Search Results (34)

This study investigates the environmental impact of combined missile and drone attacks on Kyiv, the capital of Ukraine, with a focus on the release of particulate matter (PM) into the urban atmosphere. These military strikes frequently result in the destruction of residential and industrial infrastructure, as well as fires, leading to acute increases in ambient concentrations of fine particulate matter (PM2.5). Observational data were collected between 1 and 30 June 2025 using a distributed network of low-cost air quality monitoring stations aggregated by the SaveEcoBot platform. The optical particle counters, based on light scattering technology, enable real-time monitoring of airborne particulate fractions of PM2.5 along with meteorological parameters and gas pollutants. The study period included two significant attacks (10 and 17 June), during which the temporal and spatial dynamics of PM2.5 concentrations were analyzed in comparison to baseline levels observed under non-attack conditions. Raw concentrations of PM2.5 up to 241 μg/m³ were observed in the epicenters of air-strike-induced fires, while smog plumes covered half of the city area. Elevated PM2.5 concentrations were recorded during and for several hours following the attacks and corresponding air raid alerts. The findings show days of PM2.5 exceedances above the World Health Organization (WHO) daily threshold of 15 μg/m³. These results underscore the acute environmental and public health hazards posed by military assaults on urban centers. Furthermore, this research highlights the role of citizen-driven environmental monitoring as a valuable tool for both scientific documentation and potential evidentiary support in assessing the environmental impacts of warfare. Full article

The waste dump from the abandoned La Soterraña mine, a former mercury extraction site, contains high concentrations of mercury (Hg) and arsenic (As), which pose a significant environmental risk due to direct exposure to the environment. Given the site’s topography and slope, surface runoff has been identified as the primary mechanism for the dispersal of these toxic elements into nearby watercourses. This study quantifies the amount of Hg and As released into fluvial systems through surface runoff from the waste dump. Historical topographic data, Airborne Laser Exploration Survey public data from the National Plan for Aerial Orthophotographs (1st PNOA-LiDAR) of the Spanish Ministry of Transport, Mobility and Urban Agenda, and high-precision photogrammetric drone surveys were utilized, with centimeter-level accuracy achieved using airborne GNSS RTK positioning systems on the drone. The methodology yields reliable results when comparing surfaces generated from topographic data collected with consistent methodologies and standards. Analysis indicates an environmental release exceeding 1000 kg of mercury (Hg) and 12,000 kg of arsenic (As) between 2019 and 2023, based on high spatial resolution data (GSD = 8 cm). These findings highlight a sustained temporal contribution of chemical contaminants, which imposes serious environmental and biological health risks due to persistent exposure to toxic elements. Full article

Urban air pollution poses a significant challenge to public health and sustainable development, particularly in mid-sized cities with limited monitoring capabilities. This study investigates the impact of Nature-Based Solutions (NBS) on air quality and Land Surface Temperature (LST) in Guimarães, Portugal. The first phase involves mapping pollutants and assessing European guidelines, traditional monitoring methods, and emerging tools such as sensors and satellite data. The findings indicate gaps in spatial coverage, emphasizing the importance of integrating data from Sentinel-3, Sentinel-5P, local sensors, and drones. These insights establish a foundation for the next phase, which involves predictive modeling of NBS, LST, and pollutants using machine learning techniques to support data-driven policy-making. Full article

The red imported fire ant (RIFA; Solenopsis invicta) is an invasive species that severely threatens ecology, agriculture, and public health in Taiwan. In this study, the feasibility of applying multispectral imagery captured by unmanned aerial vehicles (UAVs) to detect red fire ant mounds was evaluated in Fenlin Township, Hualien, Taiwan. A DJI Phantom 4 multispectral drone collected reflectance in five bands (blue, green, red, red-edge, and near-infrared), derived indices (normalized difference vegetation index, NDVI, soil-adjusted vegetation index, SAVI, and photochemical pigment reflectance index, PPR), and textural features. According to analysis of variance F-scores and random forest recursive feature elimination, vegetation indices and spectral features (e.g., NDVI, NIR, SAVI, and PPR) were the most significant predictors of ecological characteristics such as vegetation density and soil visibility. Texture features exhibited moderate importance and the potential to capture intricate spatial patterns in nonlinear models. Despite limitations in the analytics, including trade-offs related to flight height and environmental variability, the study findings suggest that UAVs are an inexpensive, high-precision means of obtaining multispectral data for RIFA monitoring. These findings can be used to develop efficient mass-detection protocols for integrated pest control, with broader implications for invasive species monitoring. Full article

