Search Results (524)

Urban green spaces (UGSs) are vital ecological infrastructure supporting climate resilience, public health, and environmental equity. Despite UGS’s importance, the distribution of UGS in rapidly growing desert cities is wildly disproportionate, as evidenced by a recent study that links UGS availability with road hierarchy using the Road Buffer Framework. Using Landsat 8-derived UGS (overall accuracy = 0.885; Kappa = 0.853), OpenStreetMap Roads, and WorldPop Population Data, this study found that UGS availability per capita is very low across all road classifications (0.020–0.033 m²/person) and falls significantly short of the World Health Organization’s (WHO) recommendation of 9 m²/person. Primary roads only marginally improved based on distance from roadways (0.026–0.032 m²/person), and secondary roads are experiencing little to no change (0.025–0.026 m²/person). Further, Tertiary roads show the most significant loss, with only 0.022 m²/person available within the 0–300 m buffers containing the most people. In addition, urban green spaces are still significantly inequitable, as demonstrated by Gini coefficient results of >0.80, peaking at 0.895, indicating that UGS availability per capita is substantially below international benchmarks. Therefore, the findings highlight the need of incorporating roadside greening, small park areas, and greenways into our transportation planning efforts to support the UN’s Sustainable Development Goals (SDG) 3, 10, 11, and 13. Full article

Accurate delineation of rural settlements at large spatial extents is fundamental to territorial spatial governance, rural revitalization, and the improvement of human living environments. However, in medium-resolution remote sensing imagery, rural settlement patches are typically small, morphologically complex, and easily confused with other impervious surfaces. As a result, existing products still fall short in characterizing these features. Here, we propose a lightweight Transformer-based semantic segmentation model, SELPFormer, and develop a multi-source fusion automatic labeling pipeline that integrates Global Impervious Surface Dynamics dataset, OpenStreetMap spatial priors, and nighttime lights constraints. Built upon SegFormer as the backbone, SELPFormer introduces a lightweight pyramid pooling module at the deepest feature level to aggregate multi-scale global context and embeds an SCSE channel–spatial attention mechanism into deep features to suppress background interference. In addition, it incorporates an efficient local attention module into multi-scale lateral connections to enhance boundary and texture representations, thereby jointly improving small-object recognition and fine boundary preservation. We evaluate the proposed method using Landsat multispectral imagery covering five provinces on the North China Plain. SELPFormer achieves IoU = 74.23%, mIoU = 86.43%, F1 = 85.21%, OA = 98.69%, and Kappa = 0.8452 under a unified training and evaluation protocol, yielding IoU gains of +1.44, +3.98, and +12.35 percentage points over SegFormer, U-Net, and DeepLabV3+, respectively. SELPFormer has 15.44 M parameters and attains a parameter efficiency of 3.93% IoU per million parameters and an ROC-AUC of 0.993, indicating strong threshold-independent discriminative capability. These results indicate that the proposed method can effectively extract rural settlements from medium-resolution imagery and provides a generic “global–channel–local” collaborative framework for model design and data construction. Full article

Population ageing is intensifying pressure on elderly-care provision in megacity suburbs, but spatially explicit evidence on who benefits and where gaps persist remains limited. Using Daxing District, Beijing, as a case study, under the 15-min community living circle framework, we integrate cleaned elderly-care facility POIs from the municipal government portal (209 points), census-calibrated age-stratified WorldPop 100 m grids, and an OpenStreetMap road network to evaluate walking-based supply–demand matching. Kernel density estimation (KDE) characterizes facility agglomeration; the Gaussian Two-Step Floating Catchment Area (Ga2SFCA) method (1 km threshold) measures accessibility for two cohorts (60–80 and 80+); and global Moran’s I with bivariate LISA identifies spatial coupling between accessibility and elderly population density. The results indicate the following: (1) pronounced spatial imbalance—facilities are concentrated in the northwest and east but remain sparse in central and southern areas, while elderly population density follows a center–periphery gradient, peaking at 12,000 persons/km² in core areas (e.g., Jiugong and Huangcun); (2) clear accessibility stratification—overall accessibility is low and spatially clustered, yet the 80+ cohort (13.6% of the elderly population) exhibits markedly higher accessibility than the 60–80 cohort; and (3) differentiated coupling types—global bivariate Moran’s I = 0.773143 (p < 0.01), with LISA dominated by low-demand–low-accessibility (LL) areas and additional high-demand–low-accessibility (HL) shortage zones and low-demand–high-accessibility (LH) potential redundancy zones, while HH areas are scarce. These diagnostics support zone-specific gap filling to mitigate spatial inequities and age–structural mismatches. Full article

