Search Results (457)

Machine learning (ML) has evolved into an indispensable tool for uncovering hidden patterns and deducing correlations. Currently, ML is having a profound impact on the field of groundwater resources and environment research by enhancing predictive accuracy and optimizing management strategies. In this study, we conducted a bibliometric review using CiteSpace and a global-scale analysis of ML methods applied to groundwater resources and quality based on 1326 records. The findings suggest that ML applications in groundwater resources and water environment research are still in their infancy compared with other environmental science fields. This paper then provides a systematic summary of the specific applications of machine learning methodologies within groundwater research, focusing primarily on the prediction of groundwater levels and water quality, along with the extraction of feature importance. Furthermore, a comparison was made of the pros and cons of several prevalent ML techniques used in groundwater level and water quality studies, with an emphasis on the significance of aligning data with models during the application of ML. Finally, the challenges encountered by ML tools in groundwater research were addressed, along with opportunities for the future. The significant potential of employing ML methodologies in groundwater is proposed to make the invisible visible. Full article

Groundwater storage is vital for managing water resources, especially as global water scarcity intensifies. Estimating groundwater levels regionally is challenging due to natural heterogeneity. We employed a large groundwater observation sample, along with Global Land Data Assimilation System (GLDAS) and Gravity Recovery and Climate Experiments (GRACE) datasets, to develop a random forest model for predicting groundwater levels in China’s Yellow River Basin. The model showed robustness, achieving an R² of 0.95 in calibration and an R² of 0.91 ± 0.009 in 10-fold cross-validation with 100 repetitions. Temporal predictability was lower, with an R² of 0.72 for April–May 2023; however, the temporal prediction is preliminary and limited by the short validation period (April–May 2023), which should be interpreted with caution. Spatial maps revealed significant seasonal declines in fall and winter, particularly in the middle and lower reaches. This study highlights the potential of machine learning with extensive observations to estimate regional groundwater levels and supports groundwater analysis with robust data. Full article

Numerical simulations quantify the transient impacts of implementing green infrastructure (GI) grass swales on unconfined aquifer storage and groundwater-surface water interactions around the Red Butte Creek (RBC) of Utah, USA. The Red Butte Creek Watershed (RBCW) transitions from undeveloped mountainous National Forest land to downstream urbanized areas within Salt Lake Valley (SLV). This reconnaissance-level study demonstrates that increasing stormwater infiltration in urbanized areas during the rainy months (April-June) can, until at least the subsequent March, (a) enhance aquifer recharge and support sustainable groundwater yields; and (b) improve surface water availability. Simulations predict hydrologic impacts of aquifer recharge resulting from hypothetical grass-swale implementation within a 704-acre area located around RBC. The employed model, HyperRBC, is an adaptation of a United States Geological Survey (USGS) transient numerical flow, MODFLOW, model implementation for SLV. Adaptations involved (a) uniformly refined horizontal discretization of seven aquifer layers within a sub-area encompassing parts of RBCW and an adjacent watershed; (b) updated input data; and (c) MODFLOW’s Streamflow-Routing (SFR) package to simulate RBC flow and aquifer-stream seepage. Model predictions indicated that by the end of next March: (a) about 3% of the GI-induced recharge would remain within the unconfined aquifer in the HyperRBC area; (b) 66.6% of the recharge would flow northward into the downgradient continuation of the unconfined aquifer; and (c) 30.3% would discharge to nearby stream and river. In summary, predicted hydrologic changes due to the short-term GI-induced recharge highlight increased groundwater availability within and outside the study area for at least the subsequent 12 months, including high-water-demand summer. These findings show the importance of GI in interim environmental management and in enhancing the effective use of water resources. Full article