The escalating impacts and occurrence of wildfires threaten the public, economies, and global ecosystems. Physiologically declining or dead trees are a great portion of the fires because these trees are prone to higher ignition and have lower moisture content. To prevent wildfires, hazardous vegetation needs to be removed, and the vegetation should be identified early on. This work proposes a real-time fire risk tree detection framework using UAV images, which is based on lightweight object detection. The model uses the MobileNetV3-Small spine, which is optimized for edge deployment, combined with an SSD head. This configuration results in a highly optimized and fast UAV-based inference pipeline. The dataset used in this study comprises over 3000 annotated RGB UAV images of trees in healthy, partially dead, and fully dead conditions, collected from mixed real-world forest scenes and public drone imagery repositories. Thorough evaluation shows that the proposed model outperforms conventional SSD and recent YOLOs on Precision (94.1%), Recall (93.7%), mAP (90.7%), F1 (91.0%) while being light-weight (8.7 MB) and fast (62.5 FPS on Jetson Xavier NX). These findings strongly support the model’s effectiveness for large-scale continuous forest monitoring to detect health degradations and mitigate wildfire risks proactively. The framework UAV-based environmental monitoring systems differentiates itself by incorporating a balance between detection accuracy, speed, and resource efficiency as fundamental principles. Full article

The application of artificial intelligence (AI) in monitoring and managing ocean waste reveals considerable promise for improving sustainable strategies to combat marine pollution. This study performs a bibliometric analysis to examine research trends, knowledge frameworks, and future directions in AI-driven sustainable ocean waste management. This study delineates key research themes, prominent journals, influential authors, and leading nations contributing to the field by analysing scientific publications from major databases. Research from citation networks, keyword analysis, and co-authorship patterns highlights significant topics such as AI algorithms for waste detection, machine learning models for predictive mapping of pollution hotspots, and the application of autonomous drones and underwater robots in real-time waste management. The findings indicate a growing global focus on utilising AI to enhance environmental monitoring, optimise waste reduction methods, and support policy development for sustainable marine ecosystems. This bibliometric study provides a comprehensive analysis of the current knowledge landscape, identifies research gaps, and underscores the importance of AI as a crucial enabler for sustainable ocean waste management, offering vital insights for researchers, industry leaders, and environmental policymakers dedicated to preserving ocean health. Full article

This study examines the psychological and social impacts of the April 2024 Iranian combined attack on Israel—a new, globally unprecedented experience for civilians. Aware of incoming missiles and drones, Israelis followed real-time television coverage, including countdowns and visual simulations, which allowed them to anticipate the impacts of potential strikes on their homes and communities. The attack and its coverage blurred the boundaries between crisis and media spectacle, creating a rare convergence of immediate personal threat with real-time media framing. This paper explores how this unique format influenced public anxiety, news consumption, and crisis perception. The results reveal the profound psychological effects of this real-time threat monitoring, raising important questions about the media’s impact on framing crises such as live events and the corresponding effects on public mental health. Full article

Unmanned aerial systems (UAS), commonly known as drones, have gained widespread use due to their affordability and versatility across various domains, including military, commercial, and recreational sectors. Applications such as remote sensing, aerial imaging, agriculture, firefighting, search and rescue, infrastructure inspection, and public safety have extensively adopted this technology. However, environmental impacts, particularly noise, have raised concerns among the public and local communities. Unlike traditional crewed aircraft, drones typically operate in low-altitude airspace (below 400 feet or 122 m), making their noise impact more significant when they are closer to houses, people, and livestock. Numerous studies have explored methods for monitoring, assessing, and predicting the noise footprint of drones. This study employs a bibliometric analysis of relevant scholarly works in the Web of Science Core Collection, published from 2015 to 2024, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) data collection and screening procedures. The International Journal of Environmental Research and Public Health, Aerospace Science and Technology, and the Journal of the Acoustical Society of America are the top three preferred outlets for publications in this area. This review unveils trends, topics, key authors and institutions, and national contributions in the field through co-authorship analysis, co-citation analysis, and other statistical methods. By addressing the identified challenges, leveraging emerging technologies, and fostering collaborations, the field can move towards more effective noise abatement strategies, ultimately contributing to the broader acceptance and sustainable integration of UASs into various aspects of society. Full article

