Groundwater for Sustainable Development最新文献

{"title":"Determining factors and strategy in sustainable fecal sludge management services","authors":"Nadia Paramita ,&nbsp;Rachmadhi Purwana ,&nbsp;Djoko Mulyo Hartono ,&nbsp;Tri Edhi Budhi Soesilo","doi":"10.1016/j.gsd.2024.101390","DOIUrl":"10.1016/j.gsd.2024.101390","url":null,"abstract":"<div><div>Currently, 65% of the total residents of Jakarta rely on groundwater as their primary water source for daily life. Groundwater quality is critical, with the presence of <em>Escherichia coli</em> bacteria throughout Jakarta significantly exceeding the limit. The solution to preventing groundwater pollution from fecal waste is through domestic wastewater management. On-site treatment is a solution to accelerate service achievement in Jakarta, but it has yet to be known which priority factors affect the sustainability of its services. This study aimed to determine the community's understanding of and interest in regular desludging services, the priority weights of sustainability factors for desludging services in Jakarta Province, and alternative sustainability strategies. The research and sampling in this study were conducted in Jakarta Province. Random sampling was conducted on 410 people. A hierarchical process analysis was conducted with 13 stakeholder respondents to determine the weight of the sustainability factors and the strategy to achieve sustainability of fecal sludge services. This study showed that 34.5% of Jakarta residents still rely on groundwater to meet their clean water needs through private and public wells. According to the regulations, 83% of people use septic tanks, but only 22% use desludging. To achieve sustainability of the fecal sludge service in Jakarta Province, the Leadership Factor has the highest priority, with a weight of 39%. The lowest priority was indicated by the technology factor, with a weight of 4.8%. An alternative strategy to achieve sustainability showed the highest priority weight of 82.6% for regular desludging services compared with on-call desludging. Regulations and sanctions support regular desludging. The role of leaders, both regional leaders and institutions, in committing to achieve service targets in a region is very important. Regular desludging services are recommended to ensure the sustainability of fecal sludge services in Jakarta Province.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101390"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding groundwater level patterns and abrupt changes in Central and Southern California's alluvial regions","authors":"Fabio Di Nunno,&nbsp;Francesco Granata","doi":"10.1016/j.gsd.2025.101409","DOIUrl":"10.1016/j.gsd.2025.101409","url":null,"abstract":"<div><div>The variability in groundwater levels (GWL) in California's Central Valley and Southern California Coastal Basin, driven by climatic and hydrological shifts, poses significant challenges for ecosystems and agricultural sustainability. This study employs a dual-method approach, integrating the Seasonal Kendall (SK) test and the Bayesian Estimator of Abrupt Change, Seasonality, and Trend (BEAST) algorithm, to analyze long-term trends and abrupt shifts in GWL. The SK test reveals statistically significant declines in GWL across most wells, with particularly severe reductions observed in the Central Valley and the counties of San Bernardino and San Diego. For instance, well A5 in the Central Valley recorded a Z-value of 23.83 and a β of 2.36, marking acute groundwater depletion. Similarly, in San Bernardino County, wells S11 (Z = 24.09, β = 14.50) and S17 (Z = 24.20, β = 9.53) demonstrated alarming declines. These findings suggest that reduced recharge rates and intensified extraction are driving the depletion, which in turn threatens local ecosystems through diminished streamflows and wetland contraction. However, some wells exhibited rising GWL, attributed to localized recharge, underscoring the spatial heterogeneity of groundwater dynamics. BEAST analysis further identified both positive and negative abrupt changes in GWL, reflecting complex responses to environmental variability. While several wells recorded sharp drops in GWL, such as up to −7.48 m in the Central Valley and −44.00 m in Southern California, others demonstrated notable recoveries, including up to 4.20 m in the Central Valley and 9.31 m in Southern California. These results emphasize the urgent need for tailored groundwater management strategies that address both declining and rising trends, while accounting for seasonal variability. Adaptive water management practices, which are flexible and responsive to changing conditions, will be crucial to safeguarding ecosystem integrity and sustaining agricultural productivity.