Using spatially explicit machine learning to enhance assessment of the Global Gravity-based Groundwater Product for groundwater storage change in Germany

This study focuses on the Lower Rio Grande (LRG) region of Southern New Mexico, a semi-arid area facing significant water scarcity challenges. Groundwater serves as a critical resource for agriculture, domestic use, and industry in the region, necessitating robust management and predictive tools. The research develops a novel groundwater modeling approach by integrating System Dynamics (SD) and Machine Learning (ML) techniques. A validated SD model of the LRG provided simulation data, which was used to train an ML model employing a feedforward Multilayer Perceptron (MLP) as an artificial neural network (ANN) technique. This approach simplifies groundwater dynamics by concentrating on key variables identified through correlation analysis and simulation results. The model achieved a training RMSLE of 0.031 and R-squared of 0.77, with testing results showing RMSLE of 0.036 and R-squared of 0.71, demonstrating predictive reliability. The proposed model enables accurate forecasting of groundwater storage changes while reducing reliance on extensive data inputs. It pioneers using SD simulation data as a data augmentation method for MLP model training, enhancing predictive capabilities. This integrated methodology supports informed groundwater management and policy-making, offering a transferable framework for other hydrologically similar regions. • Introduces a hybrid System Dynamics–Deep Learning framework for groundwater forecasting. • Transfers socio-hydrological feedbacks from a validated SD model into a reduced-variable ANN. • Uses SD simulations as structured synthetic data to train deep learning under data scarcity. • Enables groundwater storage prediction without reliance on full SD or physical model execution. • Provides a deployable decision-support tool for regional groundwater management and policy.

Groundwater storage depletion and contamination trade-offs under contrasting irrigation practices in drought-stressed Morocco

Groundwater is a vital component of the hydrological cycle, and understanding its dynamics is crucial for water resource management under climate change. This study employs GRACE-FO satellite data to assess groundwater storage (GWS) dynamics in Hunan Province during the 2024 flood season (April-September). Given the abundant surface water resources in this region, we explicitly incorporate the water storage of Dongting Lake and 28 large reservoirs when calculating surface water storage anomaly (SWSA), which is crucial for estimating the GWS anomaly (GWSA). Accordingly, GWSA is obtained by subtracting the soil moisture storage anomaly (SMSA) and SWSA from the GRACE-FO-derived terrestrial water storage anomaly (TWSA). Furthermore, correlation coefficients and contribution of each water storage component to TWSA are calculated to reveal inter-component interactions and response mechanisms to precipitation. Results show that original TWSA, SWSA, and GWSA increase markedly from March to July 2024. After detrending and deseasonalizing, SWSA and GWSA exhibit a complementary relationship (correlation coefficient: -0.20), with changes of -3.08 km3 and -1.12 km3 over the flood season, largely attributed to anthropogenic flood control operations. In contrast, SMSA and GWSA are weakly positively correlated (0.29), reflecting limited direct recharge efficiency. TWSA is strongly correlated with both SMSA (0.78) and GWSA (0.71), reflecting synergistic variation among water storage components. Consistently, GWSA contributes the most (44.52%) to TWSA fluctuations, followed by SMSA (31.80%) and SWSA (23.68%), highlighting the critical role of groundwater in the regional water cycle. These findings provide a valuable scientific basis for sustainable water resource management and regulation in Hunan Province.

ABSTRACT Water scarcity in Iraq’s Tigris–Euphrates basin is intensifying under climate change, upstream regulation, and increasing demand, creating pressure on groundwater and surface water sustainability. This study develops an integrated framework that merges Gravity Recovery and Climate Experiment groundwater anomalies, Global Land Data Assimilation System soil moisture fields, Moderate Resolution Imaging Spectroradiometer evapotranspiration, hydrometric observations, and machine learning to quantify groundwater–surfacewater exchanges. An extreme gradient boosting model predicts groundwater levels with R2 of 0.92 and root mean square error of 0.15 m. Results indicate groundwater storage declines ranging from −1.4 cm year−1 in the north to −0.9 cm year−1 in the south during 2002–2023, with seasonal deficits amplifying depletion. Exchange flux analysis reveals groundwater discharge sustaining rivers during droughts and flood-induced recharge during high flows. Scenario projections to 2050 show moderated depletion under RCP4.5 but accelerated decline under RCP8.5, emphasizing the need for adaptive abstraction control and managed recharge strategies.