The snowpack in the European Alps is declining due to global warming, which affects both the amount of seasonal snow and the timing of accumulation and melt. As the European Alps is the largest winter tourism destination in the world by revenue, this decline in natural snow poses an existential threat to the sector. Several smaller ski areas have closed permanently since 1980, and all Alpine regions face rising costs due to an increasing reliance on snowmaking. Professional winter sports are also affected, with several canceled events in recent years due to unsuitable snow conditions. In this study, we present the first remote sensing-based assessment of long-term snow reliability for winter tourism in the European Alps. Using snowline elevation (SLE) data derived from Landsat observations from 1985 to 2024, combined with OpenStreetMap ski infrastructure data and digital elevation models, we quantified the monthly snow coverage of ski area segments across 43 Alpine basins. Theil–Sen trends and Mann–Kendall significances were calculated for the full season and for three subseasons, with quality checks applied to guarantee sufficient data coverage. The results show predominantly negative trends across all seasons, with the strongest declines occurring in the late season. In this period, 97.8% of all downhill ski areas and 99.5% of the cross-country ski areas for which a trend was derived exhibited negative trends. For the full season, the corresponding shares were 94% for downhill ski areas and 99.2% for cross-country ski areas. In addition, areas located at the geographical edges of the European Alps showed more pronounced negative trends compared with the core regions. These findings align with previous studies on the subject and highlight the ongoing shortening of natural snow seasons and thus the increased challenges for the winter tourism sector in the Alps. Full article

The tangible patterns of urban heritage sites are composed of complex components, and their interaction is involved in the process of formation and transformation. The past of cities also partially survives in the structure of the settlement, even if many buildings are demolished or significantly transformed. In this study, we introduce a model based on the integration of urban morphology, deep learning, and artificial intelligence methods for exploring the tangible patterns of urban heritage areas at different levels of scale. The proposed model is able to define and recognize the characteristics of the basic elements of urban forms at different resolution levels and reveal the patterns of the heritage. The basic principle of the model is the analysis of urban heritage sites located in different parts of the historical city center of Istanbul. We first define the relationship patterns and complexity levels, and form the characteristics of the urban form by using geographic information systems (GIS), based on the cartographic and contemporary maps. We then employ deep-learning-based convolutional neural networks (CNNs) for automatic segmentation, using OpenCV and NumPy in Python to extract streets and blocks on both historical and contemporary map sources. Based on the results integrated with human intelligence and the CNNs model, we finally generate several prompts for AI for better reasoning in the process of pattern recognition. Our results reveal that this integration increases GPT-4o’s assumptions in the pattern recognition process and, thus, it is able to reveal similar results to those obtained from the form features with different levels of specificity that are interdependent and complementary to human assessments. Full article

Crowdsourced geospatial platforms constitute complex socio-technical systems in which data quality and reliability emerge from collective user behavior rather than centralized control. This study proposes a system-oriented, unsupervised machine learning framework to assess the reliability of crowdsourced building data using only intrinsic indicators. The framework is demonstrated through a large-scale analysis of OpenStreetMap building polygons in Tehran. Six intrinsic indicators—reflecting contributor activity, temporal dynamics, semantic instability, and geometric evolution—were normalized using fuzzy membership functions and objectively weighted based on their discriminative influence within a K-means clustering process. Five reliability classes were identified, ranging from very low to very high reliability. The resulting classification exhibited strong internal validity (average silhouette coefficient = 0.58) and pronounced spatial coherence (Global Moran’s I = 0.85, p < 0.001). This approach eliminates dependence on authoritative reference datasets, enabling scalable, reproducible, and feature-level reliability assessment in open geospatial systems. The framework provides a transferable methodological foundation for trust-aware analysis and decision-making in participatory and data-intensive systems. Full article