River Basin Management Plans (RBMPs) developed under the EU Water Framework Directive (WFD) assume stable monitoring, institutional continuity, and predictable implementation capacity—conditions that are undermined by war-driven uncertainty. This study assesses the feasibility of delivering the 2025–2030 RBMP in the Ukrainian Tisza sub-basin using a combined approach that integrates structured document analysis, a measure-level dataset derived from the Programme of Measures annexes, and a feasibility-screening framework linking expected environmental contribution, implementation dependency, and evidence readiness. The empirical basis covers 120 planned measures in a transboundary sub-basin with a large and heterogeneous surface-water portfolio. While surface-water monitoring remained operational in 2023, groundwater evidence was critically constrained because monitoring had been discontinued since 2018, and groundwater status and risk assessments had not been completed by the end of 2023. The analysis identifies a compliance-critical subset of high-contribution, high-dependency measures, particularly capital-intensive wastewater, monitoring, and groundwater-related interventions, whose implementation and verification are most vulnerable to wartime disruption. The study proposes an evidence-gap closure sequence and a verification-ready prioritisation logic for the 2025–2030 cycle, offering a transferable framework for stress-testing RBMP delivery in transboundary basins under high uncertainty. Full article

Sustainable groundwater management in regions subjected to intensive agricultural pressure requires reliable simulation tools capable of anticipating the impacts of climate change. However, in overexploited multilayer aquifers such as Tierra del Vino, locally calibrated predictive tools capable of quantifying climate-driven piezometric decline remain scarce. This study develops a numerical groundwater flow model using MODFLOW for the Tierra del Vino aquifer (Spain), a multilayer detrital system currently characterized by a critical quantitative status. Agricultural irrigation accounts for approximately 94% of total groundwater withdrawals, making it the dominant anthropogenic pressure on the system. The model was manually calibrated through more than 500 iterations, achieving a consistent representation of groundwater dynamics. Statistical evaluation based on groundwater level data from 34 piezometric monitoring points distributed across the aquifer yielded a good fit (NSE = 0.816; R = 0.928), supporting the suitability of the model for scenario analysis. Under the RCP 8.5 climate scenario, aquifer recharge could decrease by 31.75%, resulting in a significant piezometric decline within the system. At the representative well selected for the farm-scale agricultural impact analysis, this decline reaches 3.33 m and is used to evaluate its effect on pumping energy costs. The implementation of management measures proposed by the water authority reduces this decline to 1.84 m, although overexploitation conditions persist. These results indicate that current administrative restrictions are insufficient on their own and that future management should adjust abstraction rights to projected recharge conditions, maintaining the exploitation index below 0.8 to reduce the risk of long-term overexploitation. In this context, aquifer resilience is interpreted as the capacity of the groundwater system to respond to the combined pressures of climate change and agricultural abstraction while maintaining its hydrological functioning. Full article

Groundwater systems in semi-arid and industrial regions are increasingly affected by climate-driven non-stationarity and anthropogenic pressure, challenging conventional forecasting approaches. This study develops and evaluates an integrated artificial intelligence framework designed to minimize piezometric head residual dispersion under non-stationary hydroclimatic conditions. The proposed methodology combines Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Variational Mode Decomposition (VMD) with a Slime Mould Algorithm–optimized Long Short-Term Memory (SMA–LSTM) model and a CNN–LSTM architecture, which are dynamically fused using an Adaptive Weighting Model (AWM). The framework was applied to long-term groundwater level (1994–2024), groundwater quality (2017–2023), and meteorological datasets to evaluate the predictive robustness across climatic variability regimes. The proposed ensemble achieved a mean absolute error of 0.267 m, root mean square error of 0.429 m, coefficient of determination (R²) of 0.948, and Nash–Sutcliffe efficiency of 0.938, representing substantial residual reduction compared to baseline deep learning models. Residual diagnostics confirmed minimized peak deviations and stable performance under non-stationary conditions. Scenario-based simulations driven by CMIP6 climate projections indicate increasing groundwater stress under future warming trajectories, with amplified variability and declining recharge signals. These findings demonstrate that multi-stage signal decomposition coupled with metaheuristic optimization and adaptive ensemble learning significantly enhances predictive stability and residual minimization in climate-sensitive aquifer systems. The proposed framework provides a transferable, climate-resilient decision-support tool for sustainable groundwater management in industrial and semi-arid regions. Full article

