, aiming to assess sea level variations and understand the dynamics of the coastal environment. Tide gaugesplay a crucial role in providing essential data for coastal management, climate change studies, and disasterpreparedness. The research involves the deployment and maintenance of tide gauges at strategic locations along theAlbanian coastline, coupled with an in-depth analysis of the collected data. The monitoring process includescontinuous data acquisition from tide gauges, incorporating advanced sensors and telemetry systems to ensure realtime and accurate measurements. The acquired data are analyzed to identify patterns, trends, and anomalies in sealevel variations. Additionally, the study investigates the influence of meteorological and oceanographic factors on tidegauge readings, enhancing the understanding of the complex interactions shaping coastal dynamics. Furthermore, theresearch explores the implications of observed sea level changes on coastal ecosystems, infrastructure, andcommunity resilience. It provides valuable insights into potential threats such as coastal erosion, saltwater intrusion,and flooding. The findings contribute to the development of effective adaptation and mitigation strategies to addressthe challenges posed by rising sea levels.

Superoxide Photoproduction from Wetland Plant-Derived Dissolved Organic Matter: Implications for Biogeochemical Impacts of Plant Invasion.

Although the impacts of exotic wetland plant invasions on native biodiversity, landscape features, and carbon-nitrogen cycles are well appreciated, biogeochemical consequences posed by ecological competition, such as the heterogeneity of dissolved organic matter (DOM) from plant detritus and its impact on the formation of reactive oxygen species, are poorly understood. Thus, this study delves into O2•- photogeneration potential of DOM derived from three different parts (stem, leaf, and panicle) of invasive Spartina alterniflora (SA) and native Phragmites australis (PA). It is found that DOM from the leaves of SA and the panicles of PA has a superior ability to produce O2•-. With more stable aromatic structures and a higher proportion of sulfur-containing organic compounds, SA-derived DOM generally yields more O2•- than that derived from PA. UVA exposure enhances the leaching of diverse DOM molecules from plant detritus. Based on the reported monitoring data and our findings, the invasion of SA is estimated to approximately double the concentration of O2•- in the surrounding water bodies. This study can help to predict the underlying biogeochemical impacts from the perspective of aquatic photochemistry in future scenarios of plant invasion, seawater intrusion, wetland degradation, and elevated solar UV radiation.

Assessment of spatio-temporal variations in groundwater quality for the groundwater-dependent Maltese islands

Study regionMaltese islands Study focusThe Maltese islands are situated in the Mediterranean Sea, characterized by a semi-arid climate, and encounter increased levels of water stress. This study conducted a hydrochemical analysis of 35 groundwater samples to evaluate the suitability of the current groundwater for agricultural and domestic purposes. Additionally, three-dimensional numerical modeling was conducted to estimate long-term changes in groundwater levels and saline water distributions over 30 years, under the assumption that groundwater pumping will persist at the current rate. New hydrological insights for the regionSalinity factors that classify groundwater in this region can potentially be used for the irrigation of salt-tolerant crops. The output of the modeling calculations suggests that groundwater levels were expected to decrease significantly across most of the island, particularly around gallery areas. Descending the water table may compromise the discharge of coastal groundwater and potentially accelerate seawater intrusion into the inner island areas. Hydrochemical calculations indicated that an increase in salinity induced variations in saturation conditions, leading to a decrease in calcite and an increase in anhydrite, dolomite, and gypsum. The water quality characteristics and contamination evaluations conducted in this study are valuable for the development of long-term alternatives for water resource conservation in this region.

Experimental study of air curtains blocking saltwater intrusion under estuary dynamic conditions

The saltwater intrusion seriously threatens the water supply security of estuaries, while the existing salty blocking measures (e.g., gates and dams) are rude and the dynamic mechanism is not fully considered. In order to investigate countermeasures to reduce the risk of the saltwater intrusion, as well as enrichment blocking methods, in this paper, the salt-inhibiting properties of air curtain under tidal action was investigated based on a long-distance physical flume with dual tidal-salinity control capability. Experimental results indicate that air curtains significantly diminish distance of saltwater into estuaries. The bubble plumes, on the one hand, promote vertical mixing, elevating high-salinity water from the depths to the surface, thereby disrupting the vertical circulation structure of salt wedge. On the other hand, the energy dissipation and barrier effect produced by bubble bursting can significantly reduce the momentum of the invading saltwater. Meanwhile, the research emphasizes that the salt intrusion length is negatively correlated with the airflow discharge, whereas the salty-blocking effect prefer better of the weakly-mixed estuary than the strongly-mixed. Most importantly, the air curtain mixing coefficient ka were proposed at the first time to quantify the salty blocking effect. The mixing coefficient ka is the function of airflow discharge Qa and tidal current ut, demonstrating a direct proportionality to Qa and ut−1. Moreover, a quantitative relationship between ka and Qa/ut was obtained from experimental results. The research results would help inform the flexible salt-inhibiting measures of estuarine air curtain.

