Search Results (2,072)

Groundwater plays a crucial role in sustaining agriculture and livelihoods in the arid Middle Draa Valley (MDV) of southeastern Morocco. However, increasing groundwater extraction, declining rainfall, and the absence of effective floodwater harvesting systems have led to severe aquifer depletion. This study applies and compares six machine learning (ML) algorithms—decision trees (CART), ensemble methods (random forest, LightGBM, XGBoost), distance-based learning (k-nearest neighbors), and support vector machines—integrating GIS, satellite data, and field observations to delineate zones suitable for groundwater recharge. The results indicate that ensemble tree-based methods yielded the highest predictive accuracy, with LightGBM outperforming the others by achieving an overall accuracy of 0.90. Random forest and XGBoost also demonstrated strong performance, effectively identifying priority areas for artificial recharge, particularly near ephemeral streams. A feature importance analysis revealed that soil permeability, elevation, and stream proximity were the most influential variables in recharge zone delineation. The generated maps provide valuable support for irrigation planning, aquifer conservation, and floodwater management. Overall, the proposed machine learning–geospatial framework offers a robust and transferable approach for mapping groundwater recharge zones (GWRZ) in arid and semi-arid regions, contributing to the achievement of Sustainable Development Goals (SDGs))—notably SDG 6 (Clean Water and Sanitation), by enhancing water-use efficiency and groundwater recharge (Target 6.4), and SDG 13 (Climate Action), by supporting climate-resilient aquifer management. Full article

The spatial variation of forest ecosystem services at regional scales remains poorly understood, and few studies have explicitly analyzed how ecosystem services are distributed across different forest management types. This study assessed the spatial overlap between forest management types and ecosystem service hotspots in the Southeastern United States (SEUS) and the Pacific Northwest (PNW) forests. We used the InVEST suite of tools and GIS to quantify carbon storage and water yield. Carbon storage was estimated, stratified by forest group and age class, and literature-based biomass pool values were applied. Average annual water yield and its temporal changes (2001–2020) were modeled using the annual water yield model, incorporating precipitation, potential evapotranspiration, vegetation type, and soil characteristics. Ecosystem service outputs were classified to identify hotspot zones (top 20%) and to evaluate the synergies and tradeoffs between these services. Hotspots were then overlaid with forest management maps to examine their distribution across management types. We found that only 2% of the SEUS and 11% of the PNW region were simultaneous hotspots for both services. In the SEUS, ecological and preservation forest management types showed higher efficiency in hotspot allocation, while in PNW, production forestry contributed relatively more to hotspot areas. These findings offer valuable insights for decision-makers and forest managers seeking to preserve the multiple benefits that forests provide at regional scales. Full article

As urbanization accelerates and climate change intensifies, the ecological integrity of urban riparian forests faces growing threats, underscoring the need for a systematic framework to guide their sustainable management. To address this gap, we developed a causal framework by applying text mining and sentence classification to 1001 abstracts from previous studies, structured within the DPSIR (Driver–Pressure–State–Impact–Response) model. The analysis identified six dominant thematic clusters—water quality, ecosystem services, basin and land use management, climate-related stressors, anthropogenic impacts, and greenhouse gas emissions—which reflect the multifaceted concerns surrounding urban riparian forest research. These themes were synthesized into a structured causal model that illustrates how urbanization, land use, and pollution contribute to ecological degradation, while also suggesting potential restoration pathways. To validate its applicability, the framework was applied to four major urban streams in Seoul, where indicator-based analysis and correlation mapping revealed meaningful linkages among urban drivers, biodiversity, air quality, and civic engagement. Ultimately, by integrating large-scale text mining with causal inference modeling, this study offers a transferable approach to support adaptive planning and evidence-based decision-making under the uncertainties posed by climate change. Full article