Flotation tailings, the primary solid waste generated during gold extraction, may pose issues such as land occupation, environmental pollution, and geological hazards in open-pit mining areas. This study systematically investigated the environmental characteristics, long-term pollutant release patterns, and migration risks associated with flotation tailings by taking a specific backfill project as a case study and employing short-term leaching tests, long-term column leaching experiments, and multi-model numerical simulations. Short-term leaching tests indicated that tailings leachate exhibited weak alkalinity (pH 8.21−8.45) with low pollutant leaching concentrations, meeting the fundamental requirements for open-pit backfilling. Notably, leaching characteristics varied significantly among tailings from different sources, and an extended storage duration enhanced chemical stability. Long-term leaching tests identified nine characteristic pollutants, including fluoride and sulfate, with their release patterns categorized into three types: continuous slow release, initial rapid leaching, and delayed/complex release. Furthermore, simulation results from the HYDRUS and MODFLOW/MT3DMS models indicated that the maximum predicted concentrations of characteristic pollutants in the surrounding soil and groundwater will remain at low levels for 50 years post-backfilling. The site’s “micro-to-weakly permeable” strata exhibited significant pollutant retention capabilities. Based on these experimental and simulation results, a three-tier risk management system—”source control, process monitoring, and end-point surveillance”, was developed to provide technical support for the long-term environmental safety of the flotation tailings backfill project. This study revealed the environmental risk characteristics associated with the storage of flotation tailings, including land occupation, environmental pollution, and the potential for geological hazards in open pits. Furthermore, the leaching characteristics, long-term release patterns, and migration mechanisms of tailings used to backfill open pits have been elucidated, providing theoretical references and practical guidance for similar solid waste resource recovery and backfilling projects. Full article

Groundwater level prediction is essential for sustainable water resource management. Although machine learning models are widely applied, input variable selection critically affects predictive performance, and existing studies rarely evaluate model performance comprehensively, considering accuracy, stability, physical interpretability, and computational efficiency. To address this issue, this study develops a hybrid framework integrating grid search-optimized long short-term memory (GS-LSTM) with the technique for order preference by similarity to ideal solution (TOPSIS). Using the Houston area as a case study, the framework evaluates 30 input combinations derived from precipitation (P), air temperature (T), relative humidity (H), wind speed (W), and reference evapotranspiration (E) across 22 monitoring wells to identify optimal and minimal input variable combinations sets. Key findings include: (1) optimal input combinations vary substantially among wells, highlighting spatial heterogeneity; (2) P and E are dominant drivers; (3) compared to daily input data, monthly averaged data increases the prediction success rate (proportion of successful runs across 27 hyperparameter configurations) by >40% and improves R² by >0.3; (4) the minimal set comprises eight representative combinations that collectively cover the top-three ranked variable combinations for all 22 wells, maintaining high accuracy (e.g., Well 12# daily data: MAE = 0.13 m, RMSE = 0.16 m, R² = 0.92) while reducing computational cost by 92.1% relative to testing all 30 combinations. The proposed optimal and minimal input sets offer a stable, accurate, and computationally efficient solution for groundwater resource management that accounts for spatial heterogeneity. Full article

Landslides are a critical environmental hazard in mountainous regions like eastern Uganda, posing serious threats to lives, infrastructure, and ecosystems. While recent advances in geospatial technology have improved hazard assessment, existing research often lacks high-resolution, cloud-based analysis for dynamic landscapes such as the Mount Elgon region. This study addresses that gap by developing a landslide susceptibility map (LSM) using Google Earth Engine (GEE), which integrates remote sensing and geospatial data for scalable analysis. The main objective is to identify landslide-prone zones by analyzing eight conditioning factors, namely slope, elevation, vegetation cover, rainfall, land use land cover, soil type, soil moisture, and groundwater levels using the weighted overlay method (WOM). The methodology produced a classified LSM with zones of high (37.7%), moderate (58%), low (2%), and very low (2.3%) susceptibility, with validation via historical landslide data and ROC analysis yielding an AUC of 0.76, confirming strong predictive performance. The study underscores the value of GEE in hazard modeling and provides actionable insights for targeted risk mitigation, sustainable land use planning, and early warning system development in landslide-prone areas. Full article