<span>Evaluating the effect of Brasinolide on the salinity tolerance of spring onion (<em>Allium fistulosum L.)</em> under saline irrigation conditions</span>

Spring onions are an essential spice in Vietnamese food preparation for its favor and aroma. Tra Vinh, one of the coastal provinces, is greatly affected by climate change and saline intrusion. Hence, this study was conducted to access the effects of Brasinoline (Br) on the growth of Spring onion under normal conditions and salt stress events. The experiment embraced four Br concentrations (0 ppm, 0.05 ppm, 0.1 ppm, and 0.15 ppm) under both fresh water and 3‰ saltwater irrigation conditions, distributed according to the 2-factor Randomized Completely Block Design (RCBD). Preliminary results, with concentrations of Br 0.1 ppm and 0.15 ppm, show a high increase in leaf length, number of leaves/brush, number of shoots, stem diaphragm and plant green weight. Under 3‰ salt water irrigation conditions, Br concentration of 0.15 ppm showed supporting effectively the growth of Spring onions equivalent to that in fresh water.

Hydrogeological conceptual model and groundwater recharge of Avella Mts. karst aquifer (southern Italy): A literature review and update

Study regionAvella Mts., southern Italy. Study focusThe paper is focused on groundwater of Avella Mts. This aquifer has been experiencing an increasing human pressure due to periods of drought and growth in groundwater extraction. A novel hydrogeological conceptual model was developed, and groundwater recharge was estimated by two approaches. The study was carried out by an in-depth literature review and a GIS-based analysis of geological and piezometric data, ground-based meteorological and remotely sensed data. New hydrological insights for the regionThe new hydrogeological conceptual model allowed to reconstruct the aquifer lithology, its deep geometry, and, for the first time, groundwater flow scheme. Five groundwater basins were recognized with distinct outlets and subsurface outflows, suggesting a new aquifer compartmentalization in-series groundwater basins. Some basal springs are fed by autonomous basins with smaller extension, while other springs have dried up completely. The groundwater recharge varies from 7.30 to 6.90 m3/s as estimated by Turc formula and MODIS data, respectively; the values are comparable among them, confirming mutually the validity of approaches used. The comparison with previous studies highlights variations and changes for both the hydrogeological conceptual model and water balance, linked to natural and anthropogenic factors. The results obtained represent a way for supporting sustainable management of groundwater, waterwork systems security and groundwater-dependent ecosystems protection of a large sector of Campania region.

Modeling the water use associated with energy consumption changes on saltwater intrusion in the Pearl River estuary, China

The intrusion of saline tide into estuaries is one of the major environmental issues impedding the regional development of the Pearl River Estuary, which has been exacerbated by increasing water use associated with energy consumption in the estuary areas. However, the relationship among water use, energy consumption and saltwater intrusion remains ambiguous. Firstly, this paper established a k-nearest neighbor model that identified the correlation between inputs of precipitation and sectoral energy consumption and output of runoff in the Humen Channel as part of the Pearl River Estuary during 2019–2020. Then, the Finite–Volume Community Ocean Model (FVCOM) was employed to explore the process-based mechanism between runoff and salinity via three scenarios simulated for the periods 2030–2031 and 2060–2061 with different water use and precipitation levels. Finally, the impacts of sectoral energy consumption on saltwater intrusion under the different scenarios were analyzed. The results showed that the increase of the energy consumption was positively correlated to runoff, especially in the wet season of Humen Channel. The monthly average salinity exhibited remarkable seasonal variations with similar trends under three scenarios. Totally 654 days with salinity exceeding the standard were projected to take place in the downstream of Humen Channel during the simulation period.

