Search Results (81)

Posidonia oceanica seagrass, endemic to the Mediterranean Sea, provides ecological goods and ecosystem services of paramount importance. In shallow and sheltered bays, P. oceanica meadows can reach the sea surface, with leaf tips slightly emerging, forming fringing and barrier reefs. During the 20th century, P. oceanica declined conspicuously in the vicinity of large ports and urbanized areas, particularly in the north-western Mediterranean. The main causes of decline are land reclamation, anchoring, bottom trawling, turbidity and pollution. Artificial sand nourishment of beaches has also been called into question, with sand flowing into the sea, burying and destroying neighbouring meadows. A fringing reef of P. oceanica, located at Saint-Mandrier-sur-Mer, near the port of Toulon (Provence, France), is severely degraded. Analysis of aerial photos shows that, since the beginning of the 2000s, it has remained stable in some parts or continued to decline in others. This contrasts with the trend towards recovery, observed in France, thanks to e.g., the legally protected status of P. oceanica, and the reduction of pollution and coastal developments. The sand nourishment of the study beach, renewed every year, with the sand being washed or blown very quickly (within a few months) from the beach into the sea, burying the P. oceanica meadow, seems the most likely explanation. Other factors, such as pollution, trampling by beachgoers and overgrazing, may also play a role in the decline. Full article

Sustainable traffic management relies on accurate traffic flow prediction to reduce congestion, fuel consumption, and emissions and minimise the external environmental impacts of traffic operations. This study contributes to this objective by developing and evaluating advanced machine learning models that leverage multisource data to predict traffic patterns more effectively, allowing for the deployment of proactive measures to prevent or reduce traffic congestion and idling times, leading to enhanced eco-friendly mobility. Specifically, this paper evaluates the impact of multisource sensor inputs and spatial detector interactions on machine learning-based traffic flow prediction. Using a dataset of 839,377 observations from 14 detector stations along Melbourne’s Eastern Freeway, Bidirectional Long Short-Term Memory (BiLSTM) models were developed to assess predictive accuracy under different input configurations. The results demonstrated that incorporating speed and occupancy inputs alongside traffic flow improves prediction accuracy by up to 16% across all detector stations. This study also investigated the role of spatial flow input interactions from upstream and downstream detectors in enhancing prediction performance. The findings confirm that including neighbouring detectors improves prediction accuracy, increasing performance from 96% to 98% for eastbound and westbound directions. These findings highlight the benefits of optimised sensor deployment, data integration, and advanced machine-learning techniques for smart and eco-friendly traffic systems. Additionally, this study provides a foundation for data-driven, adaptive traffic management strategies that contribute to sustainable road network planning, reducing vehicle idling, fuel consumption, and emissions while enhancing urban mobility and supporting sustainability goals. Furthermore, the proposed framework aligns with key United Nations Sustainable Development Goals (SDGs), particularly those promoting sustainable cities, resilient infrastructure, and climate-responsive planning. Full article

Introduction: Endovascular thrombectomy (EVT) is highly effective for ischemic stroke patients with a large vessel occlusion. EVT is typically only offered at urban hospitals; therefore, patients are transferred for EVT from hospitals that solely offer thrombolysis. There is uncertainly around patient selection for transfer, which results in a large number of futile transfers. Machine learning (ML) may be able to provide a model that better predicts patients to transfer for EVT. Objective: The objective of the study is to determine if ML can provide decision support to more accurately select patients to transfer for EVT. Methods: This is a retrospective study. Data from Nova Scotia, Canada from 1 January 2018 to 31 December 2022 was used. Four supervised binary classification ML algorithms were applied, as follows: logistic regression, decision tree, random forest, and support vector machine. We also applied an ensemble method using the results of these four classification algorithms. The data was split into 80% training and 20% testing, and five-fold cross-validation was employed. Missing data was accounted for by the k-nearest neighbour’s algorithm. Model performance was assessed using accuracy, the futile transfer rate, and the false negative rate. Results: A total of 5156 ischemic stroke patients were identified during the time period. After exclusions, a final dataset of 93 patients was obtained. The accuracy of logistic regression, decision tree, random forest, support vector machine, and ensemble models was 68%, 79%, 74%, 63%, and 68%, respectively. The futile transfer rate with random forest and decision tree was 0% and 18.9%, respectively, and the false negative rate was 5.37 and 4.3%, respectively Conclusions: ML models can potentially reduce futile transfer rates, but future studies with larger datasets are needed to validate this finding and generalize it to other systems. Full article

