Existing methods for evaluating urban greenway restorative environments lack objectivity, efficiency, and theoretical integration. The purpose of this research is to develop a restorative environmental assessment framework for urban road binding using deep learning, street-view image data, and environmental psychology theory. It uses a semantic segmentation model called DeepLabV3+ to collect six visual environment features which are otherwise difficult to represent numerically. At the same time, it offers a methodological path for the interdisciplinary integration of artificial intelligence technology and environmental psychology theory. The calculation model of the comprehensive recovery index is constructed in four dimensions based on attention recovery theory. According to empirical analysis, this framework can successfully identify systematic differences in the restorative dimension of different types of binding paths. The presence of greenness can make a large positive contribution to the restorative effect, while building occlusions can have an inhibitory effect. The evaluation results are quite consistent with theoretical predictions and have good robustness in parameter Settings. The findings of the study offer a scientific evaluation tool for accurate diagnosis and optimization improvement of the urban road binding restorative environment. At the same time, it offers a methodological path for the interdisciplinary integration of artificial intelligence technology and environmental psychology theory.

This review utilizes a scoping methodology to analyze 62 relevant studies, examining how environmental characteristics shape perceptions of safety in urban green spaces. It distinguishes three core concepts of safety perception and develops a classification system encompassing four categories of environmental characteristics: maintenance and aesthetics, visual obstruction and imagination, escapeability and wayfinding, and spatial vitality and social presence. This framework elucidates the psychological mechanisms through which these characteristics influence perceived safety. The findings indicate that maintenance and aesthetic characteristics primarily operate by risk identification and regulatory impression, while the effects of visual obstruction are mediated by threat-related imagination. Escapeability and wayfinding characteristics facilitate risk-avoidance conditions, and spatial vitality characteristics contribute through interpersonal relationships and expectations of assistance. Environmental characteristics interact in compensatory, weakening, or covarying ways, with their significance moderated by temporal, demographic, and contextual factors. Building on this evidence, the review proposes the risk control-escape possibility-assistance availability theoretical model. The model presents a three-layer architecture linking the physical environment, environmental perception, and safety assessment, operationalizing safety perception across three measurable dimensions. It offers theoretical guidance for optimizing safety in urban green spaces, while future research should focus on empirical validation of the model and its cross-cultural applicability. • Distinguished three safety perception concepts • Classified environmental characteristics into four categories affecting safety perception • Analyzed the moderating role of contextual factors • Reviewed interactions of multiple factors • Proposed the REA theoretical model.

Association between the urban environment, parents' related concerns and perceptions, and childhood obesity and lifestyle in Barcelona, Spain.

Migration of antibiotic resistance genes in process of biodegradation of sulfonamide antibiotics in biofilm-sediment: Mechanisms, microbial communities, and driving factors.

Human-nature interactions can act as transdiagnostic factors in the prevention and salutogenesis of adverse mental health conditions related to urban stressors. However, more research is needed to investigate the role of both environmental and individual characteristics for wellbeing outcomes. Using interdisciplinary methods, this study investigated relationships between restoration outcome and exposure to objectively measured physical greenspace characteristics with perceived environmental quality as a potential mediating factor. Based on greenspace and survey data (N = 728) from 48 plots within 31 greenspaces in the inner-city of Munich, Germany, mediation models with greenspace characteristics as predictors, perceived beauty, diversity, and naturalness as mediators, and restoration outcome as the dependent variable were tested. There was a partial mediation of the relationship between restoration outcome and greenspace size by perceived beauty and perceived diversity, respectively. Vegetation density of the subcanopy was positively associated with restoration outcome, but no mediation was apparent. Perceived beauty, diversity, naturalness, time spent in the greenspace and nature connectedness were positively related to restoration outcome. Results emphasize the importance of perceived environmental quality for restoration outcome. • interdisciplinary method to measure and explain restoration in urban greenspaces • greenspace size and vegetation density were positively related to restoration • perceived beauty, diversity, and naturalness were positively related to restoration • nature connectedness and visit duration were positively related to restoration • results emphasize the importance of perceived environmental quality for restoration

Multiple sclerosis in the All of Us Research Program: Prevalence and associated demographic and geographic characteristics.