Acacia mearnsii De Wild. has been introduced to over 150 countries for its economic value. However, it easily escapes from plantations and establishes monospecific stands across plains, hills, valleys, and riparian habitats, including protected areas such as national parks and forest reserves. Due to its negative ecological impact, A. mearnsii has been listed among the world’s 100 worst invasive alien species. This species exhibits rapid stem growth in its sapling stage and reaches reproductive maturity early. It produces a large quantity of long-lived seeds, establishing a substantial seed bank. A. mearnsii can grow in different environmental conditions and tolerates various adverse conditions, such as low temperatures and drought. Its invasive populations are unlikely to be seriously damaged by herbivores and pathogens. Additionally, A. mearnsii exhibits allelopathic activity, though its ecological significance remains unclear. These characteristics of A. mearnsii may contribute to its expansion in introduced ranges. The presence of A. mearnsii affects abiotic processes in ecosystems by reducing water availability, increasing the risk of soil erosion and flooding, altering soil chemical composition, and obstructing solar light irradiation. The invasion negatively affects biotic processes as well, reducing the diversity and abundance of native plants and arthropods, including protective species. Eradicating invasive populations of A. mearnsii requires an integrated, long-term management approach based on an understanding of its invasive mechanisms. Early detection of invasive populations and the promotion of public awareness about their impact are also important. More attention must be given to its invasive traits because it easily escapes from cultivation. Full article

Accurate forecasting of river siltation is essential for ensuring inland waterway navigability and guiding sustainable sediment management. This study investigates the downstream reach of the Shihutang navigation power hub along the Ganjiang River in Jiangxi Province, China, an area characterized by pronounced seasonal sedimentation and hydrological variability. To enable fine-scale prediction, we developed a data-driven framework using a random forest regression model that integrates high-resolution bathymetric surveys with hydrological and meteorological observations. Based on the field data from April to July 2024, the model was trained to forecast monthly siltation volumes at a 30 m grid scale over a six-month horizon (July–December 2024). The results revealed a marked increase in siltation from July to September, followed by a decline during the winter months. The accumulation of sediment, combined with falling water levels, was found to significantly reduce the channel depth and width, particularly in the upstream sections, posing a potential risk to navigation safety. This study presents an initial, yet promising attempt to apply machine learning for spatially explicit siltation prediction in data-constrained river systems. The proposed framework provides a practical tool for early warning, targeted dredging, and adaptive channel management. Full article

To ensure water source security and sustainability of the national major strategic project “South-to-North Water Diversion”, this study aims to evaluate the spatio-temporal evolution characteristics of the ecosystem service value (ESV) in its water source area from 2002 to 2022. This study reveals its changing trends and main influencing factors, and thereby provides scientific support for the ecological protection and management of the water source area. Quantitative assessment of the ESV of the region was carried out using the Equivalence Factor Method (EFM), aiming to provide scientific support for ecological protection and resource management decision-making. In the past 20 years, the ESV has shown an upward trend year by year, increasing by 96%. The regions with the highest ESV were Garzê Prefecture and Aba Prefecture, which increased by 130.3% and 60.6%, respectively. The ESV of Xinlong county, Danba county, Rangtang county, and Daofu county increased 4.8 times, 1.5 times, 12.5 times, and 8.9 times, respectively. In the last two decades, arable land has decreased by 91%, while the proportions of bare land and water have decreased by 84% and 91%, respectively. Grassland had the largest proportion. Forests and grasslands, vital for climate regulation, water cycle management, and biodiversity conservation, have expanded by 74% and 43%, respectively. It can be seen from Moran’s I index values that the dataset as a whole showed a slight positive spatial autocorrelation, which increased from −0.041396 to 0.046377. This study reveals the changing trends in ESV and the main influencing factors, and thereby provides scientific support for the ecological protection and management of the water source area. Full article

Carbon (C) sequestration and nitrogen (N) and phosphorus (P) accumulation in urban forest green spaces are significant for global climate regulation and alleviating nutrient pollution. However, the effects of management and conservation practices across different urban forest vegetation types on soil C, N, and P contents and stoichiometric ratios remain largely unexplored. We selected forest soils from Guangzhou, a major Metropolis in China, as our study area. Soil samples were collected from two urban secondary forests that naturally regenerated after disturbance (108 samples) and six urban forest parks primarily composed of artificially planted woody plant communities (72 samples). We employed mixed linear models and variance partitioning to analyze and compare soil C, N, and P contents and their stoichiometry and its main driving factors beneath suburban forests and urban park vegetation. These results exhibited that soil pH and bulk density in urban parks were higher than those in suburban forests, whereas soil water content, maximum storage capacity, and capillary porosity were higher in urban forests than in urban parks. Soil C, N, and P contents and their stoichiometry (except for N:P ratio) were significantly higher in suburban forests than in urban parks. Multiple analyzes showed that soil pH had the most pronounced negative influence on soil C, N, C:N, C:P, and N:P, but the strongest positive influence on soil P in urban parks. Soil water content had the strongest positive effect on soil C, N, P, C:N, and C:P, while soil N:P was primarily influenced by the positive effect of soil non-capillary porosity in suburban forests. Overall, our study emphasizes that suburban forests outperform urban parks in terms of carbon and nutrient accumulation, and urban green space management should focus particularly on the impact of soil pH and moisture content on soil C, N, and P contents and their stoichiometry. Full article