Smart buildings’ role is crucial for advancing smart cities’ performance in achieving environmental sustainability, resiliency, and efficiency. The integration barriers continue due to technology, infrastructure, and operations misalignments and are escalated due to inadequate assessment frameworks and classification systems. The existing literature on assessment methodologies reveals diverging evaluation frameworks for smart buildings and smart cities, non-uniform metrics and taxonomies that hinder scalability, and the low use of machine learning in predictive integration modelling. To fill these gaps, this paper introduces a novel machine learning model to predict smart building integration into smart city levels and assess their impact on smart city performance by leveraging data from 147 smart buildings in 13 regions. Six optimised machine learning algorithms (K-Nearest Neighbours (KNNs), Support Vector Regression (SVR), Random Forest, Adaptive Boosting (AdaBoost), Decision Tree (DT), and Extra Tree (ET)) were employed to train the model and perform feature engineering and permutation importance analysis. The SVR-trained model substantially outperformed other models, achieving an R-squared of 0.81, Root Mean Square Error (RMSE) of 0.33 and Mean Absolute Error (MAE) of 0.27, enabling precise integration prediction. Case studies revealed that low-integration buildings gain significant benefits from progressive target upgrades, whilst those buildings that have already implemented some integrated systems tend to experience diminishing marginal benefits with further, potentially disruptive upgrades. The conclusion of this study states that by utilising the developed machine learning model, owners and policymakers are capable of significantly improving the integration of smart buildings to build better, more sustainable, and resilient urban environments. Full article

The global need to transition towards sustainable energy sources has increased the exploration of efficient methods to harness solar energy. Traditional solar panels, being stationary, often fail to capture the rays of the sun optimally across the day. This paper presents a SunPath navigator system that dynamically adjusts the solar panel’s angle, ensuring maximum exposure to the sun. The developed SunPath navigator system achieves a 27.67% average energy gain. This work has utilised the applications of various machine learning models, such as decision trees, AdaBoost, and K-nearest neighbour, for predicting energy generation. The relevance of these models is analysed based on multiple types of error such as MAE, MSE, RMSE, and R². The decision tree outperforms the other two models with a minimum error rate. It is paving the way for a future where solar energy is a primary, economical, and user-friendly power source in urban and rural areas. The dual-axis tracking system not only enhances energy generation but also estimates future energy generation. Full article

Promoting health equity is key to achieving sustainable urban development. The National Sanitary Cities in China (NSCC) policy is a critical development model aimed at improving urban environments and enhancing public health. This study evaluates the selection criteria and policy impact of NSCCs, using the nearest neighbour index, geographic concentration index, imbalance index, and kernel density estimation to analyze their distribution characteristics. Additionally, it explores influencing factors using a geodetector model and spatial overlay analysis. The findings indicate a shift in NSCC selection criteria from urban sanitation to urban health, reflecting China’s strategic focus on achieving health equity. The spatial distribution analysis indicates that NSCCs exhibit a clustered pattern, characterized by dual cores, dual centres, multiple scattered points, and regional extensions. NSCCs are influenced by both natural and socioeconomic factors, with economy and population, technological innovation, and informatization exerting greater influences. This study is valuable for understanding the spatial patterns of NSCCs, providing a scientific basis for promoting equitable and sustainable health resource allocation and policymaking. Full article

