Search Results (4,767)

This study reports a combined morphological, surface chemical, and mineralogical characterization of fine particulate matter (PM_2.5) collected at three coastal sites—Northern (Abhour), Middle (Alhamraa), and Southern (Alkhomra)—in Jeddah, Saudi Arabia, during the summer (15 June–15 September 2017). The work complements a companion trace-element study of the same campaign by adding scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS/EDX mapping), X-ray photoelectron spectroscopy (XPS), and X-ray diffraction (XRD), thereby linking bulk concentrations to particle morphology, surface oxidation state, and crystalline phase. Mean PM_2.5 concentrations were 22.2, 18.9, and 14.2 µg m⁻³ at the North, Middle, and South sites, respectively. Because samples were collected on borosilicate glass-fibre filters, the SEM images are dominated by the intrinsic fibrous matrix of the substrate; the collected aerosol is resolved as discrete sub-micrometre particles and agglomerates decorating the fibres, and the morphological interpretation is framed accordingly. XPS confirmed that surface metals (Fe, Al, Ca, and traces of Pb, Cu, Zn) occur predominantly in oxidized states, with the Middle urban site showing the strongest Fe and Pb signals. XRD identified quartz, calcite, gypsum, hematite/magnetite, and aluminum oxides, with additional Pb and Cu phases at the Middle and South sites. Principal component analysis (PCA) resolved four sources—mixed marine–crustal, terrigenous/industrial (Fe–Ti–Mn), oil combustion and shipping (V–Ni–Cu), and combustion/legacy-traffic (Pb–Zn)—consistent with prior Jeddah and Red Sea studies. The integrated approach provides surface-speciation and mineralogical details not available from bulk elemental analysis alone and establishes baseline information relevant to source management and health-risk assessment in arid coastal cities. Full article

Photogrammetric 3D city models contain detailed planimetric and elevation information that supports urban visualization and low-altitude applications. However, the direct dissemination of high-accuracy models may expose sensitive geometric measurements. Existing protection methods mainly focus on conventional encryption, coordinate scrambling, or two-dimensional data perturbation and do not adequately balance geometric accuracy degradation with the visual usability of textured 3D meshes. This study proposes a controlled geometric deformation method that processes the planimetric and elevation components independently. In the horizontal domain, a normalized Sigmoid function generates smooth, bounded, and spatially varying coordinate displacements. In the vertical domain, a normalized deformation function combines global elevation stretching with amplitude-constrained sine-wave superposition. The sine-wave parameters are generated using a seed-sensitive hybrid cascaded chaotic system, producing reproducible but model-dependent nonlinear deformation patterns. During processing, the mesh connectivity, face indices, texture coordinates, texture images, and material relationships remain unchanged. The method was evaluated using low-rise and high-rise photogrammetric 3D scenes with different horizontal extents and elevation characteristics. Under the selected 10 m planimetric and 5% elevation settings, the mean planimetric displacements were 10.474 and 10.045 m, while the relative elevation deformations were 5.01% and 5.30%, respectively. Both datasets maintained monotonic elevation relationships and achieved 100% direction consistency. Their spatial-shape coefficients deviated from the corresponding reference values by only 0.02% and 1.33%. The results demonstrate that the proposed method provides controllable and spatially continuous geometric deformation while maintaining mesh connectivity, overall morphology, and visual interpretability. It can therefore serve as a practical pre-processing approach for the risk-reduced dissemination and non-measurement-oriented visualization of photogrammetric 3D city models. Full article