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101409"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatiotemporal assessment of groundwater quality under climate change using multiscale clustering technique","authors":"Roghayeh Ghasempour ,&nbsp;V.S. Ozgur Kirca","doi":"10.1016/j.gsd.2025.101407","DOIUrl":"10.1016/j.gsd.2025.101407","url":null,"abstract":"<div><div>Assessing spatiotemporal variations of groundwater quality and identifying vulnerable areas is a crucial stage in the planning and management of water resources. This study focuses on utilizing a multiscale method to assess the water quality variables in the groundwater of Ardabil basin located in Iran. This plain is one of the important industrial and agricultural regions in Iran, and groundwater provides 89% of its total water demand. Therefore, investigating groundwater quality for this plain is indispensable. The monthly timescale datasets from 26 piezometers, covering the period of 2000–2022, were de-noised and decomposed using the Wavelet transform (WT) and Variational Mode Decomposition (VMD), respectively. The Permutation Entropy (PE) values of the subseries were computed and considered as inputs of the K-means method to zone and classify the basin in terms of the Total Dissolved Solids (TDS) and Electrical Conductivity (EC). The EC and TDS of central piezometers were predicted and the modeling uncertainty was investigated. From results, excessive use of groundwater resources resulted in a drop in groundwater levels even in rainy years. It was found that the integrated approach exhibited a desirable degree of reliability. Groundwater vulnerability assessment was done considering the hydrogeological parameters affecting groundwater pollution and using the DRASTIC approach. Nitrate values were used to validate the DRASTIC method. Matching the nitrate ion distribution map to the vulnerability map showed that the two maps corresponded, indicating that most of the points with high nitrate (21–42 mg/l) were located in areas with higher vulnerability potential (central parts).</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101407"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Probabilistic mapping of imbalanced data for groundwater contamination using classification algorithms: Performance and reliability","authors":"Yang Qiu ,&nbsp;Aiguo Zhou ,&nbsp;Hanxiang Xiong ,&nbsp;Defang Zhang ,&nbsp;Cheng Su ,&nbsp;Shizheng Zhou ,&nbsp;Lin Go ,&nbsp;Chi Yang ,&nbsp;Hao Cui ,&nbsp;Wei Fan ,&nbsp;Yao Yu ,&nbsp;Fawang Zhang ,&nbsp;Chuanming Ma","doi":"10.1016/j.gsd.2024.101393","DOIUrl":"10.1016/j.gsd.2024.101393","url":null,"abstract":"<div><div>The probabilistic mapping of groundwater contamination is a crucial foundation for sustainable groundwater management. However, groundwater data often exhibit imbalance, posing challenges for precise and reliable probability mapping. This study focused on the Jianghan Plain, evaluating the performance and reliability of various sampling and ensemble techniques using a small, imbalanced dataset (n = 246, Class0/Class1 = 0.84/0.16). Probabilistic maps revealed significant spatial variability, with high-probability areas concentrated in the western (Yichang City), eastern (Wuhan), and northern regions (north bank of Han River), while low-probability areas were in the central and southern regions. Over-sampling methods outperformed others by maintaining class balance and enhancing the reliability of mapping outcomes. The high-very high probability areas for over-sampling methods ranged from 15.5% to 18.9%, with larger very low-low areas (60.5%–66.3%). In contrast, under-sampling and ensemble methods showed larger high-very high probability areas (34.0%–53.1%) and smaller very low-low areas (21.6%–46.3%). Over-sampling methods exhibited higher F1 scores (0.27–0.33) and precision (0.375–0.43) compared to other methods. SHAP analysis demonstrated that over-sampling methods balance datasets while preserving information integrity, enhancing the credibility of mapping results. Conversely, ensemble methods faced challenges in statistical analysis, hindering interpretability. We strongly recommend, that in conducting probabilistic mapping of groundwater contamination, it is imperative to adequately consider the imbalance of datasets and not solely rely on metrics like AUC and OA. For small-size datasets akin to this study, SMOTE and ADASYN emerge as recommended sampling methods, they not only yield high-precision mapping results but also ensure interpretability, thereby providing a more reliable basis for sustainable groundwater management.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101393"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigating the role of ENSO in groundwater temporal variability across Abu Dhabi Emirate, United Arab Emirates using machine learning algorithms","authors":"Khaled Alghafli ,&nbsp;Xiaogang Shi ,&nbsp;William Sloan ,&nbsp;Awad M. Ali","doi":"10.1016/j.gsd.2024.101389","DOIUrl":"10.1016/j.gsd.2024.101389","url":null,"abstract":"<div><div>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 m 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.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101389"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Economic perspectives on groundwater conservation: Insights from farmers in western Uttar Pradesh, India","authors":"Akshi Bajaj ,&nbsp;S.P. Singh ,&nbsp;Diptimayee Nayak ,&nbsp;Ankit Nagar","doi":"10.1016/j.gsd.2025.101412","DOIUrl":"10.1016/j.gsd.2025.101412","url":null,"abstract":"<div><div>Groundwater management for irrigation is a critical area of research, particularly in developing economies like India where agriculture is heavily dependent on this resource. In India, groundwater is governed by the rule of capture, such that groundwater beneath an individual's land is treated as a private resource. This open-access nature leads to overexploitation and presents significant challenges for effective regulation. The present study seeks to assess the farmers' preferences for groundwater management