The development trend of urban underground space towards deep and large three-dimensional foundation pit projects in complex environments faces the challenges of deformation and instability of supporting structures, strong sensitivity of the surrounding environment, and significant limitations of the traditional design theory. Based on the ultra-long/deep foundation pit project at the Shenzhen Airport East Station, a refined three-dimensional finite element simulation is used to systematically study the deformation mechanism of the supporting structures of deep and large foundation pits under a complex environment and investigate the influence on the neighbouring buildings. In this study, a three-dimensional finite element model is constructed considering the soil–structure coupling effect, and the mechanical response law of the foundation pit under the compliant–inverse combination method is revealed. Based on ABAQUS 6.14, a 10 m wide strip-shaped model of the central island area and an environmental risk source model including an underground station and group pile foundation are established. The analysis shows the following: the lateral shift in the ground wall is distributed in a ‘convex belly’ shape, with a maximum displacement of 29.98 mm; the pit bottom is raised in the shape of the bottom of a rebutted pot, and the settlement behind the wall has an effect ranging up to 3.8 times the depth of the excavation; the lateral shift in the side wall of the neighbouring underground station and the differential settlement of the group piles validate the predictive ability of the model on the complex-environment coupling effect. The research results can provide guidance for the design and construction of support structure projects and similar projects. Full article

The loss of a city’s agricultural lands due to land use change through urban development is a global problem, as local food production is an essential green infrastructure for intergenerational sustainability. Like many cities, much of Sydney’s rapid urban development occurs on land previously used for food production. Sydney has one of the highest rates of urban growth among Western cities and a planning strategy that marginalises its agricultural productivity. To better understand and advocate for Sydney’s capacity for food production we explore all available government datasets containing agricultural biophysical capacity using a critical GIS approach. Employing various spatial-data visualisations to contextualise agricultural production, we examine inherent biophysical agricultural capacity in Sydney and comparable regions along the eastern coast of NSW. Our approach interrogates the notion that Sydney’s metropolitan landscape is of low inherent biophysical quality for agriculture, thereby challenging current development and planning orthodoxy and policy. In ascertaining Sydney’s comparative capacity for agriculture we find that, despite current metropolitan planning policy, datasets reveal western Sydney is biophysically well suited for agriculture. Sydney overall is comparable to five of six other coastal regions of NSW and superior to at least two. While acknowledging metropolitan land use complexities that shape agricultural production in practice, we argue for improved critical application and contextual understanding of existing agricultural datasets to better inform future planning policy to advance regional food security and aid long-term sustainability. Full article

Urbanisation and densification of the built environment is an important feature of the future sustainable environment, which importantly influences the window view quality. This survey addresses a research gap on unfavourable reactions to window views in dense urban environments, where the distance between buildings enables only the view of the neighbouring façade, and also the question of which architectural visual elements specifically trigger them. The typical variables of the studied window views are the various degrees of maintenance, compositional quality, surface quality, activity dynamics, and complexity. The quantitative data, such as general reactions of the observers to window views, the reasons for the reactions, and the assessment of specific features, were collected by means of a close-ended questionnaire. The targeted population was predominantly the work-active population, the population performing sedentary/office work for at least part of the working day. The analyses of the results are predominantly performed using descriptive statistics and encompass overall reactions to similar window views and correlations between gender, age, and window view preferences. An important finding is that gender and the way the respondents spend their workday do not significantly affect the response to the motifs of the window view. The research further shows that it is very difficult to incite and retain enough visual interest to specific window views with standard architectural approaches and subdued architectural design. Full article