This study examines urban green infrastructure (UGI) branding as a governance practice shaped by institutional homogenization and strategic responses within China’s multi-level policy framework. Against the backdrop of global sustainability agendas, UGI branding is conceptualized as a policy-oriented, symbolically embedded instrument for communicating cities’ commitments to green development and climate resilience. Using an institutional “identity–label–image” framework, integrated with policy diffusion theory and multi-center regional development models, we systematically analyze historical brand-label data from 27 core cities in the Yangtze River Delta. Our findings reveal three key patterns: (1) brand diffusion follows dual pathways of mandatory and imitative homogenization, with evolutionary rhythms tied to five-year planning cycles, generating discernible “policy waves”; (2) within polycentric regional structures, core cities act as institutional “interpreters” and benchmarks, while peripheral cities pursue imitation-driven differentiation, reflecting complex dynamics of collaboration and competition; and (3) urban identities expressed through brand labels progressively align with substantive sustainability transitions, aiming to enhance regional competitiveness and upward recognition. We conclude that UGI branding constitutes a deep-seated mechanism of sustainable urban governance, offering a novel theoretical lens on China’s institutional logic of city branding and providing actionable insights for optimizing collaborative brand governance and integrated green infrastructure planning in urban agglomerations. Full article

Urban streets are critical public spaces that support residents’ daily psychological recovery, and their landscape quality is directly related to pedestrians’ physical and mental well-being. In the rapid urbanization process, numerous urban streets have exhibited problems such as excessive building density, cluttered visual interfaces, a lack of natural elements, and an absence of regional characteristics, leading to a continuous decline in the psychological restorative capacity of street spaces and failure to meet residents’ demands for a healthy urban environment. Existing research mostly employs qualitative assessment methods to evaluate walking experiences and psychological restoration levels of street environments, lacking high-precision, pixel-level quantification of street landscape elements and rarely incorporating regional cultural elements into the analytical framework of restorative environments. This study takes Foshan, a famous historical and cultural city in China, as the research object, and selects five typical streets in the main urban area, including comprehensive streets, living streets, landscape streets, commercial streets, and historical–cultural streets, to construct a technical route of “data collection–element quantification–model construction–effect analysis.” Leveraging the pre-trained Mask2Former semantic segmentation model and pedestrian-perspective street-view images (SVIs), combined with field research, the study quantifies 22 street landscape elements across five dimensions: environment, transportation, social interaction, facilities, and culture. Through PCA principal component analysis and K-means clustering, 20 typical photos were objectively sampled, and public psychological evaluations were conducted using the Perceived Restorativeness Scale (PRS). A stepwise multiple linear regression model was then employed to construct an exploratory explanatory model for street psychological restoration, identifying key influencing factors and their effect intensities. The results indicate the following: (1) Environmental and cultural elements are the core characteristics associated with pedestrians’ psychological restoration, whereas transportation, social, and facility elements are correlated only with certain restoration dimensions and show no significant association with the overall psychological restoration level. (2) Among the 22 element indicators, the Green View Index showed the strongest positive association with psychological restoration (β = 0.681, p < 0.001); historical memory markers and the Blue View Index also exhibited significant positive associations. (3) By integrating the elements associated with pedestrians’ psychological restoration and their association strengths, an exploratory explanatory model of the psychological restoration benefits of urban street landscapes was constructed, with an adjusted coefficient of determination of 69.8%, accounting for 69.8% of the variation in street psychological restoration levels. The findings establish an exploratory analytical framework and furnish empirical evidence for healthy city planning and street renewal in similar historical and cultural cities. Full article

Grouping vehicles with similar paths is important for traffic analysis, but camera-image trajectories are distorted by perspective, and unsupervised clustering does not directly reveal how many traffic movements should be expected. This paper presents Homography-Guided Semantic Maneuver Graph Trajectory Clustering (HG-SMG-TC), a model-selection framework that uses a lightweight homography to estimate intersection structure while retaining isotropically normalized camera coordinates for clustering. Entry and exit endpoint groups are consolidated into physical approach-level groups, and their supported origin–destination relationships form a maneuver graph. Bootstrap resampling converts this structure into an interval for the expected number of observed movements, which guides clustering model selection. The method is evaluated on 67,029 vehicle trajectories from five urban intersection scenes in the Traffic Node Video Dataset, using separate target-estimation, model-selection, and independent-test recording blocks. Independent polygon-rule reference labels cover 89.6–98.4% of test trajectories. HG-SMG-TC reduces mean target-count error from 3.20 for untargeted selection and 2.53 for the point-target variant to 2.13, while achieving an adjusted Rand index of 0.734 and normalized mutual information of 0.839. The results show that the proposed semantic maneuver prior improves target alignment and provides a reproducible way to guide unsupervised trajectory clustering, while retaining explicit trade-offs across evaluation metrics. Full article