Monitoring sediment concentration in water bodies is crucial for assessing water quality, ecosystems, and environmental health. However, physical sampling and sensor-based approaches are labor-intensive and unsuitable for large-scale, continuous monitoring. This study employs machine learning models to estimate suspended sediment concentration using images captured in natural light, named RGB, and near-infrared (NIR) conditions. A controlled dataset of approximately 1300 images with SSC values ranging from 1000 mg/L to 150,000 mg/L was developed, incorporating temperature, time of image capture, and solar irradiance as additional features. Random forest regression and gradient boosting regression were trained on mean RGB values, red reflectance, time of captured, and temperature for natural light images, achieving up to 72.96% accuracy within a 30% relative error. In contrast, NIR images leveraged gray-level co-occurrence matrix texture features and temperature, reaching 83.08% accuracy. Comparative analysis showed that ensemble models outperformed deep learning models like Convolutional Neural Networks and Multi-Layer Perceptrons, which struggled with high-dimensional feature extraction. These findings suggest that using machine learning models and RGB and NIR imagery offers a scalable, non-invasive, and cost-effective way of sediment monitoring in support of water quality assessment and environmental management. Full article

Situated in the southern hilly-mountain belt of China’s “Three Zones and Four Belts Strategy”, Gannan region is a critical ecological shelter belt for the Ganjiang River. Decades of intensive mineral extraction and irrational agricultural development have rendered it into an ecologically fragile area. Consequently, multiple restoration initiatives have been implemented in the region over recent decades. However, it remains unclear how relationships among ecosystem services have evolved under these interventions and how future ecosystem management should be optimized based on these changes. Thus, in this study, we simulated and assessed the spatiotemporal dynamics of five key ESs in Gannan region from 1990 to 2020. Through integrated correlation, clustering, and redundancy analyses, we quantified ES interactions, tracked the evolution of ecosystem service bundles (ESBs), and identified their socio-ecological drivers. Despite a 31% decline in water yield, ecological restoration initiatives drove substantial improvements in key regulating services: carbon storage increased by 6.9 × 10¹² gC while soil conservation rose by 4.8 × 10⁸ t. Concurrently, regional habitat quality surged by 45% in mean scores, and food production increased by 2.1 × 10⁵ t. Critically, synergistic relationships between habitat quality, soil retention, and carbon storage were progressively strengthened, whereas trade-offs between food production and habitat quality intensified. Further analysis revealed that four distinct ESBs—the Agricultural Production Bundle (APB), Urban Development Bundle (UDB), Eco-Agriculture Transition Bundle (ETB), and Ecological Protection Bundle (EPB)—were shaped by slope, forest cover ratio, population density, and GDP. Notably, 38% of the ETB transformed into the EPB, with frequent spatial interactions observed between the APB and UDB. These findings underscore that future ecological restoration and conservation efforts should implement coordinated, multi-service management mechanisms. Full article

Agriculture is the backbone of Punjab’s economy, and with much of India’s population dependent on agriculture, the requirement for accurate and timely monitoring of land has become even more crucial. Blending remote sensing with state-of-the-art machine learning algorithms enables the detailed classification of agricultural lands through thematic mapping, which is critical for crop monitoring, land management, and sustainable development. Here, a Hyper-tuned Deep Neural Network (Hy-DNN) model was created and used for land use and land cover (LULC) classification into four classes: agricultural land, vegetation, water bodies, and built-up areas. The technique made use of multispectral data from Sentinel-2 and Landsat-8, processed on the Google Earth Engine (GEE) platform. To measure classification performance, Hy-DNN was contrasted with traditional classifiers—Convolutional Neural Network (CNN), Random Forest (RF), Classification and Regression Tree (CART), Minimum Distance Classifier (MDC), and Naive Bayes (NB)—using performance metrics including producer’s and consumer’s accuracy, Kappa coefficient, and overall accuracy. Hy-DNN performed the best, with overall accuracy being 97.60% using Sentinel-2 and 91.10% using Landsat-8, outperforming all base models. These results further highlight the superiority of the optimised Hy-DNN in agricultural land mapping and its potential use in crop health monitoring, disease diagnosis, and strategic agricultural planning. Full article

