Search Results (810)

Accurate short-term prediction of urban waterlogging depth is essential for real-time flood risk management in rapidly urbanizing areas under climate variability. Departures from quasi-stationary operating conditions, caused by changes in drainage efficiency, inflow patterns, or measurement quality, weaken historical rainfall–water depth relationships, making purely data-driven models prone to error accumulation. In this study, a GeoAI-based, physics-enhanced machine learning framework is proposed, which translates the water balance principle into Physical Violation Scores (PVSs) and incorporates them as additional input features. PVSs remain zero under expected rainfall–water depth behavior and become positive only under departure scenarios, providing sparse and lightweight diagnostic signals without modifying model structures or loss functions. The framework is implemented on five algorithms (Support Vector Machine, Multilayer Perceptron, Random Forest, Extremely Randomized Trees, and XGBoost) to construct physics-enhanced models (PEMs). These are evaluated against original feature models (OFMs) across 1 h and 2 h forecasting horizons. Results show that most PEMs improve prediction performance compared with their corresponding OFMs, with more pronounced gains at the 2 h horizon. Bootstrap analysis and RMSE-based error amplification factor further indicate comparable or lower R² variability and reduced recursive error amplification for most PEMs. Interpretability analyses show that rainfall forcing and water-depth persistence remain dominant predictors, whereas PVSs act as auxiliary diagnostic signals. Overall, the proposed framework provides a lightweight, reliable, interpretable, and scalable GeoAI approach for incorporating water balance knowledge into short-term urban waterlogging prediction, supporting climate resilience and smart urban water management. Full article

Urban parks are often regarded as carbon sinks, yet their net carbon performance depends on the balance between vegetation carbon uptake and maintenance-related emissions, as well as the accurate representation of within-park spatial heterogeneity. This study used backpack LiDAR, field vegetation surveys, and maintenance inventories to quantify annual carbon sequestration, maintenance emissions, and net carbon budget in 44 plots covering nine biotope types across 16 parks in central Xianyang, China. A four-level biotope classification incorporating canopy openness, ground cover, tree composition, and vertical stratification was applied to link LiDAR-derived three-dimensional structure with ecological-unit-level carbon accounting. Carbon sequestration and net carbon budget differed significantly among biotopes, whereas maintenance emissions did not. Closed broadleaved single-layer forest showed the highest carbon sequestration density (0.772 kg C m⁻²), while hard-surfaced partly closed broadleaved single-layer forest showed the lowest value (0.132 kg C m⁻²). Closed woody biotopes functioned as strong carbon sinks, partly closed biotopes as weak sinks, and the partly open short-grass biotope was the only carbon source. Three-dimensional green volume density was the strongest positive predictor of net carbon budget (β = 0.417, p = 0.032), followed by stem density (β = 0.276, p = 0.048), whereas irrigation-related emissions showed a significant negative coefficient (β = −0.276, p = 0.021). Carbon sequestration explained more variation in net carbon budget than maintenance emissions (adjusted R² = 0.409 vs. 0.134). These findings suggest that backpack LiDAR can support fine-scale identification of priority carbon-sink units in urban parks and that low-carbon park management should prioritize three-dimensional woody vegetation structure while reducing high-input irrigation where feasible. Full article

Urban forests support wildlife populations across North America and the world. Yet, challenges remain for research and practice to integrate wildlife habitat as a core component of the myriad objectives that urban foresters manage. Ecosystem services have been adopted as a dominant paradigm in urban forestry for both advocacy and management, yet accounting for contributions to wildlife habitat does not fit squarely within typical ecosystem service frameworks. The i-Tree program, a suite of urban forest ecosystem service models and tools developed by the US Forest Service, presented an opportunity to link widely used urban forest assessment field protocols with indicators of suitable habitat. In this reflection piece, we demonstrate how the i-Tree Wildlife project assessed whether urban forest structural assessment methods could be applied to assess wildlife habitat provision, operationalizing the fundamental question “How do urban forests support wildlife?” We describe the development process for integrating bird habitat suitability models for 12 species present in the northeastern US, ten native and two non-native birds, into the flagship i-Tree Eco tool. We offer reflections, challenges, and opportunities from this process. Ultimately, the improvement of ecosystem assessment tools like i-Tree can assist practitioners who aim to manage healthy and productive urban forests that benefit people and wildlife. Full article

