Search Results (109)

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks. Full article

In the digital transformation era, understanding the relationship between digital and real economies is vital for regional development. This study analyses the interaction between these two economies in Henan Province using panel data from 18 cities (2011–2023). It incorporates policy support intensity through fuzzy set theory, applies an integrated weighting method to measure development levels, and uses regression models to assess the digital economy’s impact on the real economy. The coupling coordination degree model, kernel density estimation, and Gini coefficient reveal the coordination status and spatial distribution, while the ecological Lotka–Volterra model identifies the symbiotic patterns. The key findings are as follows: (1) The digital economy does not directly determine the state of the real economy. For example, cities such as Zhoukou and Zhumadian have low digital economy levels but high real economy levels. However, the development of the digital economy promotes the real economy without signs of diminishing returns. (2) The two economies are generally coordinated but differ spatially, with greater coordination in the Central Plains urban agglomeration. (3) The digital and real economies exhibit both collaboration and competition, with reciprocal mutualism as the dominant mode of integration. These insights provide guidance for policymakers and offer a new perspective on the integration of both economies. Full article

Spice by-products, often discarded as waste, represent an untapped resource for sustainable packaging solutions due to their unique, multifunctional, and bioactive profiles. Unlike typical plant residues, these materials retain diverse phytochemicals—including phenolics, polysaccharides, and other compounds, such as essential oils and vitamins—that exhibit controlled release antimicrobial and antioxidant effects with environmental responsiveness to pH, humidity, and temperature changes. Their distinctive advantage is in preserving volatile bioactives, demonstrating enzyme-inhibiting properties, and maintaining thermal stability during processing. This review encompasses a comprehensive characterization of phytochemicals, an assessment of the re-utilization pathway from waste to active materials, and an investigation of processing methods for transforming by-products into films, coatings, and nanoemulsions through green extraction and packaging film development technologies. It also involves the evaluation of their mechanical strength, barrier performance, controlled release mechanism behavior, and effectiveness of food preservation. Key findings demonstrate that ginger and onion residues significantly enhance antioxidant and antimicrobial properties due to high phenolic acid and sulfur-containing compound concentrations, while cinnamon and garlic waste effectively improve mechanical strength and barrier attributes owing to their dense fiber matrix and bioactive aldehyde content. However, re-using these residues faces challenges, including the long-term storage stability of certain bioactive compounds, mechanical durability during scale-up, natural variability that affects standardization, and cost competitiveness with conventional packaging. Innovative solutions, including encapsulation, nano-reinforcement strategies, intelligent polymeric systems, and agro-biorefinery approaches, show promise for overcoming these barriers. By utilizing these spice by-products, the packaging industry can advance toward a circular bio-economy, depending less on traditional plastics and promoting environmental sustainability in light of growing global population and urbanization trends. Full article

This study investigates the complex dynamics of new-type urbanization in resource-based county-level cities, using Wuan City in Hebei Province, China, as a representative case. As China pursues a high-quality development agenda, cities historically dependent on resource extraction face profound challenges in achieving sustainable and inclusive urban growth. This research employs a multi-method approach—including Theil index analysis, industrial shift-share analysis, a Cobb–Douglas production function model, and a composite urbanization index—to quantitatively diagnose the constraints on Wuan’s development and assess its transformation efforts. Our empirical results reveal a multifaceted situation: while the urban–rural income gap has narrowed, rural income streams remain fragile. The shift-share analysis indicates that although Wuan’s traditional industries have regained competitiveness, the city’s economic structure is still burdened by a persistent negative structural component, hindering diversification. Furthermore, the economy exhibits characteristics of a labor-intensive growth model with inefficient capital deployment. These underlying issues are reflected in a comprehensive urbanization index that, after a period of rapid growth, has recently stagnated, signaling the exhaustion of the city’s traditional development mode. In response, Wuan attempts an “industrial transformation-driven new-type urbanization” path. This study details the three core strategies being implemented: (1) incremental population urbanization through development at the urban fringe and in industrial zones; (2) in situ urbanization of the existing rural population; and (3) the cultivation of specialized “characteristic small towns” to create new, diversified economic nodes. The findings from Wuan offer critical, actionable lessons for other resource-dependent regions. The case demonstrates that successful urban transformation requires not only industrial upgrading but also integrated, spatially aware planning and robust institutional support. We conclude that while Wuan’s model provides a valuable reference, its strategies must be adapted to local contexts, emphasizing the universal importance of institutional innovation, human capital investment, and a people-centered approach to achieving resilient and high-quality urbanization. Full article