The main challenge in long-text image–text retrieval lies in the fact that some existing vision–language models mainly rely on global image and text features for matching. Without explicit local alignment constraints, these models may struggle to fully capture complex semantic information in long textual descriptions, such as local objects, fine-grained attributes, and spatial relationships. To address the insufficient modeling of local details in global semantic matching, this paper proposes a patch–word fine-grained alignment retrieval model, named PWFAR. Built upon the Long-CLIP framework, the proposed method introduces an explicit fine-grained alignment mechanism between image patches and text tokens. By using textual words to guide the matching of local image regions, PWFAR enhances the model’s ability to capture local semantic correspondences. Specifically, PWFAR consists of three complementary training objectives: long-text global contrastive learning, short-text compact semantic supervision, and patch–word fine-grained alignment. These objectives are jointly optimized to constrain overall semantic consistency, core semantic stability, and local detail matching relationships. The model is trained on the 888k subset of the ShareGPT4V dataset and evaluated on the COCO2017 and Urban1k datasets. Experimental results show that PWFAR achieves competitive performance across different backbone networks and retrieval directions. Its clearest and most consistent gains are observed on the Urban1k long-text retrieval task, where it outperforms Long-CLIP and Long-CLIP-888k in both retrieval directions. These results indicate that the proposed fine-grained alignment mechanism can effectively improve the model’s ability to capture local semantic relationships in long texts, thereby verifying the effectiveness of PWFAR for long-text image–text retrieval. Full article

Urban greening studies have traditionally emphasized vegetation quantity, while the perceptual implications of horticultural composition and spatial configuration remain less clearly understood. This study investigated how horticultural configurations were associated with multidimensional landscape perception across 10 urban parks in Chengdu, China. A total of 500 standardized landscape images, comprising 50 images per park, were assessed by 150 participants across 17 perceptual dimensions. Vegetation composition, spatial configuration, and conventional greenness indicators were quantified from the images and park-level spatial data. Principal component analysis and PERMANOVA were used to characterize structural gradients among parks, while exploratory factor analysis was used to identify integrated perceptual domains. XGBoost models with five-fold cross-validation were subsequently developed to predict individual perceptual outcomes, and SHapley Additive exPlanations (SHAP) were applied to interpret feature contributions and nonlinear response patterns. Multi-objective optimization was further used to explore hypothetical configuration scenarios involving trade-offs among perceptual objectives. The first two structural principal components explained 65.60% of the variation in horticultural composition and spatial organization, and park configurations differed significantly (PERMANOVA: F = 166.66, p = 0.001). Horticultural typologies differed across 15 of the 17 perceptual dimensions (all p < 0.001), with the largest differentiation observed for nature (ε² = 0.270), species richness (ε² = 0.259), openness (ε² = 0.251), being away (ε² = 0.245), serenity (ε² = 0.236), and enclosure (ε² = 0.234). The XGBoost models showed consistently strong predictive performance, with test-set R² values of 0.692–0.812 and cross-validated R² values of 0.756–0.796. SHAP analyses indicated differentiated and nonlinear associations: vegetation continuity and enclosure were primarily related to restorative immersion, open configurations to spatial accessibility, and ornamental and compositional complexity to affective richness. The optimization results further identified continuous trade-offs among restorative immersion, spatial openness, and affective richness, rather than a single universally optimal configuration. These findings show that landscape perception is associated with the spatial organization and composition of horticultural elements through multidimensional and nonlinear pathways. The study therefore extends vegetation-quantity assessments by providing a configuration-based analytical framework for exploring perceptually balanced urban horticultural environments. Full article