Water infiltration into soil is a key process in regulating the hydrological cycle and sustaining ecosystem services in high-Andean environments. However, limited information is available regarding its dynamics in these ecosystems. This study evaluated the influence of three types of vegetation cover and soil properties on water infiltration in a high-Andean environment. A double-ring infiltrometer, the Water Drop Penetration Time (WDPT, s) method, and laboratory physicochemical characterization were employed. Soils under forest cover exhibited significantly higher quasi-steady infiltration rates (i_s, 0.248 ± 0.028 cm·min⁻¹) compared to grazing areas (0.051 ± 0.016 cm·min⁻¹) and agricultural lands (0.032 ± 0.013 cm·min⁻¹). Soil organic matter content was positively correlated with i_s. The modified Kostiakov infiltration model provided the best overall fit, while the Horton model better described infiltration rates approaching i_s. Sand and clay fractions, along with K⁺, Ca²⁺, and Mg²⁺, were particularly significant during the soil’s wet stages. In drier stages, increased Na⁺ concentrations and decreased silt content were associated with higher water repellency. Based on WDPT, agricultural soils exhibited persistent hydrophilic behavior even after drying (median [IQR] from 0.61 [0.38] s to 1.24 [0.46] s), whereas forest (from 2.84 [3.73] s to 3.53 [24.17] s) and grazing soils (from 4.37 [1.95] s to 19.83 [109.33] s) transitioned to weakly or moderately hydrophobic patterns. These findings demonstrate that native Andean forest soils exhibit a higher infiltration capacity than soils under anthropogenic management (agriculture and grazing), highlighting the need to conserve and restore native vegetation cover to strengthen water resilience and mitigate the impacts of land-use change. Full article

The impacts of land use transition on ecological environment quality (EEQ) during China’s rapid urbanization have attracted growing concern. However, existing studies predominantly focus on single-scale analyses, neglecting scale effects and driving mechanisms of EEQ changes under the coupling of administrative units and grid scales. Therefore, this study selects Zhejiang Province—a representative rapidly transforming region in China—to establish a “type-process-ecological effect” analytical framework. Utilizing four-period (2005–2020) 30 m resolution land use data alongside natural and socio-economic factors, four spatial scales (city, county, township, and 5 km grid) were selected to systematically evaluate multi-scale impacts of land use transition on EEQ and their driving mechanisms. The research reveals that the spatial distribution, changing trends, and driving factors of EEQ all exhibit significant scale dependence. The county scale demonstrates the strongest spatial agglomeration and heterogeneity, making it the most appropriate core unit for EEQ management and planning. City and county scales generally show degradation trends, while township and grid scales reveal heterogeneous patterns of local improvement, reflecting micro-scale changes obscured at coarse resolutions. Expansive land transition including conversions of forest ecological land (FEL), water ecological land (WEL), and agricultural production land (APL) to industrial and mining land (IML) primarily drove EEQ degradation, whereas restorative ecological transition such as transformation of WEL and IML to grassland ecological land (GEL) significantly enhanced EEQ. Regarding driving mechanisms, natural factors (particularly NDVI and precipitation) dominate across all scales with significant interactive effects, while socio-economic factors primarily operate at macro scales. This study elucidates the scale complexity of land use transition impacts on ecological environments, providing theoretical and empirical support for developing scale-specific, typology-differentiated ecological governance and spatial planning policies. Full article

