Search Results (17)

Ambient air pollution is the most important environmental factor impacting human health. Urban landscapes present unique air quality challenges, which are compounded by climate change adaptation challenges, as air pollutants can also be affected by the urban heat island effect, amplifying the deleterious effects on health. Nature-based solutions have shown potential for alleviating environmental stressors, including air pollution and heat wave abatement. However, such solutions must be designed in order to maximize mitigation and not inadvertently increase pollutant exposure. This study aims to demonstrate potential applications of nature-based solutions in urban environments for climate stressors and air pollution mitigation by analyzing two distinct scenarios with and without green infrastructure. Utilizing low-cost sensors, we examine the relationship between green infrastructure and a series of environmental parameters. While previous studies have investigated green infrastructure and air quality mitigation, our study employs low-cost sensors in tropical urban environments. Through this novel approach, we are able to obtain highly localized data that demonstrates this mitigating relationship. In this study, as a part of the NERC-FAPESP-funded GreenCities project, four low-cost sensors were validated through laboratory testing and then deployed in two locations in São Paulo, Brazil: one large, heavily forested park (CIENTEC) and one small park surrounded by densely built areas (FSP). At each site, one sensor was located in a vegetated area (Park sensor) and one near the roadside (Road sensor). The locations selected allow for a comparison of built versus green and blue areas. Lidar data were used to characterize the profile of each site based on surrounding vegetation and building area. Distance and class of the closest roadways were also measured for each sensor location. These profiles are analyzed against the data obtained through the low-cost sensors, considering both meteorological (temperature, humidity and pressure) and particulate matter (PM₁, PM_2.5 and PM₁₀) parameters. Particulate matter concentrations were lower for the sensors located within the forest site. At both sites, the road sensors showed higher concentrations during the daytime period. These results further reinforce the capabilities of green–blue–gray infrastructure (GBGI) tools to reduce exposure to air pollution and climate stressors, while also showing the importance of their design to ensure maximum benefits. The findings can inform decision-makers in designing more resilient cities, especially in low-and middle-income settings. Full article

Vehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network extraction structure, either a single global or local measure. However, for vehicle images with high intra-class variance and low inter-class variance, exploring globally invariant features and discriminative local details is necessary. In this paper, we propose a Feature Fusion Network (GLFNet) that combines global and local information. It utilizes global features to enhance the differences between vehicles and employs local features to compactly represent vehicles of the same type. This enables the model to learn features with a large inter-class distance and small intra-class distance, significantly improving the model’s generalization ability. Experiments show that the proposed method is competitive with other advanced algorithms on three mainstream road traffic surveillance vehicle re-identification benchmark datasets. Full article

The NH 58 area in India has been experiencing an increase in landslide occurrences, posing significant threats to local communities, infrastructure, and the environment. The growing need to identify areas prone to landslides for effective disaster risk management, land use planning, and infrastructure development has led to the increased adoption of advanced geospatial technologies and statistical methods. In this context, this research article presents an in-depth analysis aimed at developing a landslide susceptibility zonation (LSZ) map for the NH 58 area using remote sensing, GIS, and logistic regression analysis. The study incorporates multiple geo-environmental factors for analysis, such as slope aspect, curvature, drainage density, elevation, fault distance, flow accumulation, geology, geomorphology, land use land cover (LULC), road distance, and slope angle. Utilizing 50% of the landslide inventory data, the logistic regression model was trained to determine correlations between causal factors and landslide occurrences. The logistic regression model was then employed to calculate landslide probabilities for each mapping unit within the NH 58 area, which were subsequently classified into relative susceptibility zones using a statistical class break technique. The model’s accuracy was verified through ROC curve analysis, resulting in a 92% accuracy rate. The LSZ map highlights areas near road cut slopes as highly susceptible to landslides, providing crucial information for land use planning and management to reduce landslide risk in the NH 58 area. The study’s findings are beneficial for policymakers, planners, and other stakeholders involved in regional disaster risk management. This research offers a comprehensive analysis of landslide-influencing factors in the NH 58 area and introduces an LSZ map as a valuable tool for managing and mitigating landslide risks. The map also serves as a critical reference for future research and contributes to the broader understanding of landslide susceptibility in the region. Full article