(1) Pholidoptera griseoaptera (De Geer, 1773) (Orthoptera, Tettigoniidae) is a common and widespread inhabitant of forest edges in Europe and may therefore serve as a suitable model species for understanding past and future changes in forest wildlife. (2) We recorded the presence or absence of the species in 189 forest and forest-edge plots within the Kaluga Region using acoustic observations and pitfall trapping, and analysed the data using logistic regression. (3) Across the region, the main positive factor affecting species presence was the dominance of nemoral herbs in the herb layer. The main negative factors were habitat isolation caused by physical barriers and location within moraine plains formed during the late stage of the Moscow glaciation. The presence of coniferous tree species and spatial autocovariation were also significant factors, although their contributions were relatively small. The abundance of Ph. griseoaptera was higher in forests located within river valleys. Within Kaluga, the long-term persistence of tree vegetation and habitat isolation were the main significant factors affecting species occurrence. The smallest urban habitat occupied by the species covered approximately 13 ha, whereas the total area of unmown patches within this habitat was only about 0.2 ha. (4) Ph. griseoaptera may be used as an indicator of the long-term persistence of broadleaved deciduous (nemoral) forests. Under conditions of high urbanization, however, the species may become threatened. Full article

The accelerated growth of cities has intensified interest in the ecosystem services provided by urban forests, increasingly conceptualized as socio-ecological systems (SESs). This study presents a structured narrative review combined with bibliometric analysis of research published between 2010 and 2025 to examine how urban forests are addressed in relation to ecosystem service provision and climate change adaptation. The literature search and screening process followed procedures informed by the PRISMA framework to enhance transparency in the identification and selection of relevant studies. The results reveal a marked increase in scientific production during the last decade, with approximately 70% of publications concentrated in five countries: the United States, China, Italy, Canada, and Brazil. Although research methodologies are diverse, a strong bias toward quantitative ecological models—particularly tools such as i-Tree—persists, often prioritizing carbon sequestration while overlooking social dimensions of urban forest governance. A key finding is the disconnect between objectively modeled ecosystem services and the benefits perceived by citizens, which may influence the long-term sustainability and acceptance of urban green infrastructure. In addition, emerging research highlights the importance of considering ecosystem disservices, such as allergenic pollen, infrastructure conflicts, or maintenance costs, within urban forest planning. Finally, the review identifies a significant research gap in Latin America and the Caribbean, where rapid urbanization requires context-specific socio-ecological approaches. Advancing urban forest management therefore requires transdisciplinary frameworks that integrate ecological processes, social perception, governance, and climate adaptation to support more resilient and equitable cities. Full article

Stomatal conductance (g_S) is a key driver of urban tree transpiration and heat mitigation potential, but few studies compare machine learning models for predicting g_S across multiple species in cities. This study applies five machine learning models (XGBoost, Random Forest, Support Vector Machine [SVM], Neural Network, and Random Forest Adjusted) and two classical models (Multiple Linear Regression and Generalized Additive Model [GAM]) to predict g_S for 15 dominant tree species in the urban forest of Mexico City using environmental variables (air temperature, vapor pressure deficit, photosynthetically active radiation, and leaf water potential). We trained the models on a dataset of 300 observations per species, with 70% for training, 20% for validation, and 10% for testing, and evaluated performance using RMSE, MAE, and R². Overall, XGBoost, GAM and SVM consistently showed the highest predictive performance, with R² values up to 0.997, while the Neural Network and Multiple Linear Regression performed poorly (R² ≈ 0.10–0.65). Model performance varied substantially among species, with XGBoost performing best for seven species, GAM for four, and SVM for four. Our results demonstrate that tree species g_S can be accurately predicted using machine learning models in urban forests; however, model choice should account for species differences in performance. We therefore recommend that practitioners consider ensemble approaches of multiple models, excluding only the Neural Network, when selecting predictors for individual species. Full article

Tree mechanical stability is essential for forest management and urban safety. Although static pulling tests are currently the standard for non-destructive advanced risk assessments, these tests have significant methodological limitations. Large trees require high applied forces to produce measurable signals, which poses safety risks and causes equipment wear. Conversely, structurally compromised ancient, veteran, or dead trees (snags) may yield poor signal-to-noise ratios at low loads, leading to unstable model fits and unreliable safety factor extrapolations. Additionally, standard inclinometers often experience interference from motion-induced accelerations. This study introduces a high-resolution, low-noise measurement approach that resolves small basal inclinations and stem bending responses. This method uses laser-based tracking to monitor stem bending, torsion, and inclination under mechanical load. Experimental data were collected by combining traditional pulling tests with this novel system, as well as by conducting a pilot study that monitored tree movement during low-strength wind gusts. The proposed method enables more precise characterization of the initial load-response curve. Improving the signal-to-noise ratio at lower force levels allows for more robust safety extrapolations. When combined with a 3D LiDAR scan, the method can reveal deviations from the theoretical bending line in order to locate internal defects and variations in wood properties. These findings bridge a critical gap in tree risk assessment by improving the applicability of static testing to massive trees, as well as ecologically valuable yet structurally vulnerable snags and ancient and veteran trees. Full article