The mapping and monitoring of coastal regions are critical to ensure their sustainable use and viability in the long term. Delineation of coastlines is becoming increasingly important in the light of climate change and rising sea levels. However, many coastlines are highly dynamic; therefore, mono-temporal assessments of coastal ecosystems and coastlines are mere snapshots of limited practical value for space-based planning. Understanding of the spatio-temporal dynamics of coastal ecosystem boundaries is important to inform ecosystem management but also for a meaningful delineation of the high-water mark, which is used as a benchmark for coastal spatial planning in South Africa. This research aimed to use hyper-temporal Sentinel-2 imagery to extract ecological zones on the coast of KwaZulu-Natal, South Africa. A total of 613 images, collected between 2019 and 2023, were classified into four distinct coastal ecological zones—vegetation, bare, surf, and water—using a Random Forest model. Across all classifications, the percentage of each of the four classes’ occurrence per pixel over time was determined. This enabled the identification of ecosystem locations, spatially static ecosystem boundaries, and the occurrence of ecosystem boundaries with a more dynamic location over time, such as the non-permanent vegetation zone of the foredune area as well as the intertidal zone. The overall accuracy of the model was 98.13%, while the Kappa coefficient was 0.975, with user’s and producer’s accuracies ranging between 93.02% and 100%. These results indicate that cloud-based analysis of Sentinel-2 time series holds potential not just for delineating coastal ecosystem boundaries, but also for enhancing the understanding of spatio-temporal dynamics between them, to inform meaningful environmental management, spatial planning, and climate adaptation strategies. Full article

The ecosystem services (ESs) of forests are the benefits that people derive from forest ecosystems. Their precise recognition is important for differentiating and determining the optimal principles of multifunctional forest management. The aim of this study is to identify some important ESs based on a site classification system at the lowest level—i.e., forest stands, at the forest owner level—as a tool for differentiated management. ESs were assessed within the Czech Republic and are expressed in units in accordance with the very sophisticated Forest Site Classification System. (1) Biomass production: The vertical differentiation of ecological conditions given by vegetation tiers, which reflect the influence of altitude, exposure, and climate, provides a basic overview of biomass production; the highest value is in the fourth vegetation tier, i.e., the Fageta abietis community. Forest stands are able to reach a stock of up to 900–1200 m³·ha⁻¹. The lowest production is found in the eighth vegetation tier, i.e., the Piceeta community, with a wood volume of 150–280 m³·ha⁻¹. (2) Soil conservation function: Geological bedrock, soil characteristics, and the geomorphological shape of the terrain determine which habitats serve a soil conservation function according to forest type sets. (3) The hydricity of the site, depending on the soil type, determines the hydric-water protection function of forest stands. Currently, protective forests occupy 53,629 ha in the Czech Republic; however, two subcategories of protective forests—exceptionally unfavorable locations and natural alpine spruce communities below the forest line—potentially account for 87,578 ha and 15,277 ha, respectively. Forests with an increased soil protection function—a subcategory of special-purpose forests—occupy 133,699 ha. The potential area of soil protection forests could be up to 188,997 ha. Water resource protection zones of the first degree—another subcategory of special-purpose forests—occupy 8092 ha, and there is potentially 289,973 ha of forests serving a water protection function (specifically, a water management function) in the Czech Republic. A separate subcategory of water protection with a bank protection function accounts for 80,529 ha. A completely new approach is presented for practical use by forest owners: based on the characteristics of the habitat, they can obtain information about the fulfillment of the habitat’s ecosystem services and, thus, have basic information for the determination of forest categories and the principles of differentiated management. Full article

In response to the global ecological and agricultural challenges posed by coastal saline-alkali areas, this study focuses on Dongying City as a representative region, aiming to develop a high-precision soil salinity prediction mapping method that integrates multi-source remote sensing data with machine learning techniques. Utilizing the SCORPAN model framework, we systematically combined diverse remote sensing datasets and innovatively established nine distinct strategies for soil salinity prediction. We employed four machine learning models—Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Geographical Gaussian Process Regression (GGPR) for modeling, prediction, and accuracy comparison, with the objective of achieving high-precision salinity mapping under complex vegetation cover conditions. The results reveal that among the models evaluated across the nine strategies, the SVR model demonstrated the highest accuracy, followed by RF. Notably, under Strategy IX, the SVR model achieved the best predictive performance, with a coefficient of determination (R²) of 0.62 and a root mean square error (RMSE) of 0.38 g/kg. Analysis based on SHapley Additive exPlanations (SHAP) values and feature importance indicated that Vegetation Type Factors contributed significantly and consistently to the model’s performance, maintaining higher importance than traditional salinity indices and playing a dominant role. In summary, this research successfully developed a comprehensive, high-resolution soil salinity mapping framework for the Dongying region by integrating multi-source remote sensing data and employing diverse predictive strategies alongside machine learning models. The findings highlight the potential of Vegetation Type Factors to enhance large-scale soil salinity monitoring, providing robust scientific evidence and technical support for sustainable land resource management, agricultural optimization, ecological protection, efficient water resource utilization, and policy formulation. Full article