A comprehensive framework for stochastic calibration and sensitivity analysis of large-scale groundwater models

Abstract. We introduce a comprehensive and robust theoretical framework and operational workflow that can be employed to enhance our understanding, modeling and management capability of complex heterogeneous large-scale groundwater systems. Our framework encapsulates key components such as the three-dimensional nature of groundwater flows, river–aquifer interactions, probabilistic reconstruction of three-dimensional spatial distributions of geomaterials and associated properties across the subsurface, multi-objective optimization for model parameter estimation through stochastic calibration, and informed global sensitivity analysis (GSA). By integrating these components, we effectively consider the inherent uncertainty associated with subsurface system characterizations as well as their interactions with surface waterbodies. The approach enables us to identify parameters impacting diverse system responses. By employing a coevolutionary optimization algorithm, we ensure efficient model parameterization, facilitating simultaneous and informed optimization of the defined objective functions. Additionally, estimation of parameter uncertainty naturally leads to quantification of uncertainty in system responses. The methodology is designed to increase our knowledge of the dynamics of large-scale groundwater systems. It also has the potential to guide future data acquisition campaigns through an informed global sensitivity analysis. We demonstrate the effectiveness of our proposed methodology by applying it to the largest groundwater system in Italy. We address the challenges posed by the characterization of the heterogeneous spatial distribution of subsurface attributes across large-scale three-dimensional domains upon incorporating a recent probabilistic hydrogeological reconstruction specific to the study case. The system considered faces multiple challenges, including groundwater contamination, seawater intrusion, and water scarcity. Our study offers a promising modeling strategy applicable to large-scale subsurface systems and valuable insights into groundwater flow patterns that can then inform effective system management.

Microbial Community Shifts in Tea Plant Rhizosphere under Seawater Stress: Enrichment of Beneficial Taxa.

Seawater intrusion has a significant impact on the irrigation quality of agricultural water, thereby posing a threat to plant growth and development. We hypothesized that the rhizosphere of tea plants harbors beneficial microorganisms, which may improve the tolerance of tea plants to seawater stress. This study utilized 16s and ITS techniques to analyze microbial community shifts in the tea plant rhizosphere and non-rhizosphere under seawater stress conditions. The findings suggest that seawater stress leads to a reduction in microbial diversity, although the rhizosphere microbial diversity in stressed soils showed a relatively higher level. Moreover, the rhizosphere of the tea plant under seawater stress exhibited an enrichment of plant growth-promoting rhizobacteria alongside a higher presence of pathogenic fungi. Network analysis revealed that seawater stress resulted in the construction of a more complex and stable rhizosphere microbial network compared to normal conditions. Predictions of bacterial potential functions highlighted a greater diversity of functional groups, enhancing resource utilization efficiency. In general, the rhizosphere microorganisms of tea plants are jointly selected by seawater and the host. The microorganisms closely related to the rhizosphere of tea plants are retained and, at the same time, attract beneficial microorganisms that may alleviate stress. These findings provide new insights into plant responses to saline stress and have significant implications for leveraging vegetation to enhance the resilience of coastal saline soils and contribute to economic progress.

Gonadal development of striped catfish (Pangasianodon hypophthalmus) in climate-caused salinity intrusion

Salinity intrusion is one of the major climate-caused problems globally. The present work evaluated the impacts of salinity on the gonadal improvement in striped catfish (Pangasianodon hypophthalmus). The fingerlings of striped catfish (8.63 g) were cultured at three different salinity levels (0, 4, and 8 ppt) for two years. Gonadal development was assessed by gonadosomatic index (GSI) and histological analysis over six months at the end of two years of rearing from April to September. The gonad histological observations and the associated changes in GSI showed that the male and female striped catfish cultured in different salinity conditions could complete testicular and ovarian maturation at 4 and 8 ppt salinity by June and July, as they have grown at 0 ppt salinity. The current findings indicate that despite a slow rate of development, salinity up to 8 ppt showed a positive impact on the gonadal development of striped catfish. Asian J. Med. Biol. Res. 2024, 10(2), 89-98

Energy-water management system based on robust predictive control for open-field cultivation

Food availability has been endangered by recent global events, where agriculture, the main food source for the global population, is expected to increase even more to fulfill the growing food demand. Along with food production, water and energy consumption are also increased, leading to over-extraction of groundwater and an excess emission of greenhouse gases due to fossil fuel consumption. In this context, a balance of these three resources is crucial; therefore, the water-energy-food nexus is considered to address the previous issues by designing an energy-water management system based on robust predictive control. This controller estimates the future worst-case scenario for multiple climatic conditions, such as solar radiation, ambient temperature, wind speed, precipitation, and groundwater recharge, to define an optimal irrigation volume, maximize crop growth, and minimize water consumption. At the same time, the controller schedules daily irrigation and groundwater extraction, considering energy availability from solar generation and storage, to fulfill the previously defined irrigation volume while minimizing operating costs. Climate prediction is done through fuzzy prediction intervals, whose lower or upper bound are used as worst-case to include climate uncertainty on the controller design. The energy-water management system is tested in different experiments, where results show that considering a robust approach ensures maximum crop development, avoids over-extraction of groundwater, and prioritizes renewable energy sources. This work proposes a robust energy-water management system designed to be sustainable. Considering the water-energy-food nexus, the system ensures food security and proper resource allocation, tackling global starvation, water availability, and energy access.