Land subsidence (LS) is a widespread geoenvironmental problem driven by both natural processes and human activities. Identifying the main factors controlling LS susceptibility and their spatial contribution patterns is essential for LS management and mitigation. In this study, an interpretable earth observation framework was developed for the North China Plain (NCP) to quantify both spatial and non-spatial contributions of dominant LS drivers. Land displacement was derived from Sentinel-1A SAR images using Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) processing. The displacement map was then combined with nine geoenvironmental variables to construct an LS susceptibility model using the eXtreme Gradient-Boosting (XGBoost) algorithm. The model performed well, with an R² of 0.96, an EVS of 0.96, and an MAE of 2.25 mm/yr. SHapley Additive exPlanations (SHAP) analysis was employed to quantify feature contributions and their effects on LS susceptibility. The results show that a deep groundwater level (DGL) was the dominant factor, followed by elevation and a shallow groundwater level (SGL). The effect of DGL was strongest when it ranged from −75 to 20 m. Elevation showed a clear effect on LS occurrence when values fall between 30 and 50 m. Relatively high subsidence sensitivity was mainly observed in areas where SGL was below −7 m. Interaction effects, particularly those between DGL and elevation and between DGL and SGL, further increased LS susceptibility in specific areas. The highest predicted susceptibility occurred in areas with DGL below −20 m and elevations below 30 m. Higher susceptibility was also identified where DGL was high and SGL ranged between −20 and −10 m, and where DGL was low and SGL ranged from 15 to 20 m. In contrast, factors such as slope and aspect had limited influence at the regional scale. The contributions of the predominant factors show obvious marginal effects and significant spatial heterogeneity to LS susceptibility. The results clarify where and how key factors shape subsidence and can inform targeted mitigation measures and urban planning by local authorities. Full article

Groundwater drainage-induced karst collapse is a major geohazard in coal-mining regions of central Hunan, threatening residential safety and infrastructure. This study focuses on the Tuoshan minefield in the Jinzhushan mining area by integrating multi-source field data, including surveys of 170 collapse points, long-term groundwater monitoring at six boreholes, and high-density electrical geophysics. A topographically corrected MODFLOW seepage-field model is developed and calibrated for 2014 (RMSE = 0.32 m; NSE = 0.85) and validated for 2015–2016 (RMSE = 0.41 m; NSE = 0.81). To address the large groundwater-level simulation errors commonly encountered in subtropical hilly karst mining settings, the model incorporates a topographic correction, improving simulation accuracy by 12% relative to an uncorrected model. The simulations capture rapid “steep rise–slow fall” groundwater dynamics: Heavy rainfall (>100 mm/day) raises groundwater levels by 2.8–3.1 m within 2–3 days, whereas pumping (200 m³/h) causes a 1.9–2.2 m decline within one week. A 1.2 km drawdown funnel forms and overlaps with 89% of collapse points, indicating that seepage-field evolution and groundwater-level decline control collapse clustering, with soil suffusion and soil–water–rock interaction acting as key amplifying processes. Based on Terzaghi’s effective stress principle and the Theis solution, a collapse prediction formula is derived and validated using measured events (accuracy = 87.5%), and a region-specific critical hydraulic gradient (i_n = 0.85) is determined, lower than values reported for North China. The proposed workflow provides quantitative thresholds and model-based guidance for karst collapse prevention in subtropical mining areas. Full article

Karst aquifers present unique challenges for groundwater level prediction due to their dual-porosity structures and highly nonlinear hydrological responses. This study systematically evaluates nine machine learning and deep learning models (RF, XGBoost, LSTM, CNN, Transformer, N-BEATS, CNN-LSTM, Seq2Seq-LSTM, and Attention-Seq2Seq-LSTM) for rainfall-driven groundwater level forecasting in the Maocun subterranean river catchment, Guilin, Guangxi, China. Two years of hourly high-frequency data from three monitoring sites representing distinct hydrogeological zones (recharge, flow, and discharge) were employed within a multidimensional evaluation framework integrating single-step accuracy, multi-step stability, and computational efficiency. Results indicate that the Transformer achieved the highest single-step prediction accuracy, attaining the lowest RMSE (0.130–0.606 m) and highest R² (0.813–0.965) across all three sites. CNN-LSTM offered the best balance between predictive performance and computational cost, requiring an average training time of only 27.97 s and 28.0 convergence epochs. N-BEATS demonstrated superior long-term stability in 12-steps-ahead forecasting, achieving R² = 0.914 at ZK1, outperforming all other architectures. More fundamentally, hydrogeological complexity exerted a dominant control on predictive skill that systematically outweighed differences arising from model architecture. All models yielded R² below 0.813 at the geologically complex ZK2 site, whereas R² exceeded 0.950 across all models at ZK1, indicating that aquifer complexity, rather than algorithm selection, constitutes the primary constraint on prediction feasibility. This study presents the first application of N-BEATS to karst groundwater level forecasting and proposes a replicable multidimensional evaluation framework, providing a scientific reference for intelligent modelling of complex karst systems. Full article