This review investigates the influence of European Union regulations on the adoption of artificial intelligence in smart city solutions, with a structured emphasis on regulatory barriers, technological challenges, and societal benefits. It offers a comprehensive analysis of the legal frameworks in effect by 2025, including the Artificial Intelligence Act, General Data Protection Regulation, Data Act, and sector-specific directives governing mobility, energy, and surveillance. This study critically assesses how these regulations affect the deployment of AI systems across urban domains such as traffic optimization, public safety, waste management, and energy efficiency. A comparative analysis of regulatory environments in the United States and China reveals differing governance models and their implications for innovation, safety, citizen trust, and international competitiveness. The review concludes that although the European Union’s focus on ethics and accountability establishes a solid basis for trustworthy artificial intelligence, the complexity and associated compliance costs create substantial barriers to adoption. It offers recommendations for policymakers, municipal authorities, and technology developers to align regulatory compliance with effective innovation in the context of urban digital transformation. Full article

This study evaluates deep learning models for vehicle detection in urban environments, focusing on the integration of regional data and standardized evaluation protocols. A central contribution is the creation of DebStreet, a novel dataset that captures images from a specific urban setting under varying weather conditions, providing regionally representative information for model development and evaluation. Using DebStreet, four state-of-the-art architectures were assessed: Faster R-CNN, YOLOv8, DETR, and Side-Aware Boundary Localization (SABL). Notably, SABL and YOLOv8 demonstrated superior precision and robustness across diverse scenarios, while DETR showed significant improvements with extended training and increased data volume. Faster R-CNN also proved competitive when carefully optimized. These findings underscore how the combination of regionally representative datasets with consistent evaluation methodologies enables the development of more effective, adaptable, and context-aware vehicle detection systems, contributing valuable insights for advancing intelligent urban mobility solutions. Full article

Indian mock strawberry (Duchesnea indica, syn. Potentilla indica), a clonal invasive plant native to Asia, has rapidly spread in Europe, where its ecological adaptation allows it to thrive under varying environmental conditions. It is mostly found in urban habitats such as lawns, parks, and urban and peri-urban forests, where it thrives in various plant communities. It can become dominant in certain communities, indicating its competitive advantage over native plants. Due to similar habitat preferences, it often coexists with the native species Glechoma hederacea, with which it shares other characteristics such as clonal growth. This study investigates the effects of light, nutrients, and competition on the growth, morphology, and physiology of D. indica. A controlled pot experiment exposed plants to combinations of sunlight and shade, optimal and increased nutrient levels, and competitive scenarios with the native plant G. hederacea. The plant traits of biomass, leaf and ramet number, stolon and flower production, leaf greenness, the photosynthetic efficiency of Photosystem II, and stomatal conductance were assessed. Results revealed that light and nutrient availability significantly enhanced growth metrics. In shaded conditions, D. indica adapted with elongated petioles and increased specific leaf area. Competition significantly reduced growth, with G. hederacea outperforming D. indica. These findings highlight the complex interplay between abiotic and biotic factors in influencing invasive species impact, providing essential insights for ecosystem management. Full article

In competitive organizations and projects, assessing risks related to human capital is essential for improving workplace conditions and ensuring project success. This study evaluates primary, secondary, and residual human capital risks in urban water transfer projects using an innovative hybrid DEMATEL–MARCOS approach. The DEMATEL method was employed to analyze causal relationships and interdependencies among risks, while the MARCOS method ranked their significance. The key findings reveal that “accidents during material transportation” (primary risk), “corrosion” (secondary risk), and “pipeline pressure” (residual risk) are the most critical factors influencing human capital in such projects. The study provides a structured framework for prioritizing risk mitigation strategies, offering actionable insights for policymakers and project managers to enhance safety, efficiency, and workforce well-being. By integrating multi-criteria decision-making techniques, this research bridges a gap in the water industry’s risk management practices and contributes to safer, more sustainable infrastructure development. Full article

World Heritage plays a vital role in promoting sustainable urban development. Cultural and creative industries (CCIs) have gained recognition as an effective instrument for urban revitalization in recent years. The Cities, Culture, and Creativity (CCC) framework introduced by the United Nations Educational, Scientific and Cultural Organization (UNESCO) and the World Bank emphasizes the core role of culture and creativity in enhancing urban competitiveness, attractiveness, and sustainability. Based on that framework, this study takes Pingyao as a case study, using a literature review and non-participatory observation, systematically examines its assets and resources, assesses the outcomes at the spatial, economic, and social levels, and explores how CCIs, with the support of enabling factors, contribute to urban revitalization. The findings indicate that Pingyao, relying on its historical and cultural heritage, promotes the development of CCIs, resulting in significant spatial optimization, economic growth, and social benefits, while also shaping unique cultural brands. This study verifies the applicability of the CCC framework in analyzing the urban revitalization mechanism, further reveals the role of CCIs in the revitalization of World Heritage cities, enriches the urban regeneration theory, and offers theoretical and practical reference for the revitalization and sustainable development of other World Heritage cities. Full article