Crop segmentation, the process of identifying and delineating agricultural fields or specific crops within an image, plays a crucial role in precision agriculture, enabling farmers and public managers to make informed decisions regarding crop health, yield estimation, and resource allocation in Midwest Brazil. The crops (corn) in this region are being damaged by wild pigs and other diseases. For the quantification of corn fields, this paper applies novel computer-vision techniques and a new dataset of corn imagery composed of 1416 256 × 256 images and corresponding labels. We flew nine drone missions and classified wild pig damage in ten orthomosaics in different stages of growth using semi-automatic digitizing and deep-learning techniques. The period of crop-development analysis will range from early sprouting to the start of the drying phase. The objective of segmentation is to transform or simplify the representation of an image, making it more meaningful and easier to interpret. For the objective class, corn achieved an IoU of 77.92%, and for background 83.25%, using DeepLabV3+ architecture, 78.81% for corn, and 83.73% for background using SegFormer architecture. For the objective class, the accuracy metrics were achieved at 86.88% and for background 91.41% using DeepLabV3+, 88.14% for the objective, and 91.15% for background using SegFormer. Full article

In response to the challenge of atmospheric pollution posed by growing environmental problems, this study reviews and analyzes the research status and development trends of green infrastructure (GI) in improving air pollution from 2014 to 2024. Using the CiteSpace tool, we explore research hotspots, disciplinary developments, significant contributors, and influential literature in this field, identifying current research gaps and predicting future trends. The findings indicate that GI significantly impacts the reduction of air pollution, the regulation of urban microclimates, and the enhancement of ecosystem services. However, existing studies often focus on isolated aspects and lack comprehensive assessments. Moreover, the research trajectory in this field shows a declining trend. Future research should emphasize interdisciplinary integration, combining ecology, urban planning, meteorology, and public health. By utilizing advanced technologies, such as drones, remote sensing, AI, and big data analysis, we can improve data accuracy and the generalizability of research findings. Additionally, it is crucial to consider the performance of GI under different climatic conditions and socio-economic contexts to comprehensively quantify its overall benefits in terms of air quality, urban thermal comfort, public health, and economic impact. This comprehensive approach will provide a scientific basis for policy-making and urban planning. Full article

Urban green spaces (UGSs) play a significant role in promoting public health by facilitating outdoor activities, but issues of spatial and socioeconomic inequality within UGSs have drawn increasing attention. However, current methods for assessing UGS inequality still face challenges such as data acquisition difficulties and low identification accuracy. Taking Harbin as a case study, this research employs various advanced technologies, including Python data scraping, drone imagery collection, and Amap API, to gather a diverse range of data on UGSs, including photos, high-resolution images, and AOI boundaries. Firstly, elements related to physical activity within UGSs are integrated into a supply adjustment index (SAI), based on which UGSs are classified into three categories. Then, a supply–demand improved two-step floating catchment area (SD2SFCA) method is employed to more accurately measure the accessibility of these three types of UGSs. Finally, using multiple linear regression analysis and Mann–Whitney U tests, socioeconomic inequalities in UGS accessibility are explored. The results indicate that (1) significant differentiation exists in the types of UGS services available in various urban areas, with a severe lack of small-scale, low-supply UGSs; (2) accessibility of all types of UGSs is significantly positively associated with housing prices, with higher-priced areas demonstrating notably higher accessibility compared to lower-priced ones; (3) children may be at a disadvantage in accessing UGSs with medium-supply levels. Future planning efforts need to enhance attention to vulnerable groups. This study underscores the importance of considering different types of UGSs in inequality assessments and proposes a method that could serve as a valuable tool for accurately assessing UGS inequality. Full article

Semantic segmentation algorithms leveraging deep convolutional neural networks often encounter challenges due to their extensive parameters, high computational complexity, and slow execution. To address these issues, we introduce a semantic segmentation network model emphasizing the rapid generation of redundant features and multi-level spatial aggregation. This model applies cost-efficient linear transformations instead of standard convolution operations during feature map generation, effectively managing memory usage and reducing computational complexity. To enhance the feature maps’ representation ability post-linear transformation, a specifically designed dual-attention mechanism is implemented, enhancing the model’s capacity for semantic understanding of both local and global image information. Moreover, the model integrates sparse self-attention with multi-scale contextual strategies, effectively combining features across different scales and spatial extents. This approach optimizes computational efficiency and retains crucial information, enabling precise and quick image segmentation. To assess the model’s segmentation performance, we conducted experiments in Changge City, Henan Province, using datasets such as LoveDA, PASCAL VOC, LandCoverNet, and DroneDeploy. These experiments demonstrated the model’s outstanding performance on public remote sensing datasets, significantly reducing the parameter count and computational complexity while maintaining high accuracy in segmentation tasks. This advancement offers substantial technical benefits for applications in agriculture and forestry, including land cover classification and crop health monitoring, thereby underscoring the model’s potential to support these critical sectors effectively. Full article