ABSTRACT Groundwater is a vital component of the global water cycle and plays a critical role in ecological security and sustainable development. Groundwater storage anomalies (GWSA) are jointly driven by climate change and human activities. However, existing studies on GWSA mainly rely on the quantitative characteristics of explanatory variables, while the investigation of spatial data patterns remains limited despite their increasing importance. This study develops a geocomplexity-heterogeneity model to identify spatial drivers of GWSA by integrating spatially local complexity with robust stratified heterogeneity. The geocomplexity-heterogeneity model was used to identify both national-scale patterns of GWSA and the dominant climatic and anthropogenic explanatory factors in two representative regions, including the Huang-Huai-Hai Plain and the southeastern Tibetan Plateau, over the period 2002–2022. The results indicate that national GWSA in China decreased at a rate of 1.89 mm yr−1 during 2002–2022. The most significant decline occurred in the Huang-Huai-Hai Plain (10.68 mm yr−1), while the Sichuan Basin and surrounding regions showed moderate recovery. In the Huang-Huai-Hai Plain, GWSA variability reflects the combined effects of climatic water processes and intensive human water use, with temperature playing a leading role and irrigation exerting a strong influence primarily through its interaction with climatic conditions. In contrast, GWSA in the southeastern Tibetan Plateau was primarily shaped by natural climate processes, particularly precipitation and vegetation dynamics. The geocomplexity-heterogeneity model enhances the spatial interpretation of GWSA by combining local complexity with stratified heterogeneity, thereby improving the robustness of region-specific driver identification.

The present study focuses on a comprehensive stream hydrography analysis of the Thoppaiyar sub-basin, a significant tributary system of the Cauvery basin located in Tamil Nadu, India. The analysis integrates morphometric evaluation, hydrograph interpretation, and geospatial techniques to assess the hydrological behavior of the basin for sustainable development. The basin is characterized by dendritic to sub-dendritic drainage patterns developed over Precambrian crystalline formations, indicating minimal structural disturbance and relatively homogeneous lithology. Quantitative morphometric parameters such as stream order, drainage density, bifurcation ratio, elongation ratio, and relief characteristics were derived using GIS and remote sensing data, particularly Digital Elevation Models (DEM). Hydrograph analysis reveals that the basin exhibits a rapid hydrological response to rainfall, with a steep rising limb, short lag time, and high peak discharge, suggesting low infiltration capacity and significant surface runoff. The recession limb is relatively steep, indicating limited groundwater storage and baseflow contribution. These characteristics reflect the semi-arid climatic conditions, sparse vegetation cover, and soil properties of the basin. Spatial analysis of slope, land use/land cover, and drainage distribution further highlights areas prone to soil erosion, runoff concentration, and water scarcity. The study emphasizes the importance of integrating hydrography with watershed management practices such as artificial recharge structures, check dams, afforestation, and sustainable land use planning. The delineation of micro-watersheds enables prioritization of critical zones for intervention. The results demonstrate that scientific hydrography analysis can significantly contribute to sustainable basin development by improving water resource management, minimizing flood risks, enhancing groundwater recharge, and maintaining ecological balance. This research provides a valuable framework for regional planning and can be applied to similar semi-arid basins across India.

Surface water extent (SWE) is a key indicator of the regional water balance in dryland environments. However, the hydrological processes regulating SWE responses remain poorly constrained. Focusing on the Mu Us Sandy Land (MUSL), this study integrates multi-source remote sensing and hydrological datasets to investigate the long-term evolution of SWE and, critically, to distinguish the hydrological linkages between SWE dynamics and water storage variability in endorheic and exorheic regions during 1987–2024. An improved water extraction method was implemented on the Google Earth Engine platform, and SWE dynamics were interpreted within a water-balance framework supported by attribution analysis using machine learning. The results show that total SWE exhibited a significant increasing trend (7.95 km2 yr−1, p < 0.05) during 1987–2024, primarily driven by permanent SWE, while fundamentally different hydrological regimes governed SWE evolution. In the endorheic basin, SWE exhibited strong co-variation with subsurface water storage, with soil moisture and groundwater storage changes occurring concurrently with SWE changes. In contrast, no synchronous increase in SWE with groundwater storage was observed in the exorheic region. Instead, SWE expansion was mainly associated with accelerated groundwater storage depletion and reservoir construction. These contrasting patterns indicated that SWE dynamics in the endorheic basin were primarily controlled by subsurface water storage, whereas in exorheic regions they were largely driven by human-induced water redistribution rather than increases in total water storage. These findings highlight the importance of integrated surface–subsurface water management for sustaining long-term water security under climate change and increasing human water regulation.