The environmental quality of conference and exhibition places in small- and medium-sized cities plays a crucial role in attracting exhibitors, fostering the growth of the conference and exhibition industry and enhancing the market competitiveness of these places. However, past decision makers have often adopted planning models from large cities, neglecting the interaction between conference and exhibition places in smaller cities and local lifestyles as well as urban environments. From an “environment-behavior” perspective, this study reveals the unique interaction mechanisms between exhibitors and the built environment within such venues. Moving beyond the limitations of traditional research that focused solely on physical indicators, we place particular emphasis on exhibitors’ behavioral adaptations and their overall exhibition experience in the convention environment. To address this gap, this study employs a mixed-method approach that integrates field surveys, interviews, and questionnaires to systematically collect data from 10 representative cases. First, a preliminary study was conducted to establish an evaluation index system for place environmental quality. Through regression analysis, six key indicators—such as promotional atmosphere, site accessibility, and surrounding urban development conditions—were identified as significant factors influencing place quality. Second, subjective evaluations were conducted based on users’ actual experiences and experts’ professional insights, leading to the development of an importance–performance analysis model to assess value expectations and place environmental performance. The results indicated that users had high expectations for elements such as parking availability, transportation facilities, and the surrounding commercial atmosphere. In contrast, experts emphasized the significance of proximity to urban transportation hubs, site accessibility, and the spatial orientation of public spaces in determining environmental quality. Moreover, differences in evaluations among experts from various fields revealed notable variations in focus and priority considerations. Finally, based on a statistical analysis of the survey results, this study proposes three design recommendations—“adaptation, attraction, and quality enhancement”—to optimize the environmental quality of conference and exhibition places in small- and medium-sized cities, offering both theoretical and practical guidance for future planning, design, and evaluation. Full article

Remote sensing image change detection plays a vital role in diverse real-world applications such as urban development monitoring, disaster assessment, and land use analysis. As deep learning strives, Convolutional Neural Networks (CNNs) have shown their effects in image processing applications. There are two problems in old-school change detection techniques: First, the techniques do not fully use the effective information of the global and local features, which causes their semantic comprehension to be less accurate. Second, old-school methods usually simply rely on differences and computation at the pixel level without giving enough attention to the information at the semantic level. To address these problems, we propose a multi-scale cross-attention network (MSCANet) based on a CNN in this paper. First, a multi-scale feature extraction strategy is employed to capture and fuse image information across different spatial resolutions. Second, a cross-attention module is introduced to enhance the model’s ability to comprehend semantic-level changes between bitemporal images. Compared to the existing methods, our approach better integrates spatial and semantic features across scales, leading to more accurate and coherent change detection. Experiments on three public datasets (LEVIR-CD, CDD, and SYSU-CD) demonstrate competitive performance. For example, the model achieves an F1-score of 96.19% and an IoU of 92.67% on the CDD dataset. Additionally, robustness tests with Gaussian noise show that the model maintains high accuracy under input degradation, highlighting its potential for real-world applications. These findings suggest that our MSCANet effectively improves semantic awareness and robustness, offering a promising solution for change detection in complex and noisy remote sensing environments. Full article

This paper explores the intersection of water quality management and advanced metaheuristic algorithms (MAs) by optimizing the location of water quality sensors in urban water networks. A comparative analysis of ten cutting-edge MAs, Harris Hawk Optimization (HHO), Artemisinin Optimization (AO), Educational Competition Optimizer (ECO), Fata Morgana Algorithm (FATA), Moss Growth Optimization (MGO), Parrot Optimizer (PO), Polar Lights Optimizer (PLO), Rime Optimization Algorithm (RIME), Runge Kutta Optimization (RUN), and Weighted Mean of Vectors (INFO), was conducted to determine their effectiveness in minimizing the risk of contaminated water consumption. Both benchmark and real-world water network serve as case studies to assess algorithmic performance. The optimization process focuses on reducing the volume of contaminated water by treating sensor placement as a critical design variable. EPANET 2.2 software was integrated with the optimization algorithms to simulate water quality and hydraulic behavior within the networks. The obtained results from analysis of two urban water networks revealed that the newer algorithms, such as the RIME and FATA, exhibit superior convergence rates and stability compared to traditional methods. While all tested algorithms demonstrated satisfactory performance, this study provides foundational insights for future research, paving the way for more effective algorithmic solutions in water quality management. Full article