Power load forecasting is essential for power system security and energy dispatch. With the increasing renewable integration, load patterns have become more volatile and uncertain, difficult for traditional forecasting methods to maintain high adaptability. To address this challenge, this study proposes the Llama3-QLoRA-GeoWeather framework, a novel power load forecasting approach based on the open-source large language model Llama 3.3 70B. The framework introduces a two-stage progressive fine-tuning strategy based on QLoRA, significantly reducing computational costs and allowing adaptation on constrained hardware. Moreover, geographic features from the OpenStreetMap ecosystem and meteorological data from OpenWeatherMap API are integrated to further enhance the forecasting performance. A comprehensive Llama3-PowerFrame enhancement framework for future power systems is also designed. Experimental results demonstrate that Llama3-QLoRA-GeoWeather achieves the best forecasting performance (MAPE = 1.16%), outperforming the state-of-the-art baselines. This corresponds to a reduction in MAE, RMSE, and MAPE by approximately 42.7%, 67.8%, and 42.3% respectively, providing a viable technical pathway for building the next-generation intelligent load forecasting system across multiple scenarios with high credibility and strong adaptability. Full article

This study aims to establish an integrated landscape planning model and explore its applicability through the convergence of digital twin technology. The primary goal is to address the fragmented implementation of landscape policies and to provide a systematic framework that enhances efficiency and visualization in the planning process. To this end, text-mining analysis was conducted to extract relevant laws, statutory plans, and project data, thereby identifying key factors for model construction. The resulting model integrates conservation-oriented and recreation-oriented modules, presenting a practical approach for landscape management. Furthermore, by utilizing Blender 3D and OpenStreetMap, this study demonstrates the process through which a digital twin visualizes and simulates the spatial characteristics of the actual target site, thereby validating its utility in decision-making and stakeholder communication. The results indicate that the landscape planning model was reconfigured and integrated into 6 detailed implementation measures and 41 specific indicators. Moreover, the model visually linked 36 laws and approximately 70 plans and projects. Ultimately, the study confirms that the proposed approach provides a dynamic, data-driven platform for sustainable landscape management. Full article

The ongoing advance of urbanization has increased the need for accurate monitoring of urban green space (UGS). However, existing remote-sensing UGS mapping still struggles with inconsistent data quality, diverse urban forms, and limited cross-city generalization. This study focuses on China’s Guangdong-Hong Kong-Macao Greater Bay Area as its research region, establishing a fully automated UGS mapping framework based on Sentinel-2 time-series imagery and standardized OpenStreetMap (OSM) data. This process achieves UGS mapping at 10 m resolution for 16 cities within the metropolitan area through a dynamic standardized OSM tagging system, a Sentinel-2 satellite image sample generation mechanism integrating spectral and textural features, multidimensional sample quality assessment and weighting strategies, as well as balanced cross-city sampling and weighted SVM classification. The results demonstrate that this method exhibits stable performance across multiple urban environments, achieving an average overall accuracy of approximately 0.83 and an average F1 score of approximately 0.82. The highest recorded F1 score reaches 0.96, highlighting the method’s strong generalization capability under diverse urban conditions. The mapping results reveal significant disparities in UGS distribution within the Guangdong-Hong Kong-Macao Greater Bay Area, reflecting the combined effects of varying urban development patterns and ecological contexts. The unified workflow proposed in this study demonstrates strong applicability in handling heterogeneous urban structures and enhancing cross-regional comparability. It provides consistent, transparent, and reusable foundational data for regional eco-urban planning, urban green infrastructure development, and policy evaluation. Full article