alternatives and their marginal willingness to pay (MWTP) for sustaining the groundwater resources. Employing the contingent ranking method and rank-ordered logit model, the analysis is based on primary data from 300 farm households in Western Uttar Pradesh, India. Findings show that farmers prefer the groundwater management alternative of metered private tube wells, despite its higher cost, because their MWTP for this attribute is the highest. This suggests a strong preference for maintaining private rights to groundwater extraction while supporting sustainability through per-unit consumption charge. Farmers exhibit a significant MWTP of INR 1718 (USD 20.48) annually for the non-use benefits of groundwater. While this WTP may seem modest compared to the intrinsic value of groundwater's non-use benefits, it marks a critical step toward organised groundwater governance. Furthermore, farmer characteristics—such as education level and landholding size—significantly influence their preferences for various groundwater management attributes. These findings underscore the importance of policy interventions that incorporate economic incentives alongside conservation goals to address the ongoing groundwater depletion in agrarian economies like India.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"29 ","pages":"Article 101412"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sustainable restoration of low-quality groundwater through aquifer storage and recovery","authors":"Vahid Sobhi Gollo ,&nbsp;Bentley Bo Schmidt ,&nbsp;Carsten Hansen ,&nbsp;Nima Shokri","doi":"10.1016/j.gsd.2024.101396","DOIUrl":"10.1016/j.gsd.2024.101396","url":null,"abstract":"<div><div>The escalating challenges in urban water supply, driven by rapid urbanization, climate change, and water resources pollution, necessitate innovative solutions for sustainable water management. Urban areas frequently encounter spatial constraints for the installation of new production wells, thereby intensifying water scarcity. Shifting climate conditions lead to increased occurrences of extreme weather events, aggravating global water scarcity and impeding sustainable development, particularly impacting human health and exacerbating societal inequalities. To address this issue, our study explores the retrofitting of inactive production wells for aquifer storage and recovery (ASR) in low-quality aquifers, providing a systematic framework. The evaluation focuses on the suitability of inactive wells for ASR operations and utilizes the FEFLOW 8.1 groundwater model to assess the impact of hydrogeological conditions on ASR system recovery efficiency (RE). To validate this framework, we concentrate on the northwest region of the Hamburg metropolitan area, utilizing generalized hydrogeological conditions to yield universally applicable results. This region is characterized by high sulphate concentrations in groundwater, limiting the utility of production wells. Our findings demonstrate that ASR in a low-quality aquifer can constitute a viable strategy to address water scarcity. Under ideal aquifer conditions, ASR can achieve recovery efficiencies exceeding 100%. Our proposed framework emphasizes the necessity of a meticulous assessment of well design, considering construction materials and geological factors to prevent clogging. Key efficiency factors include the hydraulic gradient, injection and ambient concentrations, proximity to production wells, and dispersivity. Furthermore, ASR contributes to cost reduction by enhancing water management infrastructure and optimizing capacity utilization. This research provides a comprehensive perspective, offering valuable insights applicable to diverse locations grappling with water scarcity challenges.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101396"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unraveling two-dimensional modeling of multispecies reactive transport in porous media with variable dispersivity","authors":"Kumar Rishabh Gupta,&nbsp;Pramod Kumar Sharma","doi":"10.1016/j.gsd.2025.101404","DOIUrl":"10.1016/j.gsd.2025.101404","url":null,"abstract":"<div><div>The movement of reactive contaminants in subsurface has led to variations in groundwater quality, particularly near chemical and nuclear repositories because of the geochemical and hydrodynamic processes involved in porous media. This study deals with the two-dimensional numerical model to address multispecies transport through saturated porous media with steady-state flow conditions, considering advection, longitudinal and transverse dispersion with the first-order decay and the same is validated with the analytical solution. Focusing on four-species radionuclide decay, this study explores three dispersion models considering constant (ADC), linear (ADL) and exponential distance-dependent dispersivities (ADED) and their comparative analysis reveals the plume mobility emphasizing the role of dispersivity in shaping reactive solute transport by incorporating effective dispersivity. The results show that the concentrations of all radionuclides exhibit their peak values within the source area at time of 500 years, in which ²²⁶Ra has the largest plume and a discernible decrease of 12% and 20% is observed in the first moment for ADL and ADED as compared to ADC. Also, the relative plume size is in the order of ²²⁶Ra &gt; ²³⁸Pu &gt; ²³⁴U &gt; ²³⁰Th stipulating that the daughter species with largest plume may not necessarily dominate migration. Further, the spatial moments are used to encapsulate the sensitivity analysis, extending the applicability to simulate reactive transport scenarios. This study enhances the ability to predict and understand the long-term environmental perturbations by developing methodologies for modeling and forecasting the contaminants behavior that contributes to SDG-6 and SDG-13 through sustainable groundwater management.