With the rapid advancement of urbanisation and transit networks, exploring the spatial relationship between metro systems and cultural heritage is crucial for both heritage preservation and sustainable urban development. This study uses the nearest neighbour index, kernel density analysis, and spatial value evaluation to examine the distribution patterns of cultural heritage in Beijing and its spatial interaction with the metro network. The results show that different types of cultural heritage have distinct distribution characteristics: stone inscriptions are widely dispersed due to their need for preservation in natural settings; traditional villages and ancient tombs are shaped by historical and geographical factors; and industrial heritage is concentrated in areas of historical industrial activity, reflecting strong functional zoning traits. The metro network enhances the accessibility of cultural heritage, especially national- and provincial-level sites, which are predominantly clustered near metro stations. However, geographically isolated world heritage sites, such as the Great Wall and the Ming Tombs, remain less connected to the metro network, helping preserve their authenticity and avoid overdevelopment. Furthermore, thematic designs and cultural displays within Beijing’s metro stations successfully bridge the gap between history and modernity, positioning metro stations as key platforms for cultural dissemination. Nevertheless, metro construction presents challenges to heritage conservation, including potential impacts on site stability due to tunnelling and conflicts between modern station design and the aesthetic integrity of historic districts. These findings offer practical insights for cultural heritage preservation and transit planning in Beijing and serve as a reference for the sustainable development of other historic cities worldwide. Full article

Veteran trees are important elements in forests, as well as urban and suburban areas, and represent part of our cultural heritage. However, increasing age also brings a reduction in vitality. Information on tree physiological vitality can be gained by examining ecophysiological traits, such as photosynthesis, stomatal conductance, and leaf water potential. Here, we assess the effects of age on the photosynthesis and water status of 600-year-old pedunculate oak trees (Quercus robur L.) by comparing them with neighbouring 25-year-old trees. While gas exchange measurements indicated lowered photosynthesis in old trees, their maximum rates of Rubisco carboxylation and electron transport were similar to younger trees, suggesting that biochemical limitations to photosynthesis are not the reason behind their reduced vitality. Moreover, there was no difference in light-adapted and dark-adapted chlorophyll fluorescence between old and young trees. In contrast, stomatal conductance (under unlimited soil water availability) was lower, indicating increased stomatal limitations to photosynthesis in veteran trees. On the other hand, high water potential during mild summer drought conditions indicated better access to soil water in old trees, while stomatal conductance in old trees was higher than in young trees at night. A reduced ability to open and close stomata may be one of the reasons for the observed decline in veteran tree vitality, with a lowered ability to regulate stomatal conductance resulting in reduced carbon gain and unnecessarily high water loss. Full article

This article examines the potential of fuzzy set theory for analysing gradual changes in land use patterns within peri-urban areas. The primary objective of the study was to propose a methodology based on fuzzy set theory for the precise delineation of city boundaries and the identification and spatial localisation of the urban–rural transition zone. The analysis focused on elucidating the defining parameters of this area and the scope of land use changes within the urban–rural transition zone. The analysis employed data from four discrete time points. The data were collected in 2005, 2010, 2017, and 2022. The characteristics of the urban–rural transition zone were evaluated through an examination of historical data and the current land use patterns in regions experiencing direct urbanization pressure. The study demonstrated that, although spatial barriers remain, the city’s development has continued at a consistent pace. Between 2005 and 2010, the area of land classified as urban exhibited a 10% increase, with a further 7% increase observed in the subsequent period, spanning 2010 to 2017. In the most recent period under examination, the urban land area increased by 9%, a figure that is consistent with the rates observed in previous years. These results indicate the stability of urbanization processes in the analysed city, while also revealing significant changes in the limits of urban development and in the intensity of land use. The research project concentrated on the city of Olsztyn and the neighbouring suburban areas, which are subject to direct influence from the city’s expansion. The area under study encompasses 202.4 km² within an eight-km radius of the city centre. The authors of the study emphasized the necessity for systematic monitoring of changes in the transition zone between urban and rural areas. This is to ensure effective control of spatial development and ongoing adjustment of planning tools to effectively prevent uncontrolled expansion. The methodology used enabled the precise delimitation of urban development and the transition zone. This allowed for an in-depth analysis of changes in land use intensity. Full article