Access to large-scale public transport journey data is essential for analysing accessibility, equity, and urban mobility. Although digital platforms such as Google Maps provide detailed routing for individual users, their licensing and access restrictions prevent systematic data extraction for research purposes. Open-source routing engines such as OpenTripPlanner offer a transparent alternative, but are often limited to local or technical deployments that restrict broader use. This study evaluates the feasibility of deploying a publicly accessible, open-source routing platform based on OpenTripPlanner to support large-scale public transport route simulation across multiple cities. Using Australian metropolitan areas as a case study, the platform integrates GTFS and OpenStreetMap data to enable repeatable journey queries through a web interface, an API, and bulk processing tools. Across eight metropolitan regions, the system achieved itinerary coverage above 90 percent and sustained approximately 3000 routing requests per minute under concurrent access. These results demonstrate that open-source routing infrastructure can support reliable, large-scale route simulation using open data. Beyond performance, the platform enables public transport accessibility studies that are not feasible with proprietary routing services, supporting reproducible research, transparent decision-making, and evidence-based transport planning across diverse urban contexts. Full article

About 16% of typhoons making landfall in China strike Hainan Island, where near-surface extreme winds in dense urban areas exhibit a strong spatiotemporal heterogeneity that is difficult to capture with current observations and mesoscale models. Focusing on Haikou during Super Typhoon Yagi (2024)—the strongest autumn typhoon to hit China since 1949—we developed a multiscale ERA5–WRF–PALM framework to conduct 30 m resolution large-eddy simulations. PALM results are in reasonable agreement with most of the five automatic weather stations, while performance is weaker at the most sheltered park site. Mean near-surface wind speeds increased by 20–50% relative to normal conditions, showing a coastal–urban gradient: maps of weighted cumulative exposure to strong winds (≥Beaufort force 8) show much longer and more intense events along open coasts than within built-up urban cores. Urban morphology exerted nonlinear effects: wind speeds followed a U-shaped relation with both the open-space ratio and mean building height, with suppression zones at ~0.5–0.7 openness and ~20–40 m height, while clusters of super-tall buildings induced Venturi-like acceleration of 2–3 m s⁻¹. Spatiotemporal analysis revealed banded swaths of high winds, with open areas and islands sustaining longer, broader extremes, and dense street grids experiencing shorter, localized events. Methodologically, this study provides a rare, systematically evaluated application of a multiscale ERA5–WRF–PALM framework to a real typhoon case at 30 m resolution in a tropical coastal city. These findings clarify typhoon–city interactions, quantify morphological regulation of extreme winds, and support risk assessment, urban planning, and wind-resilient design in coastal megacities. Full article

In agriculture, climate change is the most critical global issue. It is widely acknowledged that addressing this issue poses a considerable challenge, primarily due to its multifaceted impact on regional economies and land management practices. The concept of Nature-based Solutions (NbS) provides a prosperous approach offering both adaptation and mitigation models. However, NbS implementation is often compromised by various natural and societal challenges. Vojvodina Province, the northern province of the Republic of Serbia, features a typical rural landscape where centuries of agricultural practice have led to significant environmental changes, with 70% of the territory converted to arable land. However, climate change has been demonstrated to induce increasingly extreme weather conditions, which in turn exacerbate the situation with regard to food production. This paper aims to examine the most prosperous ways for NbS implementation in Vojvodina Province. The preset study mapped areas suitable for the implementation of selected NbS on the territory of Vojvodina Province. Maps were created in QGIS, while data were extracted from various sources (CORINE Land Cover, OpenStreetMap, the Institute for Nature Conservation of Vojvodina Province, and EUNIS platform). The area suitable for NbS in Vojvodina amounts to 1,183,228 ha or 55.74%. An increase in the area dedicated to organic and regenerative agriculture is projected, with a predicted range of up to 5%. Finally, we have identified grazing as a desirable management option for grassland management, which we have mapped, and it could potentially be practiced on almost 10% of the territory. Moreover, the engagement of various stakeholders is crucial in the implementation of NbS over the territory of the rural landscape. Considering that neighboring countries are facing the same climate circumstances and a similar social context, the findings we have presented in the paper may be applied to the region of the southern part of the Pannonian Plain. Full article