According to the European Drought Observatory, more than 30% of Europe has been under drought warning conditions since 2018. This situation is primarily attributed to a persistent decline in groundwater resources. Satellite observations confirm that groundwater levels have not been recovering; in some regions, they continue to decrease. Data from the Global Gravity-based Groundwater Product (G3P) project, which employs satellite gravimetric measurements, enable continuous monitoring of groundwater variations and provide a globally consistent map of gravity field changes, directly converted into terrestrial water storage variations, of which groundwater is a key component. This study aims to estimate groundwater storage using models from the Global Gravity-based Groundwater Product derived from the Gravity Recovery and Climate Experiment (GRACE) mission. Based on the estimated groundwater storage, the Groundwater Drought Index (GDI) was calculated for climatically homogeneous regions in Europe, as defined by the Köppen–Geiger climate classification. To enhance the analysis of temporal GDI variations, the index time series was decomposed using the Fourier transform, allowing for the identification of dominant periodic components and long-term trends. Time series decomposition revealed a strong seasonal dependence of groundwater. The highest levels are observed in spring and the lowest in autumn. A positive trend of groundwater resources was found for Scandinavia region (0.0006 cm). In other areas, a decline in groundwater resources is noticeable since 2016, with the biggest decline in areas of Central and Eastern Europe (-0.0011 cm) and Balkan Peninsula (0.0006 cm).

Water is a vital resource whose availability is increasingly uneven due to climate variability, land-use changes, and rising water demand. This condition leads to water surplus during the rainy season and deficit during the dry season, including in the Prumpung Watershed, Tuban Regency. This study aims to analyze the monthly and annual water balance and evaluate the relationship between water availability and water demand in the study area. A descriptive quantitative approach was employed using the Thornthwaite–Mather method, based on rainfall and air temperature data from 2015 to 2024, combined with domestic and non-domestic water demand data for 2024. The results indicate that potential evapotranspiration fluctuates in accordance with air temperature, while actual evapotranspiration is influenced by groundwater availability. Groundwater storage increases during the rainy season and decreases during the dry season. The annual water balance reveals a dominance of deficit conditions in most observation years, although surplus occurs during certain periods. The Prumpung Watershed is vulnerable to water deficits due to uneven rainfall distribution. Sustainable water resource management strategies, focusing on conservation, are required to maintain a long-term hydrological balance.

Over the past decade, the tourism sector in the karst region of Gunung Kidul has experienced substantial growth, contributing significantly to local revenue generation and expanding employment opportunities for surrounding communities. Nevertheless, the rapid development of tourism infrastructure, land-use conversion, and intensive exploitation of karst landscapes have generated constitutional concerns related to the State’s obligation to safeguard environmental sustainability. Karst ecosystems perform essential ecological functions, including groundwater storage, hydrological regulation, and providing habitats for diverse biological species. Consequently, environmental degradation in these areas may result in long-term ecological consequences. This study aims to examine the tension between tourism-driven economic development and the protection of karst environments from the perspective of Article 33 of the 1945 Constitution of the Republic of Indonesia, as well as the principles of sustainable development. The research employs a socio-legal approach, combining normative analysis of statutory regulations with conceptual examination of the green constitution doctrine and sustainable development framework. The findings indicate that Article 33 of the 1945 Constitution not only emphasizes state control over natural resources for the prosperity of the people but also implicitly incorporates principles of environmental sustainability and ecological responsibility. Accordingly, tourism policies that disregard environmental carrying capacity and ecological limits within karst regions risk contradicting constitutional mandates. The integration of sustainable development principles into spatial planning policies and licensing mechanisms is therefore essential to ensure a balanced relationship between economic advancement and environmental preservation.