As urbanization progresses rapidly, the pollution of heavy metal wastewater and the disposal of municipal solid waste incineration bottom ash (MSWI-BA) have emerged as significant challenges. MSWI-BA is a porous material recognized as an environmentally friendly adsorbent. To prevent escalating costs in future practical engineering applications, this study employed unmodified, natural MSWI-BA. This research assessed the adsorption capabilities of MSWI-BA for Pb(II) and Zn(II) through static adsorption experiments, which included adsorption kinetics and isotherm studies. The influence of various factors on the adsorption performance of MSWI-BA was investigated through adjusting the solution pH and the amount of ash, competitive adsorption conditions, and regeneration experiments. Advanced techniques, including ESEM-EDS, XRD, and FTIR, were utilized to analyze the adsorption mechanisms. The results indicated that under the conditions of pH values of 4 and 5, a temperature of 318 K, and an ash dosage of 0.1 g/20 mL, the maximum adsorption capacities of MSWI-BA for Pb(II) and Zn(II) were 89.09 mg/g and 33.77 mg/g, respectively. MSWI-BA demonstrates robust regeneration potential over multiple cycles, validating its practical feasibility. The principal mechanisms for removal include chemical precipitation, ion exchange, and surface complexation. By repurposing it as an efficient and low-cost adsorbent, this represents a sustainable strategy. Full article

Keeping track of air quality is paramount to issue preemptive measures to mitigate adversarial effects on the population. This study introduces a new quantum–classical approach, combining a graph-based deep learning structure with a quantum neural network to predict ozone concentration up to 6 h ahead. The proposed architecture utilized historical data from Houston, Texas, a major urban area that frequently fails to comply with air quality regulations. Our results revealed that a smoother transition between the classical framework and its quantum counterpart enhances the model’s results. Moreover, we observed that combining min–max normalization with increased ansatz repetitions also improved the hybrid model’s performance. This was evident from evaluating the assessment metrics root mean square error (RMSE), coefficient of determination (R²) and forecast skill (FS). Values for R² and FS for the horizons considered were 94.12% and 31.01% for the 1 h, 83.94% and 48.01% for the 3 h, and 75.62% and 57.46% for the 6 h forecasts. A comparison with the existing literature for both classical and QML models revealed that the proposed methodology could provide competitive results, and even surpass some well-established forecasting models, proving to be a valuable resource for air quality forecasting, and thus validating this approach. Full article

The growing and unprecedented water crisis leads to the need to find alternative water resources, and the reuse of treated urban wastewater is an excellent approach. Accordingly, in this work, the disinfection of a secondary effluent (W) discharged from a wastewater treatment plant (WWTP) by hydrogen peroxide combined with radiation (H₂O₂+UV/visible) was studied with the aim of obtaining treated water that can be reused. Firstly, the effect of hydrogen peroxide alone, radiation per se and the combined H₂O₂+UV/Visible process in the inactivation of enterobacteria were assessed. It was found that the oxidant alone is not efficient; the maximum inactivation is achieved when the oxidant and radiation are used simultaneously. For the first time, the effect of some operational parameters, namely the hydrogen peroxide concentration (between 50 and 125 mg/L), initial pH (from 5.0 to 7.0), temperature (between 15 and 25 °C), and radiation intensity (100 to 500 W/m²), on the efficiency of the disinfection process was assessed. When the process was carried out under the best operating conditions found ([H₂O₂] = 75 mg/L, pH = 5.0, T = 25 °C, and UV/visible light with I = 500 W/m²), total enterobacteria and total heterotrophs were inactivated and the abundance of the 16S rRNA, bla_TEM, qnrS, and intl1 genes was reduced. The cultivable microorganisms grew again after 3 days of storing the treated wastewater (TW), making it impossible to reuse such effluent after storage. Therefore, the potential capacity of a diverse bacterial community present in river water to inhibit the regrowth of potentially harmful bacteria present in the urban secondary wastewater after the application of the treatment process was also evaluated. To the authors’ knowledge, this has never been studied before. For this purpose, the TW was diluted with river water (R) at a volumetric percentage of 50/50—sample R+TW. It was found that, after storage, only the total heterotrophs grew, while the abundance of the targeted genes remained practically constant. The R+TW sample after storage met the legal limits for reuse in urban and agricultural applications. The results of this study suggest that the combination of the H₂O₂+UV/visible radiation treatment with dilution of the final treated effluent with natural surface water can contribute to reducing the burden of water scarcity. Full article