This study introduces SquareSwish, a smooth, self-gated activation $f\left(x\right)=x\sigma {\left(x\right)}^2$, and benchmarks it against ten established activations (ReLU, LeakyReLU, ELU, SELU, GELU, Snake, LearnSnake, Swish, Mish, Hard-Swish) across six CNN architectures (EfficientNet-B1/B4, EfficientNet-V2-M/S, ResNet-50, and Xception) under a uniform transfer-learning protocol. Two geographically grounded datasets are used in this study. FuelRiskMap-TR comprises 7686 satellite images of urban fuel stations in Türkiye, which is semantically enriched with the OpenStreetMap context and YOLOv8-Small rooftop segmentation (mAP@0.50 = 0.724) to support AI-enabled, ICT-integrated risk screening. In a similar fashion, FuelRiskMap-UK is collected, comprising 2374 images. Risk scores are normalized and thresholded to form balanced High/Low-Risk labels for supervised training. Across identical training settings, SquareSwish achieves a top-1 validation accuracy of 0.909 on EfficientNet-B1 for FuelRiskMap-TR and reaches 0.920 when combined with SELU in a simple softmax-probability ensemble, outperforming the other activations under the same protocol. By squaring the sigmoid gate, SquareSwish more strongly attenuates mildly negative activations while preserving smooth, non-vanishing gradients, tightening decision boundaries in noisy, semantically enriched Earth-observation settings. Beyond classification, the resulting city-scale risk layers provide actionable geospatial outputs that can support inspection prioritization and integration with municipal GIS, offering a reproducible and low-cost safety-planning approach built on openly available imagery and volunteered geographic information. Full article

Accurate localization in canopy-occluded, GNSS-challenged environments is critical for autonomous robots and intelligent vehicles. This paper presents a coarse-to-fine trajectory estimation framework using millimeter-wave radar as the primary sensor, leveraging its foliage penetration and robustness to low visibility. The framework integrates short- and long-term temporal feature enhancement to improve descriptor distinctiveness and suppress false loop closures, together with adaptive OpenStreetMap-derived priors that provide complementary global corrections in scenarios with sparse revisits. All constraints are jointly optimized within an outlier-robust backend to ensure global trajectory consistency under severe GNSS signal degradation. Evaluations conducted on the MulRan dataset, the OORD forest canopy dataset, and real-world campus experiments with partial and dense canopy coverage demonstrate up to 55.23% reduction in Absolute Trajectory Error (ATE) and a minimum error of 1.83 m compared with baseline radar- and LiDAR-based SLAM systems. The results indicate that the integration of temporally enhanced radar features with adaptive map constraints substantially improves large-scale localization robustness. Full article

Spatial accessibility to education represents a key component of spatial justice, yet significant disparities persist between urban and rural areas in Romania. The present paper introduces the concept of education deserts as settlements where the population lacks proper access to education within a reasonable commuting distance and travel time, with a focus on high schools. Open-source demographic and institutional data and GIS-based spatial analysis were used in identifying education deserts across Romania. These were later evaluated based on a 20 min travel time or a 25 km distance threshold computed using OpenStreetMap API data. To assess the multidimensional nature of education deserts, a Composite Demand Index (CDI) and an Access Hardship Index (AHI) have been developed. Both were integrated into a final Education Desert Index (EDI) that captures unmet demand and spatial constraints. Results indicate that 34.3% of Romanian settlements (1092 LAU2s) and 15.2% of the high school-aged population reside in education deserts, found predominantly in the country’s North-East, South, and Centre regions. These areas coincide with rural, peripheral zones characterised by infrastructural deficits and low educational attainment. Findings reveal spatial inequities in upper secondary education provision between urban and rural communities. The present study offers a replicable methodological framework for evaluating educational accessibility and supports evidence-based policymaking aimed at reducing spatial disparities in education. Full article