Exploring AI approaches for predicting groundwater levels in coastal agro-climatic zones: a case study in Cuttack District, Odisha

Groundwater level (GWL) prediction across various time scales is essential for efficient management and governance of water resources especially in regions characterized by arid and semi-arid climates, and it holds great significance. Within certain coastal regions, agro-climatic zones give rise to challenges like water scarcity in summer and waterlogging during the rainy season, resulting in reduced GWL during scarcity periods and saltwater intrusion that contaminates groundwater. This study emphasizes on application of diverse AI methodologies, encompassing Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Wavelet Transform-based ANN (W-ANN), ANFIS (W-ANFIS), SVR (W-SVR), and LSTM (W-LSTM) models for quantitative assessment of groundwater in Odisha's Cuttack District, aiming to comprehend GWL fluctuations across the region. The investigation leverages historical groundwater data from monitoring wells, incorporating monthly datasets of rainfall, temperature, relative humidity, and GWLs. Through comparative assessment using statistical methods namely Pearson’s R (R), co-efficient of determination (R2), Root Mean Squared Error (RMSE), and Sum of Squared Error (SSE), the most precise and robust AI approach for groundwater estimation in the area is identified. The W-LSTM (R2-0.78196, RMSE- 0.09254, R-0.88428 and SSE-2.66357) and W-ANFIS (R2-0.74068, RMSE-0.08229, R-0.86063 and SSE-2.10596) hybrid algorithms consistently achieved the most accurate predictions for GWLs followed by W-SVR, W-ANN hybrid models and LSTM and ANN for all stations. Overall, this study demonstrated promising outcomes, offering a dependable foundation for water resources planners to guide future investigations into groundwater resources.

Super-hydrophilic carbonized wood-based solar steam evaporator: A novel approach to enhance freshwater generation

Solar steam evaporation has been shown to represent an advanced approach to freshwater generation. The primary obstacles in developing solar steam generation devices utilizing biomass materials include intricate manufacturing procedures and a comparatively lower energy conversion efficiency. Here, we detailed a straightforward approach involving the deposition of polydopamine (PDA) onto carbonized wood, creating an innovative solar interface evaporation device. Treated wood obtained by removing a part of lignin and hemicellulose was transformed into carbonized wood through a straightforward wood carbonization process. Subsequently, the carbonized wood's water and light absorption were further enhanced by applying a hydrophilic coating using dopamine (DA) and diethylenetriamine (DETA). The result was the development of a wood-based solar interface evaporator capable of performing three essential functions: light absorption, photothermal conversion, and water transfer. The Super-hydrophilic carbonized wood (SCW) solar steam evaporator possessed an evaporation efficiency of approximately 91.81 %, net evaporation of 1.7853 kg m−2 h−1 in seawater, an evaporation efficiency of approximately 78.44 %, and net evaporation of 1.52538 kg m−2 h−1 in groundwater at one sun, respectively. Therefore, SCW holds substantial promise for applications in seawater desalination and groundwater extraction, offering a valuable solution to address the issue of inadequate freshwater availability.

Analisis Kualitas Air Sumur Bor Berdasarkan Kesesuaian Higiene Sanitasi di Kelurahan Ujung Gurun Kecamatan Padang Barat Kota Padang

This study aims to determine the quality of well water in Ujung Gurun Village, Padang City and the factors that influence it. The research method used is quantitative research by utilizing primary data taken from several well samples in the area. The parameters tested include pH, Total Dissolved Solids (TDS), iron (Fe), manganese, and lead.The results showed that most of the water quality parameters have met the requirements, except for the iron (Fe) content which is in the range of 1.7 to 7.5 Mg/L, exceeding the set limit. Overall, the quality of well water in Ujung Gurun Village is quite good, but further processing is needed to reduce the iron content to comply with the applicable regulations.The factors that affect the water quality in this area are poor and clogged drainage, as well as the possibility of seawater intrusion. Improvement and maintenance of the drainage system as well as appropriate water treatment need to be carried out to improve the quality of well water in Ujung Gurun Village, Padang City.