Deadwood is one of the main structural features of forest ecosystems and plays an important role in the nutrient cycle, in maintaining production and environmental heterogeneity, and acts as an indicator for assessing the biodiversity of forest ecosystems. This research was conducted with the aim of evaluating the quantitative and qualitative characteristics of deadwood according to the influence of forest accessibility indicators in a comparison between natural and recreational forests. The studied area was divided into three accessibility classes based on the slope gradient range, the slope direction towards the nearest road, the road type, and distance from the road. These classes were: Easy-recreational forest (RE-F), Medium-natural forest 1 (NA-F1), and Difficult-natural forest 2 (NA-F2). In each accessibility class, three transects (750 × 50 m) were established, and three deadwood groups (snag, log, and stump) were recorded along the transects and their volume was calculated. The results of the analysis of variance show that accessibility has a significant effect on the presence of deadwood. The number and volume of snags, logs and dead stumps per hectare was higher in NA-F2 than in NA-F1 and RE-F. In each of the investigated classes, logs and stumps had the highest and the lowest number and volume of deadwood per hectare, respectively. The snag longevity index (= log volume/snag volume) decreased with accessibility. NA F2 showed the greatest value, while REF and NA F1 were not significantly different from each other. The results show that decay classes DC2 in NA-F2 and DC3 in NA-F1 and RE-F had the highest percentage of decay frequency. Finally, the forest accessibility indicators have a significant effect on the quantity, quality and distribution of different groups of deadwood in the forest. This is related to the collection of deadwood by local people who remove deadwood with different levels of intensity. Full article

Traffic sign detection is an essential component of an intelligent transportation system, since it provides critical road traffic data for vehicle decision-making and control. To solve the challenges of small traffic signs, inconspicuous characteristics, and low detection accuracy, a traffic sign recognition method based on improved (You Only Look Once v3) YOLOv3 is proposed. The spatial pyramid pooling structure is fused into the YOLOv3 network structure to achieve the fusion of local features and global features, and the fourth feature prediction scale of 152 × 152 size is introduced to make full use of the shallow features in the network to predict small targets. Furthermore, the bounding box regression is more stable when the distance-IoU (DIoU) loss is used, which takes into account the distance between the target and anchor, the overlap rate, and the scale. The Tsinghua–Tencent 100K (TT100K) traffic sign dataset’s 12 anchors are recalculated using the K-means clustering algorithm, while the dataset is balanced and expanded to address the problem of an uneven number of target classes in the TT100K dataset. The algorithm is compared to YOLOv3 and other commonly used target detection algorithms, and the results show that the improved YOLOv3 algorithm achieves a mean average precision (mAP) of 77.3%, which is 8.4% higher than YOLOv3, especially in small target detection, where the mAP is improved by 10.5%, greatly improving the accuracy of the detection network while keeping the real-time performance as high as possible. The detection network’s accuracy is substantially enhanced while keeping the network’s real-time performance as high as possible. Full article

Among the Saudi Vision 2030 programs is the Green Saudi Initiative, which aims to protect the environment, energy conversion, and sustainability projects to build a sustainable future. In the present paper, Green Infrastructures (GI) were assessed, analyzed, and mapped using GIS and Analytic Hierarchy Process-based-Multi-Criteria Decision-Making Method (AHP-MCDM). Ten criteria were selected to elaborate the GI suitability map (DEM, slope, topographic position index, rainfall, distance to the water lines, topographic wetness index, distance to the road, wind speed, housing income group high (high-income people) map, employment in the agricultural sector, and land use land change). The results revealed four classes of suitability: Poor, Fair, Good, and Excellent. The “Excellent” area for GI planning was estimated at 983 km² (9%), whereas the “Good” area covered 36% (3987 km²). The excellent and good areas for GI were more localized in the central part of the Al Baha region in the areas of Al Bahah, Elmandaq, Alatawlah, and the central part of Buljurshi. According to the obtained results, the southern part of the study is not suitable for GI planning; this is explained by the large area of barren land and sand. The results obtained by this research may help managers and decision-makers in future planning for GI areas in the Al Baha region. Full article