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101404"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of satellite-based water accounting plus (WA+) framework for estimating groundwater balance and utilization in a semi-arid river basin of India","authors":"Debrupa Chatterjee ,&nbsp;Pushpendra Kumar Singh ,&nbsp;Dharmaveer Singh ,&nbsp;Diganta Bhusan Das","doi":"10.1016/j.gsd.2024.101391","DOIUrl":"10.1016/j.gsd.2024.101391","url":null,"abstract":"<div><div>This study applied the satellite-based Water Accounting Plus (WA+) Framework wherein a WaterPix Model (pixel-based hydrological model) along with the Budyko hypothesis was used to account for the groundwater balance and utilization in the drought-prone Central Godavari River Basin (CGRB) of India as per the unique WA + based Land Use (WALU) classes. A reduction of 2.59 km³/year in the groundwater storage was observed during study period (2003–2020) despite the withdrawals of 8.88 km³/year against the total recharge of 13.4 km³/year, of which 12.22 km³/year was received from vertical recharge and 1.18 km³/year as the return flow (e.g., irrigation) to the groundwater. This may be attributed to the higher percentage contribution (∼54%) of the recharged groundwater to the baseflow. The higher baseflow contribution shows that surface water (SW)-groundwater (GW) interaction in the CGRB is high, and the ecological health of the basin is primarily sustained by the baseflow. The negative storage change in groundwater was also validated with the groundwater level data collected from 26 observational wells across the basin. Moreover, water demands (ET_Blue + ET_Green) were higher than the supplied water, resulting water scarcity in the CGRB for most of the districts. The consumptions from ET_Blue that is a measure of water consumption from irrigated crops suggests that the majority of water withdrawals (about 95%) originate from groundwater, revealing the basin's heavy reliance on this resource. Therefore, the marked ET_Blue hotspots (Nizamabad, Nirmal, Hingoli, parts of Nanded, Aurangabad, and Parbhani) are to be prioritised for reduced groundwater withdrawals and making ‘hotspots’ to the ‘bright spots’. The farmers of the ET_Blue hotspots regions should adopt less water-requiring crops (through crop diversification), such as millets and other coarse cereals to reduce water use in agriculture. Finally, the reliable quantification of groundwater supply and consumption using the WA + Framework can assist in groundwater resources management of a data sparse region.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101391"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Groundwater level forecasting using empirical mode decomposition and wavelet-based long short-term memory (LSTM) neural networks","authors":"Amirhossein Nazari ,&nbsp;Moein Jamshidi ,&nbsp;Abbas Roozbahani ,&nbsp;Behzad Golparvar","doi":"10.1016/j.gsd.2024.101397","DOIUrl":"10.1016/j.gsd.2024.101397","url":null,"abstract":"<div><div>Groundwater is a vital resource for multiple sectors, but over-extraction has led to significant declines in groundwater levels across many regions. Accurately forecasting groundwater levels is essential for effective planning and management. However, the presence of non-stationarity in groundwater time series, such as trends and fluctuations, can result in poor prediction performance. This study proposes a novel hybrid approach combining Long Short-Term Memory (LSTM) models with Empirical Mode Decomposition (EMD) and Wavelet Transform (WT) to address these challenges. Non-stationary data from three wells in San Bernardino County, California, collected over a five-year period (2017–2022), were used for training and testing the models. The time-series data were preprocessed using EMD and WT to break down complex patterns into simpler components, which were then fed into LSTM models to improve forecasting accuracy. Our results show that the EMD-LSTM model significantly outperforms both the Wavelet-LSTM and traditional Single LSTM models when the error is rooted in a trend factor. According to the Root Mean Squared Error (RMSE) index, The EMD-LSTM reduced forecasting errors by up to 19% and 78% for wells W0804 and W0904, respectively. In contrast, for the well 4905, WT and EMD were not able to increase LSTM accuracy when fluctuations happened randomly. These findings demonstrate that the EMD-LSTM model is a powerful tool for forecasting groundwater levels, especially in cases where non-stationarity is prevalent. This approach can be applied to enhance groundwater management strategies, helping decision-makers ensure sustainable water resource planning, particularly in regions facing unsustainable groundwater withdrawals.</div></div>","PeriodicalId":37879,"journal":{"name":"Groundwater for Sustainable Development","volume":"28 ","pages":"Article 101397"},"PeriodicalIF":4.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}