Agricultural systems in the European Union face simultaneous pressures from demographic decline, economic fragility, and biodiversity loss. The shrinking share of young farmers raises concerns about the long-term viability of rural areas, while monoculture and production intensification continue to erode crop diversity and ecosystem resilience. Although generational renewal policies aim to address demographic challenges, their potential to intersect with environmental or resilience-related dimensions remains insufficiently explored, particularly in structurally constrained agricultural contexts such as Greece. This study investigates how the EU's Common Agricultural Policy (CAP) Young Farmers Measure, designed primarily to support generational renewal, relates to crop diversification and resilience-related characteristics among young farmers. The analysis addresses three questions: whether young farmers who intend to remain in agriculture beyond the mandatory support period exhibit different diversification trajectories; whether distinct socio-economic and agronomic profiles are associated with heterogeneous diversification behaviours; and how resilience-related attributes vary across diversification levels and across the farmer profiles identified through clustering. Farm level and socio-economic data from young farmers in Greece were used to quantify crop diversification through a standardized Crop Diversification Index (CDI). K-means clustering was applied to identify heterogeneous farmer profiles based on structural, socio-economic, and diversification characteristics. A multidimensional Young Farmers Resilience Index (YFRI) was constructed using Min–Max normalization across ten economic, social, and environmental indicators, providing a composite description of resilience-related attributes. The methodological approach is descriptive and exploratory, focusing on variation within the beneficiary population rather than on causal inference. Young farmers intending to remain in agriculture beyond the mandatory support period displayed higher and more variable CDI values than non-continuing farmers, indicating distinct diversification trajectories associated with long-term engagement. The cluster analysis revealed three structurally and behaviourally differentiated farmer profiles, each exhibiting characteristic diversification patterns shaped by farm size, production orientation, and household composition. YFRI scores also varied across clusters, reflecting the interaction of structural capacity, socio-economic conditions, and diversification profiles. These findings highlight substantial heterogeneity within the beneficiary population and illustrate how generational-renewal policies intersect with diversification and resilience-related attributes under the structural conditions of Greek agriculture. The study provides a replicable framework for examining how socio-economic context measures within the CAP relate to environmental and resilience-relevant characteristics. By demonstrating the diversity of pathways through which young farmers combine structural conditions, behavioural orientations, and crop portfolios, the findings support more integrated policy design capable of jointly addressing demographic, environmental, and structural challenges. • Generational renewal, biodiversity and social resilience challenge agricultural systems. • Young farmers with long-term engagement intentions exhibit higher diversification levels. • Young farmers' socio-economic and agronomic profiles co-shape diversification. • Generational renewal policy should be linked with environmental and resilience dimensions.

When feeling safe becomes risky: A VR-EEG-computer vision framework for analyzing cyclist safety in dynamic traffic environment.

Built environment features: Predictors or effect modifiers of post-disaster mental health outcomes? A systematic review.

Location-based accessibility is widely assessed using zonal frameworks that aggregate high-resolution results into summary statistics. This aggregation-induced error is often assumed to be negligible, yet this assumption is rarely verified and may obscure critical disparities. This study introduces “Accessibility Misrepresentation” as the deviation between high-resolution accessibility and zonal proxies. Using building-level public transport accessibility in Metropolitan Melbourne, the research evaluates the magnitude, spatial patterns, and equity implications of misrepresentation. Results show systematic variation across travel time thresholds, built environment characteristics, aggregation methods, and service levels. Missed detection of populations without accessibility peaks at 15–20 min thresholds commonly used in neighbourhood accessibility policies, predominantly affecting densely populated middle suburbs where public transport catchments misalign with administrative boundaries. Continuous errors in accessibility values show no systematic directional bias; however, minorities can experience substantial misstatements sufficient to alter normative assessments. Equity analysis reveals disproportionate impacts on middle-status populations often overlooked by conventional frameworks. Population-weighted medians substantially outperform means in reducing misrepresentation. However, no single statistic adequately captures internal variation, particularly with multimodal distributions. A dual-scale approach is recommended: high-resolution computation to characterise within-zone distributions, combined with zonal summaries accompanied by distributional diagnostics, including share of residents without accessibility and upper-tail error indicators. This approach enhances transparency, supports equity-focused and defensible planning decisions without costing additional resources. • Zonal summaries cause “Accessibility Misrepresentation”. • Well-served zones may mask large accessibility gaps. • Middle socioeconomic group has large underserved subpopulations. • Medians outperform means as summaries of zonal accessibility. • Dual-scale analyses expose disparities and preserve interpretability.

Differential Association Between Surrounding Greenness and Mortality in Individuals With Coronary Heart Disease.

The interplay of home and work neighbourhood environment characteristics and associations with active commuting

Machine learning-based modeling for monitoring and predicting the detection rate and severity of pathogenic microorganisms in seafood.

P31. Predicting Mortality After Cardiac Surgery Using Deep Learning-Derived Built Environment Features

Effect of natural and artificial surroundings on perceived restorativeness and affective states: Evidence from a satellite image segmentation-based method

ABSTRACT Widespread disturbance to frugivory networks endangers ecosystem functioning. Carbon‐rich tropical forests are particularly vulnerable to seed dispersal limitation from frugivore declines. However, understanding the ecological consequences of frugivore declines in tropical forests is challenging due to incomplete knowledge of existing frugivore‐plant interaction networks. Here, we assessed the impact of frugivore loss on aboveground biomass (AGB) across 260 tropical forest plots in Gabon, using imputed interaction networks between 122 frugivore species and 99,349 individual trees. We investigated (1) how faunal degradation of frugivores affects AGB, (2) the relative importance of different vertebrate taxa to AGB maintenance, (3) the role of dietary redundancy and seed dispersal compensation in AGB change, and (4) geographic patterns in AGB change. Simulated degradation of endangered frugivores reduced AGB, but results varied by taxon: simulated degradation of elephants, apes, monkeys, ungulates, and bats decreased AGB, but degradation of carnivores and birds increased AGB. Results were sensitive to imputed interaction failing to account for unobserved interactions may underestimate future AGB storage. Results were also sensitive to compensatory effects: assuming seed dispersal compensation due to dietary redundancy dampened, and in some cases reversed, the magnitude of AGB change. Anthropogenic and environmental plot characteristics predicted vulnerability to AGB change. AGB loss tended to occur in forests at low latitudes, low elevation, low precipitation, and farther from villages. Primary forests were more vulnerable to AGB loss than secondary forests. Accounting for ecological interactions across broad taxonomic groups and spatial scales—not just charismatic taxa and in well‐studied areas—is critical for understanding the nuanced effects of frugivore declines on ecosystem functioning.