Hydrodynamically triggered landslides remain a major concern in reservoir regions, where the mechanisms controlling displacement evolution are still not fully understood and the multi-scale deformation responses induced by individual hydrodynamic factors remain difficult to quantify. To address these issues, this study establishes a TSD-TET composite framework by integrating time-series signal decomposition with deep learning for multi-scale displacement prediction and the mechanism-oriented interpretation of hydrodynamically triggered landslides. The monitored displacement sequence is first decomposed into physically interpretable components, including trend, periodic, and random terms. Each component is subsequently predicted using deep temporal learning models to capture different deformation characteristics at multiple temporal scales. Meanwhile, key hydrodynamic driving factors, including rainfall, reservoir water level, and groundwater level, are decomposed within the same framework to examine their statistical associations with different displacement components. The proposed approach is applied to the Donglingxin landslide located in the Sanbanxi Hydropower Station reservoir area. Results show that the model achieves high prediction accuracy under both long-term forecasting horizons and limited-sample conditions, with a cumulative displacement coefficient of determination reaching R² = 0.945. Mechanism analysis further indicates that trend deformation is mainly controlled by geological structure and gravitational loading, periodic deformation is strongly modulated by hydrological cycles associated with reservoir water level fluctuations, and random deformation is more likely to reflect short-term disturbances and transient hydrodynamic forcing. These findings provide new insights into the deformation mechanisms of hydrodynamically triggered landslides and offer a promising technical pathway for improving displacement prediction, monitoring, and early warning of reservoir-induced landslide hazards. Full article

Over six decades, satellite remote sensing of water resources has evolved from manual interpretation of weather photographs to AI systems that learn hydrologic predictions directly from satellite imagery. This review traces that evolution through the observation-to-inference arc—a framework for the progressively tightening coupling between what satellites observe and what hydrologists infer. Using illustrative applications in precipitation, evapotranspiration, soil moisture, snow, surface water, and groundwater, we show how early observations (1960–1985) remained disconnected from operational hydrology; how calibrated retrieval algorithms (1985–2000) established a one-way pipeline from satellites to models; how operational infrastructure (2000–2015), anchored by MODIS, GRACE, GPM, and Sentinel, achieved assimilative coupling through computational feedback between models and observations; and how deep learning (2015–present) is beginning to collapse this pipeline. Multi-source data fusion has been a recurring enabler at each stage. We articulate a four-level AI vision and research trajectory, from AI-assisted interpretation through AI-native retrieval and AI-driven inference to autonomous Earth observation intelligence. Persistent challenges in mission continuity, calibration, equity of access, and translating satellite-derived information into operational water management decisions provide essential context for evaluating both the promise and limits of this trajectory. Full article

In the ecologically fragile West Liao River Basin, characterizing groundwater dynamics is crucial for sustainable water management. Using 2000–2016 groundwater level data, this study applies Seasonal-Trend decomposition using Loess (STL) and change-point detection to analyse trends. Driving factors are quantified via random forest combined with SHapley Additive exPlanations (SHAP) analysis, and a novel STL–Long Short-Term Memory (STL-LSTM) hybrid model is developed for forecasting. Key findings include: (1) Groundwater levels declined persistently, with a significant change point in 2009. The post-2009 decline rate accelerated to −0.749 m/yr, a 55.7% increase. (2) Statistical attribution reveals that soil moisture (43.5%) and climatic factors (29.0%) are the primary predictors of groundwater variability. The dominance of soil moisture highlights the key role of agricultural irrigation, which strongly modifies soil water dynamics during the growing season. (3) The STL-LSTM model achieves optimal predictive performance (R² = 0.8805, RMSE = 0.7081 m), demonstrating enhanced accuracy for non-stationary sequences. This integrated framework combines trend diagnosis, driver interpretation, and hybrid modelling, offering scientific support for precise groundwater management in semi-arid agricultural basins. Full article