Wastewater treatment plants (WWTPs) are essential infrastructure for urban water management. Their stable operation is critical to effluent quality and public safety. However, wastewater treatment involves complex biochemical processes and extensive electromechanical equipment. Hazards such as sludge flotation in secondary clarifiers, fire, electric shock, and toxic gas poisoning may occur. These hazards can threaten worker safety and reduce treatment efficiency. Traditional inspection mainly relies on manual patrols, fixed-camera monitoring, and experience-based judgment. These methods often have low efficiency, limited coverage, and delayed responses. To address these limitations, this paper investigates robot-based hazard detection for WWTPs. A multisource hazard detection dataset is constructed for secondary clarifiers and confined spaces, including images collected by an inspection robot. Object detection models are then applied to identify typical hazards. Comparative experiments are conducted using Faster R-CNN and several YOLO-series models. YOLOv12 achieves mAP@0.5 values of 0.917 and 0.819 for sludge flotation detection and confined space hazard detection, respectively. It also provides a good balance between detection performance and inference efficiency. The results demonstrate that robot vision combined with object detection can support intelligent inspection in WWTPs. Full article

As urban underground spaces and infrastructure development accelerate, subsurface elements such as buried pipelines, integrated utility tunnels, subway tunnels, cavity defects, and deep-seated hidden hazards become increasingly intertwined. Consequently, urban target detection is characterized by pronounced scale discrepancies, intense environmental interference, and severely confined operational spaces. The transient electromagnetic method (TEM) is highly valuable for rapid surveys and hazard identification in urban underground spaces owing to its inherent advantages, including non-contact operation, adaptability to hardened pavements, high sensitivity to low-resistivity anomalies, and the ability to probe a broad range of depths. In recent years, research has shifted from improving isolated instrumentation to synergistically optimizing sensing platforms, transmitter–receiver systems, anti-interference methodologies, and imaging interpretation workflows. Specifically, small-loop configurations and high-frequency excitation technologies have improved shallow-sounding capabilities in confined urban spaces; anti-interference techniques have increased data reliability in complex noise environments; and apparent resistivity mapping, virtual wave-field migration, and rapid inversion methodologies have enabled profiling results to transition from qualitative identification to fine-scale interpretation. Concurrently, the evolution of ground-towed, UAV-borne, helicopter-borne, and semi-airborne platforms has progressively endowed urban TEM profiling with continuous, mobile, and scenario-specific operational capabilities. Looking to the future, further technical breakthroughs in urban TEM technology are required to improve shallow-resolution, deep-seated penetration, multi-source interference decoupling, and real-time concurrent imaging. Full article

Aesthetic perception of rural streetscapes reflects individuals’ cognitive responses to their surroundings and is central to understanding how landscape preferences are formed. Existing studies using Scenic Beauty Estimation (SBE) are constrained by incomplete indicator systems and overreliance on linear approaches. This study proposes an interpretable machine learning framework that integrates multi-source data to examine the nonlinear influences of streetscape features on SBE. Using Sanguan Village, a water-networked settlement in Jiangsu, we developed a 24-indicator system spanning color, spatial, natural, artificial, and cultural dimensions. Based on 523 panoramic images and aesthetic ratings from 1175 respondents, we compared OLS, DT, MLP, SVR, RF, and XGBoost models. The best-performing XGBoost, combined with SHAP analysis, revealed threshold effects and interaction patterns among variables. Green visibility, architectural aesthetics, building visibility, sky visibility, environmental coordination, and water are the top six feature variables most strongly associated with rural streetscape aesthetic perception, and each exhibits threshold effects. The saturation threshold for green visibility is 0.153, and architectural aesthetics can only make a positive contribution when its score exceeds 3.815. The appropriate range for building visibility is below 0.452, while the optimal value for sky visibility is approximately 0.194. We also explored the context-dependence of these threshold effects across urban and rural settings. This study proposes streetscape optimization strategies focusing on screening key factors, controlling their thresholds, and coordinating the allocation of streetscape features. The interpretable analytical framework for rural scenic beauty established in this research can facilitate evidence-based landscape optimization and provide scientific support for sustainable rural development and tourism in this case. Full article