Urban green spaces provide essential ecosystem services, yet mismatches between subjective perceptions and objective assessments may constrain effective planning. This study examines the correspondence between perceived and measured ES across two contrasting urban green spaces in Shanghai: Century Park, a managed urban park, and Sanlin Green Space, a naturalistic urban forest. Objective ecosystem services (regulating, supporting, and cultural) were quantified using UAV-based biotope mapping and indicators including biophysical metrics (Net Primary Production, Water Retention, PM10 removal, and Land Surface Temperature), structural diversity indices (Shannon Diversity of land cover, vegetation, and tree structure), and visual–spatial proxies (Green View Index, Sky View Index, Water View Index, color metrics, and spatial openness). Subjective perceptions were derived from panoramic image-based questionnaires, with perception scores predicted using XGBoost and aggregated via SHapley Additive exPlanations (SHAP). Correlation analyses, spatial regression models, and partial least squares structural equation modeling were applied to explore relationships and pathways. Results show weak but significant positive associations in the urban park, whereas no overall correspondence was observed in the urban forest. Spatial mismatches were concentrated in biotopes with distinctive visual–ecological features and in fragmented areas. Green View Index is associated with higher perceptions in both sites, while the Sky View Index reduced perception in the forest context. These findings highlight strong context dependence in perceived–measured ecosystem service relationships and underscore the importance of integrating ecological structure and visual legibility in the design and management of the studied urban green spaces in Shanghai. Full article

Urban trees are increasingly deployed as nature-based infrastructure to mitigate heat and manage stormwater, yet quantitative guidance on how species traits and site context shape transpiration remains fragmented. We conducted a systematic metadata analysis of seven field studies that measured daily transpiration rate in urban settings using heat-pulse methods. The units and spatial scales reported were harmonized with the sap flow density across active sapwood (J_s, g H₂O/${\mathrm{cm}}^2$/day) by converting reported stand transpiration and the outer 2 cm of sapwood sap flux using established Gaussian radial distribution functions for angiosperms and gymnosperms, which account for the non-linear decline in sap flux from the vascular cambium to the heartwood boundary. We then summarized distributions and tested group differences with Kruskal–Wallis and Dunn post hoc comparisons across wood anatomy, climate, soil texture, and planting configuration. Conifers exhibited significantly lower median $J_s$ (39.76 g/${\mathrm{cm}}^2$/day) than angiosperms, while the ring-porous group (median $J_s$ = 92.25 g/${\mathrm{cm}}^2$/day) and diffuse-porous groups (median $J_s$ = 96.70 g/${\mathrm{cm}}^2$/day) had similar distributions overall. Climate-modulated responses within wood anatomy groups differed, with diffuse-porous species exhibiting the highest median $J_s$ (152.59 g/${\mathrm{cm}}^2$/day) in semi-arid regions, ring-porous species maintaining comparatively stable median $J_s$ across climates (varying slightly between 80.72 and 99.32 g/${\mathrm{cm}}^2$/day), and conifers reaching their highest median $J_s$ (69.90 g/${\mathrm{cm}}^2$/day) in humid continental sites. Soil texture effects were consistent with moisture availability: sandy loam generally reduced $J_s$ relative to loam or silt loam for conifers and diffuse-porous species. Across anatomies, single trees transpired more than clustered trees or closed canopies. For example, planting as single trees increased median $J_s$ by 86% in conifers (from 33.01 to 61.37 g/${\mathrm{cm}}^2$/day) and by 45% in diffuse-porous species (from 81.31 to 118.25 g/${\mathrm{cm}}^2$/day). These results provide actionable ranges and contrasts to inform species selection and planting design for urban greening and runoff reduction, while highlighting data gaps for future research. Ultimately, by matching specific wood anatomies and planting configurations to local soil and climatic conditions, urban planners and ecohydrologists can strategically optimize urban forests to maximize targeted ecosystem services. Full article