Application of hydro-economic modelling to river basin development planning and management in Nepal

Numerical simulation of the protection perimeters of groundwater catchment structures in crystalline bedrock environment: Case of the Babo watershed (Central-Western Côte d′Ivoire)

Abstract Understanding groundwater recharge pathways is essential for designing effective managed aquifer strategies, yet in heterogeneous alluvial aquifers, these pathways are often uncertain and difficult to resolve with sparse well networks. We apply gravity as an independent constraint to quantify groundwater storage dynamics and evaluate recharge strategies in the Ailiao River basin of southern Taiwan. Seven super‐hybrid gravity surveys, integrating absolute, relative, and superconducting gravimeters, were conducted between November 2023 and July 2025 under contrasting hydrological conditions. The surveys revealed distinct seasonal and spatial variability, with recharge driven primarily by rainfall and locally enhanced by river infiltration during wet periods. Stations within 1 km of the river recorded gravity increases up to 100 μGal, while sites beyond 3 km showed minimal (<10 μGal) or delayed responses, delineating a recharge front that attenuates with distance. Comparisons with groundwater levels demonstrated that thick unsaturated zones filter and delay recharge, complicating direct estimation of specific yield. In‐channel modifications provided localized, short‐term recharge but were constrained by unsaturated sediments, whereas stations near proposed recharge‐lake sites recorded stronger and more sustained wet‐season gains, suggesting that recharge lakes offer greater potential for long‐term aquifer replenishment. The super‐hybrid framework maintained referencing continuity despite instrument downtime and typhoon‐related damage, achieving precisions of 3–8 μGal. Beyond operational robustness, our results underscore the value of gravimetry as a non‐invasive complement to well monitoring, capable of constraining recharge fronts, aquifer heterogeneity, and the performance of managed aquifer strategies. These findings provide practical guidance for groundwater management in Taiwan and other alluvial plains worldwide.

A Bio-Inspired Artificial Intelligence Framework Leveraging Remote Sensing for Groundwater Storage Modeling in Climate-Stressed Regions

Geomorphological indicators of groundwater storage in arid hard rock aquifers

Impacts of timescales on the relationship between compound drought-hot extremes based on precipitation and groundwater.

Understanding groundwater dynamics of the depleted aquifer in the Indus Basin based on the downscaled GRACE data and groundwater modelling

Delineating groundwater potential in arid closed basins under dual-constraints of water quantity and quality: An integrated LASSO regression and Geospatial-AHP approach

ABSTRACT Understanding how streamflow is generated across spatial scales is crucial for enhancing regional hydrological models and effective water management. However, knowledge on how different geomorphic characteristics, landscape structure and subsurface properties influence streamflow remains limited, particularly in tropical Andean catchments. To address this gap, we investigated streamflow responses and generation processes across six nested tropical Andean catchments (6–91 km 2 ), characterized by permeable fractured bedrock, interconnected lake systems, wetlands and complex geomorphology within the Quinuas Ecohydrological Observatory in southern Ecuador. Using nearly a decade of hydrometric, stable isotopes and hydrogeochemical data, we applied a multi‐criteria approach that combined mixing models, transit times modelling, young water fractions estimation, and principal component analysis to identify dominant flow paths and controls on streamflow generation. Our findings reveal that, despite relatively uniform rainfall distribution across the catchments, streamflow responses are shaped by catchment structure, particularly geological controls and subsurface water storage. Small headwater catchments (6–19 km 2 ) exhibited rapid discharge responses to rainfall, with MTTs as low as 41 weeks, where wetlands and high‐altitude lakes regulated flows by slowly releasing stored water during dry periods. In contrast, larger downstream catchments (54–91 km 2 ) showed increasing dependence on deep groundwater storage within the permeable bedrock, with MTTs exceeding 100 weeks. Young water fraction estimates further revealed that fast, well‐connected flow paths persist across all catchment scales, coexisting with the progressive increase in groundwater storage and longer transit times observed downstream. The PCA revealed three groups driven by geology, topography and land cover that jointly shape MTT variability across scales. These results highlight the dominant role of geological and geomorphological variability in governing how water is generated and transported throughout complex terrain, providing new insights into structure‐dependent hydrological behaviour in tropical Andean catchments.