Small-scale and urban indoor farms typically rely on manual observation, which delays stress detection and yields inconsistent crop quality. While large language models (LLMs) and retrieval-augmented generation (RAG) have been explored for agricultural advisory systems, their integration into a single cloud-free indoor-farming platform that couples multimodal symptom interpretation with autonomous environmental control remains largely unexamined. This study presents an integrated platform built around an agentic AI advisory pipeline that runs entirely on-device on commodity hardware. The pipeline couples a RAG-grounded Mistral 7B language model with a LLaVA 7B vision-language model through condition-based routing, intent classification, multi-step reasoning, and an LLM validation gate, delivering context-aware text and image-based symptom-level guidance from a conversational interface. The advisory layer operates alongside vision-based plant monitoring and a deliberately isolated threshold-based control layer, in which an ESP32 microcontroller autonomously actuates irrigation and lighting against predefined thresholds while a Raspberry Pi 5 performs continuous plant detection and browning monitoring. On Cos lettuce, the advisory pipeline achieved 82.00% weighted accuracy across 50 queries spanning health, symptom, watering, pest, root-health, and growth-stage categories, scored against established plant pathology and postharvest references, with no incorrect responses recorded. The study contributes the design of an agentic advisory pipeline and its integration into a working, cloud-free indoor-farming platform, providing an on-device foundation for intelligent small-scale farming. Full article

Efficient parking space management in urban settings represents a growing challenge owing to the sustained increase in the vehicle fleet. This study presents a comparative evaluation of five object detection architectures —YOLOv8s, YOLOv11s, YOLOv12s, RT-DETR-L and Faster R-CNN—applied to real-time intelligent vehicle occupancy monitoring under variable lighting conditions. The models were trained via transfer learning on a custom dataset of 1463 source images (21,944 annotated instances; expanded to 3511 files and 52,664 instances through offline augmentation of the training subset; three classes: free, occupied and unavailable) captured on a university campus located in Juliaca (Puno region), Peru, at 3824 m a.s.l. under daytime and nighttime clear-sky conditions from a single fixed-camera viewpoint. Each architecture was evaluated in ten independent experiments. Six dataset partitioning schemes of increasing strictness—a random control (R0) plus five leakage-controlled partitions—were evaluated. Under the strictest scheme (D3), simultaneously disjoint in acquisition date and camera viewpoint and therefore the most rigorous generalization estimate obtained in this study, accuracy ranges from mAP@0.5:0.95 of 0.9325 for Faster R-CNN to 0.8763 for YOLOv11s. Under the random partitioning conventionally applied to fixed-camera datasets, the same five architectures fell within 0.0055 of one another, all above 0.985, and their ranking was essentially inverted (Spearman $\rho =-0.80$). The differences in computational efficiency across architectures were statistically significant ($H=47.06$, $p<0.001$). YOLOv8s was the fastest of the four non-dominated architectures under the disjoint partition and was selected in 73.3% of weightings, although it ranked fourth in accuracy; its recommendation therefore rests on computational efficiency under a real-time constraint, whereas deployments that prioritize accuracy are better served by Faster R-CNN. The integrated system YOLOv8s + ByteTrack + FastAPI + Next.js 14 achieved per-slot accuracies of 87.5% and 91.8% under daytime and nighttime clear-sky conditions, respectively, using 1395 observations collected in a single university parking lot. For YOLOv8s, the transition from random to disjoint partitioning costs 0.1085 in mAP@0.5:0.95 (0.9913 to 0.8828), indicating that the near-saturated performance obtained under random partitioning substantially reflects the memorization of a fixed spatial configuration rather than generalization. The results support the feasibility of single-stage CNN architectures for intelligent parking monitoring in high-altitude Andean university environments under the evaluated acquisition conditions. Full article