BMI is influenced by both genetic and environmental factors, including features of the obesogenic environment such as walkability. This study investigated the interplay between residential walkability, genetics, and BMI among 4312 individuals from two Finnish twin cohorts (mean age: 43). Residential walkability was quantified using a composite index including built and natural environmental features. Multiple linear regression, adjusted for sociodemographic factors, showed that higher walkability was associated with lower BMI (coefficient: -0.02, 95% CI: -0.04, -0.01), but pairwise twin analyses indicated that this association was not independent of genetic and early shared environmental influences. Univariate twin modeling revealed that additive genetic effects accounted for 22% of the variation in walkability when participants were middle-aged. Bivariate moderation twin modeling showed that the additive genetic influence on BMI was significantly stronger among individuals living in areas with average or moderately low residential walkability. The unique environmental component played a larger role among those living in areas with either very low or very high residential walkability. These findings underscored the complex gene-environment interplay between walkability and BMI. While genetic susceptibility cannot be modified, public health strategies that focus on the obesogenic environment, such as improving walkability, may still help mitigate obesity risk.

Spatial dynamics of biodiversity and cycling behaviour: A geographical analysis using crowdsourced data from Strava metro.

Small-scale beauty facilities constitute a distinctive occupational setting characterized by simultaneous exposure to multiple volatile organic compounds (VOCs) emitted from hairdressing, nail services, and solvent-based cleaning. This study aims to characterize workplace environmental conditions, quantify concentrations of priority VOCs, and assess non-carcinogenic health risks under different exposure scenarios in small-scale beauty facilities in Vietnam. A field-based design was applied across four facilities, integrating structured site surveys, air monitoring, and scenario-based risk assessment under baseline, task-based, and adverse conditions. Toluene and formaldehyde were measured in two sampling campaigns, while acetone was included as an indicator of mixed exposure. Real-time measurements of formaldehyde (HCHO) and total VOCs (TVOC) were conducted to capture short-term variability. Results show that all facilities were micro-scale (15–40 m²) with prolonged exposure duration and widespread open chemical handling practices. Toluene concentrations ranged from 0.014 to 0.024 mg/m³, formaldehyde from 0.005 to 0.027 mg/m³, and acetone up to 0.066 mg/m³. End-of-shift HCHO and TVOC reached 0.45 ppm and 0.47 ppm, respectively. Formaldehyde exhibited greater variability and dominated cumulative risk. One facility recorded a hazard index (HI) exceeding 1, increasing to 1.2872 under adverse conditions. The findings highlight that mixed VOC exposure is strongly influenced by ventilation, service intensity, exposure duration, and chemical handling practices.

Objective To investigate how AI-provided explanations impact efficiency, diagnostic accuracy, user perceptions, and workflow integration in ophthalmologists’ clinical diagnostic and treatment workflows, this study explores the challenges in human-AI interaction with transparency features in time-sensitive environments. Background While explainable AI (XAI) aims to foster trust and understanding, its introduction into complex work domains can unintentionally increase cognitive load and disrupt workflows, especially in high-stakes medical settings, potentially impairing system performance. Method The multi-phase, mixed-methods study included two parts. Study 1 ( N = 32) was a between-subjects experiment in which ophthalmologists diagnosed diabetic retinopathy with AI support, with or without visual explanations (e.g., highlighting lesions). Measures included diagnostic accuracy, diagnostic time, trust, and usefulness. Study 2 ( N = 11) employed qualitative methods, including think-aloud protocols and interviews, to explore clinicians’ experiences with AI in daily (treatment) workflows. Results In Study 1, explanations did not improve accuracy but increased decision time, reducing efficiency. Trends suggested lower perceived usefulness and trust in the explanation condition. Qualitative data from Study 2 supported these findings; clinicians found explanations time-consuming and disruptive, questioning their practical value, especially for routine cases. Conclusion A critical trade-off exists between pursuing AI transparency and the operational demand for efficiency. Explanations, while well-intentioned, can function as efficiency pitfalls in time-pressured clinical practice, highlighting the boundary conditions and challenges in designing effective human-AI systems. Application These insights inform future AI system design, favoring adaptable, on-demand explanations tailored to user needs. Such a user-centric approach supports complex cases without impeding routine task efficiency.