Cover collapse sinkhole formation is delayed in time and uncorrelated to distance from quarry in a long-term study of a karst basin

Collapse sinkholes are problematic for the hazards they bring to property, infrastructure, and human life but the prediction of their formation in time and space remains elusive. We make use of long-term data gathered in a small, highly monitored, hydrologically constrained basin; Primrose Creek, Bucks County, Pennsylvania, USA, to examine the relation between groundwater extraction, precipitation, terrain position, and cover collapse sinkhole development. The selected site is unique as a natural laboratory to explore induced sinkhole processes in that it is a clearly demarcated topographic basin with geological structural and lithologic boundaries; the stressor is extreme, has been plainly identified, and effectively captures all upstream runoff and groundwater; the groundwater withdrawals and water-level elevations have been closely monitored over a period of 20 years; and the general record of land conditions goes back more than a century. We evaluated the history of a carbonate-rock quarry, its development and expansion over many decades, as well as associated precipitation and ground-water level data, and cover collapse sinkhole occurrence within the basin. Interception of discrete high conductivity zones in the Paleozoic carbonate rocks by quarry expansion was an important factor in propagating collapse occurrence. Collapses occurred mainly, though not exclusively, along drainageways and at lithologic boundaries. They formed in time-based clusters with delay of up to several years. Surprisingly, distance of collapse formation from the pumping area was not directly correlated with time elapsed; i.e., collapses did not begin to form close to the quarry, and then later form farther away. Monitoring wells were unsuccessful in delineating the pumping zone of influence although some documented water table decline and response to weather and anthropogenic events. This comprehensive study shows that in order to successfully monitor and control impacts from quarry dewatering in Paleozoic carbonate rocks it is critical to 1) develop a detailed conceptual model of groundwater pathways, 2) try to avoid excavating into high permeability zones, 3) clearly document karst features when exposed, and 4) carefully site a suitable number of monitoring wells and collect data at short intervals.

Study on the Removal Effect of 3DEPs on Microplastics in Groundwater and Desalination Mechanism

Owing to water scarcity, groundwater quality has become an important constraint on sustainable regional development, especially in coastal areas. Coastal groundwater is subject to natural conditions and intense human activities, and the evolution of water quality is extremely complex, with the possibility of seawater intrusion into the groundwater, leading to the salinisation of freshwater aquifers. At present, the commonly used methods for removing groundwater pollution include coagulation, adsorption, biological method, membrane technology, etc., among which the coagulation method is more commonly used. At present, three-dimensional electrode electrochemical technology is widely used in high salinity organic wastewater and many organic wastewaters, but there are few studies related to microplastic removal by three-dimensional electrode electrochemical technology using metallic aluminium particles as particle electrodes. The treatment of microplastics in coastal groundwater is a relatively novel issue, and with the increasing application of three-dimensional electrochemical technology in the study of desalination, the three-dimensional electrode electrochemical technology will be promising due to the high salinity of coastal groundwater, the increasingly serious pollution of microplastics, and the fluctuation of water quality and quantity.

Spatial and temporal forecasting of groundwater anomalies in complex aquifer undergoing climate and land use change

Monitoring groundwater (GW) level variations, or anomalies in multiple wells, over long periods of time is essential to understanding changes in regional groundwater resource availability. However, it is challenging to predict these GW anomalies over the long term in agricultural areas due to complicated boundary conditions, heterogeneous hydrogeological characteristics, and groundwater extraction, as well as nonlinear interactions among these factors. To overcome this challenge, we developed an advanced modeling framework based on a recurrent neural network of long short-term memory (LSTM) as an alternative to complex and computationally expensive physical models. GW anomalies were forecast two months in advance (t + 2) based on the evaluation of drivers that influence GW dynamics in densely irrigated agricultural regions. An application and evaluation of this new approach was conducted in the Wisconsin Central Sands (WCS) region in the U.S., one of the most productive agricultural regions. The modeling framework was developed for the period 1958–2020 by utilizing easily accessible dynamic and static variables to represent hydrometeorological and geological characteristics. GW anomaly observations were acquired from 26 piezometers (wells) installed in the sandy aquifer in WCS over 10–60 years. The subset of GW observations from ∼ 10–60 years, not used in model training, can forecast GW anomalies two months out with a coefficient of determination R2 ∼ 0.8. Additionally, MAE was less than 0.34 m/month across the study region for both temporal and spatial modeling frameworks. Groundwater anomalies showed high spatiotemporal variability, and their responses are influenced differently by boundary conditions, catchment geology, climate, and topography across locations. Sites with higher autocorrelation with previous two-months GW anomalies reduced bias by increasing R2. Land use change and irrigation pumping have interactive effects on GW anomalies forecasting. The novelty of this study is identifying the regional drivers of GW fluxes. This case-specific information and location-related simplification, modification, and assumption of LSTM is a unique contribution to the existing literature. Our framework can be used as an alternative method of simulating water availability and groundwater level changes in areas where subsurface properties are unknown or difficult to determine.