Land subsidence in soft-soil urban transport hubs arises from the complex coupling of natural geology and intensive anthropogenic activities, yet its spatial differentiation mechanisms and seasonal drivers remain poorly understood in high-development core areas. This study develops a progressive analytical framework integrating Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR), GeoDetector, Gaussian Mixture Model (GMM), and Singular Spectrum Analysis (SSA) to investigate spatiotemporal deformation patterns and driving mechanisms in the Shanghai Hongqiao Transport Hub Core Area from 2015 to 2024 using 209 Sentinel-1A images. Validation against official subsidence contours yields a Pearson correlation coefficient of 0.697 (p < 0.001) and an RMSE of 4.23 mm, confirming good spatial pattern agreement. Urban functional zones and construction stages are identified as the dominant influencing factors, with their interaction exhibiting notable bi-factor enhancement. Six distinct deformation response types are delineated via GMM, and two opposing seasonal signals are distinguished: near-instantaneous precipitation-driven surface loading on shallow soft soil and temperature-driven thermoelastic expansion of built structures. These findings may inform differentiated subsidence management and offer a transferable workflow for analogous soft-soil urban areas. Full article

As China’s urbanization shifts toward quality-oriented development, urban regeneration increasingly prioritizes the perceived quality of public spaces to enhance urban vitality and advance sustainable urban living. This study takes Zhengzhou’s Dongfeng Canal, a revitalized urban core waterfront, as a case to develop a human–machine collaborative analytical framework for exploring nonlinear relationships between visual environmental features and human spatial quality perception. By integrating 779 geolocated panoramic images with volunteers’ subjective rating data, this study adopts deep learning-based semantic segmentation to quantify eight objective visual indicators (e.g., greenness, color diversity, spatial structure). A random forest (RF) model links these indicators to three perceptual dimensions: scenic beauty, safety, and recreational value. Adopting explainable artificial intelligence (SHAP and PDPs), the results indicate that: (1) greenness is positively associated with positive perceptions but exhibits a significant threshold effect; (2) color diversity and waterfront accessibility substantially improve user experience, while excessive uniformity and extreme openness negatively affect perceived spatial quality. These findings challenge the simplistic linear “more-is-better” assumption in urban design and highlight the value of balanced, context-sensitive spatial interventions. This study provides evidence-based, segment-specific strategies for urban waterfront regeneration, advancing people-centered planning that integrates ecological functionality, social inclusivity, and long-term sustainability via Geospatial Artificial Intelligence (GeoAI) and geospatial analytics. Full article

Sustainable urban disaster response requires Earth observation (EO) resources to be selected according to event demands, environmental conditions, sensing capabilities, and urban targets. This study proposes an Observation Linked Open Data (O-LOD)-based Urban Disaster Observation Task (UDOT) enhancement framework for semantic EO resource configuration. O-LOD organizes heterogeneous data through four dimensions, Event, Context, Subject, and Object, which an instantiation algorithm populates as task graphs. Layered GeoSPARQL queries then match thematic and analytical capabilities, qualify orbit-derived observation opportunities against context and object constraints, and rank feasible alternatives using the Observation Capability Evaluation Model (OCEM). Evaluation on the 2020 Khartoum flood and Bobcat wildfire narrowed 202 satellite–sensor pairs to three flood-capable and four wildfire-capable pairs and returned two Khartoum and eight Bobcat ranked opportunities, with complete queries executing in 3.0 s and 0.07 s. Constraint ablation and resolution sensitivity analyses identified the conditions governing the feasible set. Publicly accessible Sentinel, Landsat, and MODIS products corroborated both retained and excluded results, supporting water-extent and burn-severity mapping where coverage, spectral bands, and image quality met the task requirements. O-LOD therefore provides a traceable semantic link from disaster observation demand to qualified and ranked EO opportunities and subsequent image assessment, supplying task-oriented inputs for downstream scheduling and supporting context-aware sensing for sustainable urban disaster response. Full article