Deadwood is a basic component in forest ecosystems since it supports many ecological and functional roles. Despite the importance of deadwood for assessing the sustainability of forest management, information on this fundamental parameter of forest ecosystems is documented mainly for protected areas, while for managed forests it is much scarcer. The study aims to assess the deadwood in managed beech forests of the National Park of Abruzzo, Lazio and Molise. These forests have an important socio-economic function for the local population, who collect the deadwood as allowed by the park regulation. The presence of deadwood found from inside the forest to logging roads was investigated. Three accessibility classes were established, and data analysis was performed according to this classification. The result showed that the accessibility to the forest affects the quantity and the decay class of the deadwood. In conclusion, the deadwood removal influences the quantity of deadwood in the forest and the removal is affected by the distance from the road. Full article

Object detection is a predominant challenge in computer vision and image processing to detect instances of objects of various classes within an image or video. Recently, a new domain of vehicular platforms, e-scooters, has been widely used across domestic and urban environments. The driving behavior of e-scooter users significantly differs from other vehicles on the road, and their interactions with pedestrians are also increasing. To ensure pedestrian safety and develop an efficient traffic monitoring system, a reliable object detection system for e-scooters is required. However, existing object detectors based on IoU loss functions suffer various drawbacks when dealing with densely packed objects or inaccurate predictions. To address this problem, a new loss function, balanced-IoU (BIoU), is proposed in this article. This loss function considers the parameterized distance between the centers and the minimum and maximum edges of the bounding boxes to address the localization problem. With the help of synthetic data, a simulation experiment was carried out to analyze the bounding box regression of various losses. Extensive experiments have been carried out on a two-stage object detector, MASK_RCNN, and single-stage object detectors such as YOLOv5n6, YOLOv5x on Microsoft Common Objects in Context, SKU110k, and our custom e-scooter dataset. The proposed loss function demonstrated an increment of 3.70% at $A{P}_S$ on the COCO dataset, 6.20% at AP55 on SKU110k, and 9.03% at AP80 of the custom e-scooter dataset. Full article

We examine Land Use Land Cover Change (LULCC) in the Dedza and Ntcheu districts of Central Malawi and model anthropogenic and environmental drivers. We present an integrative approach to understanding heterogenous landscape interactions and short- to long-term shocks and how they inform future land management and policy in Malawi. Landsat 30-m satellite imagery for 2001, 2009, and 2019 was used to identify and quantify LULCC outcomes based on eight input classes: agriculture, built-up areas, barren, water, wetlands, forest-mixed vegetation, shrub-woodland, and other. A Multilayer Perceptron (MLP) neural network was developed to examine land-cover transitions based on the drivers; elevation, slope, soil texture, population density and distance from roads and rivers. Agriculture is projected to dominate the landscape by 2050. Dedza has a higher probability of future land conversion to agriculture (0.45 to 0.70) than Ntcheu (0.30 to 0.45). These findings suggest that future land management initiatives should focus on spatiotemporal patterns in land cover and develop multidimensional policies that promote land conservation in the local context. Full article

COVID-19 is a disease caused by a new coronavirus called SARS-CoV-2 and is an accidental global public health threat. Because of this, WHO declared the COVID-19 outbreak a pandemic. The pandemic is spreading unprecedently in Addis Ababa, which results in extraordinary logistical and management challenges in response to the novel coronavirus in the city. Thus, management strategies and resource allocation need to be vulnerability-oriented. Though various studies have been carried out on COVID-19, only a few studies have been conducted on vulnerability from a geospatial/location-based perspective but at a wider spatial resolution. This puts the results of those studies under question while their findings are projected to the finer spatial resolution. To overcome such problems, the integration of Geographic Information Systems (GIS) and Multi-Criteria Decision Analysis (MCDA) has been developed as a framework to evaluate and map the susceptibility status of the infection risk to COVID-19. To achieve the objective of the study, data like land use, population density, and distance from roads, hospitals, bus stations, the bank, markets, COVID-19 cases, health care units, and government offices are used. The weighted overlay method was used; to evaluate and map the susceptibility status of the infection risk to COVID-19. The result revealed that out of the total study area, 32.62% (169.91 km²) falls under the low vulnerable category (1), and the area covering 40.9% (213.04 km²) under the moderate vulnerable class (2) for infection risk of COVID-19. The highly vulnerable category (3) covers an area of 25.31% (132.85 km²), and the remaining 1.17% (6.12 km²) is under an extremely high vulnerable class (4). Thus, these priority areas could address pandemic control mechanisms like disinfection regularly. Health sector professionals, local authorities, the scientific community, and the general public will benefit from the study as a tool to better understand pandemic transmission centers and identify areas where more protective measures and response actions are needed at a finer spatial resolution. Full article