The implementation of medical drones can quickly and efficiently expand the coverage range of an area, allowing for a faster response to incidences of out-of-hospital cardiac arrest and improving the subsequent survival rate of such incidences, while promoting sustainable health development goals under the configuration standards for automatic external defibrillators in China. In response to the problem of the selection of locations for medical drone vertiports (for take-off and landing) that are equipped with automatic external defibrillation facilities, a survival function was introduced to establish a model for site selection, with the primary optimization objective of maximizing the average survival rate of patients and taking the operating costs of a system into account. At the same time, considering the constraints of drone phase operation time, energy consumption, coverage range, etc., a medical drone vertiport site selection model was established for emergency cardiac arrest needs. An improved immune algorithm was applied to the model’s calculations and the analysis of the results, using the Jinnan District in Tianjin as an example. The results show that the proposed model and algorithm are feasible and applicable. The Jinnan District in the city of Tianjin requires a total of 24 medical drone vertiports in order to achieve full coverage of an area under the “golden 4-minute” rescue time. When the average survival rate of patients is 0.9, the operation results are deemed optimal, and the average survival rate of patients is 64.06%. Compared to ground ambulances currently used in hospitals, the implementation of medical drones could significantly shorten response time, improve the average survival rate of patients by 41.96%, and effectively improve the existing low survival rate and the accessibility of medical services. The results of this study can provide decision-making support for the planning of automatic external defibrillators in public places and the construction of sustainable and efficient emergency medical service systems. Full article

Uncrewed aerial vehicles (UAVs), commonly known as drones, have emerged as transformative tools in the healthcare sector, offering the potential to revolutionize medical logistics, emergency response, and patient care. This scoping review provides a comprehensive exploration of the diverse applications of drones in healthcare, addressing critical gaps in existing literature. While previous reviews have primarily focused on specific facets of drone technology within the medical field, this study offers a holistic perspective, encompassing a wide range of potential healthcare applications. The review categorizes and analyzes the literature according to key domains, including the transport of biomedical goods, automated external defibrillator (AED) delivery, healthcare logistics, air ambulance services, and various other medical applications. It also examines public acceptance and the regulatory framework surrounding medical drone services. Despite advancements, critical knowledge gaps persist, particularly in understanding the intricate interplay between technological challenges, the existing regulatory framework, and societal acceptance. This review highlights the need for the extensive validation of cost-effective business cases, the development of control techniques that can address time and resource savings within the constraints of real-life scenarios, the design of crash-protected containers, and the establishment of corresponding tests and standards to demonstrate their conformity. Full article

The rapid advancement of climate change and global warming have widespread impacts on society, including ecosystems, water security, food production, health, and infrastructure. To achieve significant global emission reductions, approximately 74% is expected to come from cutting carbon dioxide (CO${}_2$) emissions in energy supply and demand. Carbon Capture and Storage (CCS) has attained global recognition as a preeminent approach for the mitigation of atmospheric carbon dioxide levels, primarily by means of capturing and storing CO${}_2$ emissions originating from fossil fuel systems. Currently, geological models for storage location determination in CCS rely on limited sampling data from borehole surveys, which poses accuracy challenges. To tackle this challenge, our research project focuses on analyzing exposed rock formations, known as outcrops, with the goal of identifying the most effective backbone networks for classifying various strata types in outcrop images. We leverage deep learning-based outcrop semantic segmentation techniques using hybrid backbone networks, named OutcropHyBNet, to achieve accurate and efficient lithological classification, while considering texture features and without compromising computational efficiency. We conducted accuracy comparisons using publicly available benchmark datasets, as well as an original dataset expanded through random sampling of 13 outcrop images obtained using a stationary camera, installed on the ground. Additionally, we evaluated the efficacy of data augmentation through image synthesis using Only Adversarial Supervision for Semantic Image Synthesis (OASIS). Evaluation experiments on two public benchmark datasets revealed insights into the classification characteristics of different classes. The results demonstrate the superiority of Convolutional Neural Networks (CNNs), specifically DeepLabv3, and Vision Transformers (ViTs), particularly SegFormer, under specific conditions. These findings contribute to advancing accurate lithological classification in geological studies using deep learning methodologies. In the evaluation experiments conducted on ground-level images obtained using a stationary camera and aerial images captured using a drone, we successfully demonstrated the superior performance of SegFormer across all categories. Full article