Strengthening urban–rural linkages (URLs) has been proposed by UN-Habitat within the framework of ‘Sustainable Development Goals (SDGs)’ to narrow down urban–rural differences via shaping new urban–rural relationships. Like URL, the aim of urban–rural integration (URI) has been promoted by the Chinese government since 2019 to address existing urban–rural divides. This concept underlines the ‘rural revitalisation’ strategy and emphasises a two-way flow of urban–rural development factors. Introducing and upgrading ‘appropriate’ rural industries is crucial to stimulate and facilitate the circulation of urban–rural development factors. This research studied three neighbouring villages, situated in urban–rural interface areas in Huangyan-Taizhou, China, each driven by different types of small industries supported by URI. It analyses the impact of small rural industries on the flow of development factors between urban and rural areas. The results showed that small-scale rural industries have been enhanced URL by decreasing urban–rural differences by creating new job opportunities to attract an in-flow population, increasing investments, and upgrading public services and infrastructure. Indigenous industries demonstrated lower profitability but exhibited greater resilience compared to industries linked to global production chains and rural tourism. Thus, this study demonstrates the imperative to carefully consider the opportunities and potential risks associated with pursuing strategies of URI through rural industry development. By providing empirical insights from URI projects in China, this study contributes to theoretical and policy dialogues concerning the concepts of both URL and URI by exploring the localization of SDGs. Furthermore, it offers valuable practical knowledge and experience for other global regions confronting similar challenges to urban and rural development. Full article

This study focuses on the analysis, implementation and integration of techniques and methods, also based on mathematical algorithms and artificial intelligence (AI), to acquire knowledge of some phenomena that produce pollution with an impact on environmental health, and which start from illicit practices that occur in urban areas. In many urban areas (or agroecosystems), the practice of illegal waste disposing by commercial activities, by abandoning it in the countryside rather than spending economic resources to ensure correct disposal, is widespread. This causes an accumulation of waste in these areas (which can also be protected natural areas), which are then also set on fire to reduce their volume. Obviously, the repercussions of such actions are many. The burning of waste releases contaminants into the environment such as dioxins, polychlorinated biphenyls and furans, and deposits other elements on the soil, such as heavy metals, which, by leaching and percolating, contaminate water resources such as rivers and aquifers. The main objective is the design and implementation of monitoring programs against specific illicit activities that take into account territorial peculiarities. This advanced approach leverages AI and GIS environments to interpret environmental states, providing an understanding of ongoing phenomena. The methodology used is based on the implementation of mathematical and AI algorithms, integrated into a GIS environment to address even large-scale environmental issues, improving the spatial and temporal precision of the analyses and allowing the customization of monitoring programs in urban and peri-urban environments based on territorial characteristics. The results of the application of the methodology show the percentages of the different types of waste found in the agroecosystems of the study area and the degree of concentration, allowing the identification of similar areas with greater criticality. Subsequently, through network and nearest neighbour analysis, it is possible to start targeted checks. Full article

Throughout history, natural disasters have caused severe damage to people and properties worldwide. Flooding is one of the most disastrous types of natural disasters. A key feature of flood assessment has been making use of the information derived from remote-sensing imagery from optical sensors on satellites using spectral indices. Here, a study was conducted about a recent spectral index, the Normalised Difference Inundation Index, and a new ensemble spectral index, the Concatenated Normalised Difference Water Index, and two mature spectral indices: Normalised Difference Water Index and the differential Normalised Difference Water Index with four different machine learning algorithms: Decision Tree, Random Forest, Naive Bayes, and K-Nearest Neighbours applied to the PlanetScope satellite imagery about the Brisbane February 2022 flood which is in urban environment. Statistical analysis was applied to evaluate the results. Overall, the four algorithms provided no significant difference in terms of accuracy and F1 score. However, there were significant differences when some variations in the indices and the algorithms were combined. This research provides a validation of existing measures to identify floods in an urban environment that can help to improve sustainable development. Full article