Horse chestnut (Aesculus hippocastanum L.) is a widely planted ornamental and urban tree valued for its aesthetic and ecological functions. In recent years, declining health of horse chestnut in urban environments has been increasingly reported, often associated with a complex of biotic and abiotic stressors. During a health survey of A. hippocastanum trees growing along an urban road corridor in Warsaw, Poland, extensive bark necrosis and branch dieback were observed. The aim of this study was to identify the causal agent of these symptoms using morphological, cultural, molecular (ITS rDNA), and pathogenicity tests under controlled conditions. Fungal isolates were obtained from necrotic tissues and were consistently identified as Kalmusia variispora based on ITS sequence analysis (99.0–99.6% similarity to GenBank references) and characteristic morphology. Pathogenicity tests fulfilled Koch’s postulates, reproducing necrotic lesions and cambial damage similar to those observed in the field. To our knowledge, this is the first documented report worldwide of K. variispora infecting A. hippocastanum. The findings expand the known host range of this opportunistic Didymosphaeriaceae species and highlight its potential role in bark and wood disease complexes of urban trees. Further research is needed to assess its distribution, genetic diversity, and epidemiological significance in urban forest ecosystems. Full article

Air pollution caused by fine particulate matter (PM_2.5) poses a serious public health threat in many South Asian megacities where monitoring networks remain limited. Lahore, Pakistan—frequently ranked among the world’s most polluted cities—still lacks reliable short-term PM_2.5 forecasting systems. This study develops a performance-weighted ensemble machine learning framework that integrates satellite observations, meteorological reanalysis data, and ground monitoring measurements to improve daily PM_2.5 prediction. Eleven predictor variables were processed using a unified Google Earth Engine pipeline, including MODIS aerosol optical depth, Sentinel-5P trace gases (CO, NO₂, SO₂), and ERA5 meteorological parameters. Four tree-based machine learning algorithms—Random Forest, XGBoost, LightGBM, and CatBoost—were trained using daily observations from 2019 to 2023. Model evaluation using an independent 2024 dataset showed strong predictive capability, with Random Forest achieving R² = 0.77 (RMSE = 24.75 µg m⁻³), XGBoost R² = 0.76 (RMSE = 26.32 µg m⁻³), CatBoost R² = 0.73 (RMSE = 30.39 µg m⁻³), and LightGBM R² = 0.70 (RMSE = 32.75 µg m⁻³). To further enhance performance, the best models were combined into a weighted ensemble (RF 0.5, XGBoost 0.3, and CatBoost 0.2), which produced the highest validation accuracy (R² = 0.77; RMSE = 23.37 µg m⁻³). Statistical testing using paired t-tests and Diebold–Mariano tests confirmed that the ensemble significantly reduced forecast errors compared with individual models. Feature importance analysis revealed that surface pressure, temperature, CO, and NO₂ were the most influential predictors of PM_2.5 variability. The proposed framework demonstrates that combining satellite data, reanalysis meteorology, and ground observations through ensemble learning can provide accurate and scalable air quality forecasting for data-limited urban environments. Full article

Understanding the interplay between tree structure and seasonal dynamics, particularly cross-species, is crucial for managing urban forest ecosystems. However, balancing fine-scale inventory of trees with large-area mapping of forest ecosystems is a challenge. This endeavor integrates multi-temporal Sentinel-2 satellite remote sensing (RS) imagery with high-density handheld light detection and ranging (LiDAR) point clouds to launch exploratory analyses of cross-species phenological–structural relationships (CSPSRs) in urban park trees. We derived plot-level phenological metrics (e.g., start of growing season, SOS) and quantified fine-scale three-dimensional (3D) tree structural attributes (e.g., tree height and trunk curvature), respectively. Then, we investigated how the 3D structural attributes of urban park trees covary with their phenological traits. The results revealed the underlying CSPSRs, e.g., a weak but significant negative correlation between SOS and tree height in the study area. The derived CSPSRs demonstrate that tree structure is a key predictor of its phenology, even across species. Overall, the integrated RS approach can provide a robust framework for associating the structure and phenology of trees, offering valuable insights for the ecological management of urban forests. Full article

The increasing scarcity of urban water resources, particularly in regions with intermittent supply and household water storage tanks, demands monitoring approaches capable of identifying end-use consumption patterns beyond aggregated volume measurements. Framed primarily as a feasibility study, this research presents an IoT-based framework for the automated classification of residential water consumption activities using water-level dynamics and supervised machine learning. A non-intrusive sensing architecture based on hydrostatic pressure measurements was deployed in a domestic water tank and integrated with a cloud-based data acquisition and processing platform. Five representative household states and activities were considered: tank refilling, stable state, toilet flushing, washing clothes, and taking a bath. A labeled dataset comprising 4396 consumption events was used to train and evaluate Decision Tree, Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors, and Recurrent Neural Network (LSTM) models using features derived from water-level variations. All models achieved high performance, with accuracies above 0.92 and weighted F1-scores up to 0.93. The evaluated models showed highly comparable results, with the SVM (RBF) achieving a slightly higher accuracy (0.9307) in this evaluation setting, while ROC analysis showed AUC values between 0.97 and 1.00 across all classes, indicating strong discriminative capability. Additionally, specific activities such as washing clothes and tank refilling achieved precision and recall values above 0.95. These findings confirm that hydrostatic pressure-based sensing, combined with machine learning, enables reliable identification of domestic water-use events under intermittent supply conditions. The proposed approach provides actionable insights for demand management, leak detection, and user awareness, supporting more efficient and sustainable residential water consumption strategies. Full article

Bike sharing is an established component of urban mobility infrastructure, offering a low-emission alternative to motorized transport for short trips in cities worldwide. Accurate demand forecasting is essential for efficient system operation: it enables better bike redistribution, reduces user wait times, and lowers the operational costs associated with rebalancing. This study evaluated multiple ensemble strategies for hourly bike-sharing demand prediction, comparing bagging methods (Random Forest, Extra Trees), boosting methods (AdaBoost, Gradient Boosting Regressor, Histogram-based Gradient Boosting Regressor), and a Voting ensemble, while systematically investigating the impact of hyperparameter optimization. A repeated hold-out protocol was used, in which the dataset was randomly divided into 80% training and 20% test subsets across 10 random splits; 5-fold cross-validation was applied within each training fold exclusively for hyperparameter tuning, ensuring the test set remained unseen during model selection. Random Search and Bayesian Optimization were compared under identical budgets of 60 configurations per model. Results show that optimization substantially improves all models, with the most pronounced gains for AdaBoost (58% RMSE reduction) and Gradient Boosting Regressor (45% RMSE reduction). A Voting ensemble combining a Random Search-tuned Gradient Boosting Regressor and a Bayesian-optimized Histogram-based Gradient Boosting Regressor achieves the best overall performance (RMSE of 38.48, R² of 0.955) with the lowest variance among all repeated splits. Feature importance analysis confirms that hour of day and temperature are the dominant demand drivers, consistent with the operational patterns of urban bike-sharing systems. The performance difference between Random Search and Bayesian Optimization is negligible for most models, suggesting that well-designed search spaces allow simpler strategies to achieve competitive results. A controlled comparison conducted under identical experimental conditions shows that the Voting ensemble is statistically equivalent to XGBoost and nominally better than LightGBM, while CatBoost achieves a statistically significant advantage, highlighting it as a strong individual alternative. Full article

Road traffic accidents at intersections pose a persistent challenge in Riyadh, Saudi Arabia, contributing significantly to public health burdens and economic losses. Traditional statistical approaches often fail to capture the complex, non-linear interactions among geometric design, traffic parameters, and accident severity. This study develops a multi-methodological machine learning framework to predict intersection accident severity using the Equivalent Property Damage Only (EPDO) metric. Historical data (2017–2023) from Riyadh Municipality for 150 high-risk intersections were analyzed, incorporating predictors such as service road distance (SRD), U-turn distance (UTD), median width (MW), peak hour volume (PHV), heavy vehicle percentage (HV%), and injury/frequency counts. Six algorithms, i.e., Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, Linear Regression, and Artificial Neural Network, were compared using a 70/30 train–test split and k-fold cross-validation in this study. The Gradient Boosting model achieved superior performance (R² = 0.89 with MSE = 63.43 and RMSE = 7.96) and was selected for final deployment. SHAP feature importance analysis revealed minor injuries (MIs), serious injuries (SRIs), and fatalities (FAs) as the most important dominant predictors, with geometric factors (UTD, MW) and traffic composition (HV%) providing actionable infrastructure insights. The model ranked intersections and identified the “Jeddah Road with Taif Road” (predicted EPDO = 137.22) as the highest-risk location. Evidence-based recommendations include enforcing the minimum 300 m U-turn buffers with staggering service road exits ≥150 m and restricting heavy vehicles during peak hours. The scalable framework developed in this study supports the data-driven prioritization of safety interventions and aligns with sustainable urban mobility goals and offers transferability to other metropolitan contexts worldwide. Full article