This study aims to estimate the susceptibility of fire occurrence in the Qaradagh area of the Iraqi Kurdistan Region, by examining 16 predictive factors. We selected these predictive factors, dependent on analyzing and performing a comprehensive review of about 57 papers related to fire susceptibility. These papers investigate areas with similar environmental conditions to the arid environments as our study area. The 16 factors affecting the fire occurrence are Normalized Difference Vegetation Index (NDVI), slope gradient, slope aspect, elevation, Topographic Wetness Index (TWI), Topographic Position Index (TPI), distance to roads, distance to rivers, distance to villages, distance to farmland, geology, wind speed, relative humidity, annual temperature, annual precipitation, and Land Use and Land Cover (LULC). To extract fires that occurred between 2015 and 2020, 121 scenes of satellite images (most of them are scenes of Sentinel-2) were used, with the aid of a field survey. In total, 80% of the data (185,394 pixels) were used for the training dataset in the model, and 20% of the data (46,348 pixels) were used for the validation dataset. Conversely, 20% of these data were used for the training dataset in the model, and 80% of the data were used for the validation dataset to check the model’s overfitting. We used the logistic regression model to analyze the multi-data sites obtained from the 16 predictive factors, to predict the forest and vegetated lands that suffer from fire. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the accuracy of the proposed models. The AUC value is more than 84.85% in all groups, which shows very high accuracy for both the model and the factors selected for preparing fire zoning maps in the studied area. According to the factor weight results, classes of LULC and wind speed gained the highest weight among all groups. This paper emphasizes that the used approach is useful for monitoring shrubland, grassland, and cropland fires in other similar areas, which are located in the Mediterranean climate zone. Besides, the model can be applied in other regions, taking the local influencing factors into consideration, which contribute to forest fire mitigation and prevention planning. Hence, the mentioned results can be applied to primary warning, fire suppression resource planning, and allocation work. The mentioned results can be used as prior warnings of the outbreak of fires, taking the necessary measures and methods to prevent and extinguish fires. Full article

Angola’s forests are abundant and highly productive with enormous potential to support local needs and exportation. The forests are well distributed across the country, but the existing road network is generally poor and, in some cases, inappropriate. Based on our previous work examining deforestation patterns and the modeling of primary tree attributes of vegetation types, we proposed forest management zones (MZ) for future planning in Huambo province in Angola. Herein, that same framework is applied for the detection of the existing road network in Huambo and the proposal of alternative routes inside the MZ. We used analytic hierarchy process (AHP) and geographic information systems (GIS) to optimize connectivity among the existing forest plantations and their distance to the closest major cities within the province. We developed road suitability maps based on AHP and GIS to ensure safer driving conditions and contribute to the forest planner’s access to the current plantations. According to the suitability map created, 59.51% of the total area is suitable for road development and is counted in classes 4 and 5 in automatic classification. Parameters such as geology, slope, distance from roads to the railway, soil types, elevation, flow accumulation, and aspect were used. We provide a completed assessment of the state of existing roads and evaluate the safety of the observed road sections based on the AHP method. The calculated weights of the factors were all consistent with the model used (consistency ratio was 0.09 < 0.1). Finally, we proposed the best alternative routes to the existing cities, MZ in miombo woodlands, and forest plantations inside the province. Our findings indicated that flow accumulation, soil type, and geology were the most significant factors impacting road construction. Overall, our framework is an important starting point for further research activities towards developing a spatial decision support system (SDSS) for planning road networks in Angola. Full article

Land-use and land-cover (LULC) change analyses are useful in understanding the changes in our living environments and their driving factors. Modeling changes of LULC in the future, together with the driving factors derived through analyzing the trends of past LULC changes, bring the opportunity to assess and orientate the current and future land-use policies. As the entryway of Quang Ninh province, Vietnam, Dong Trieu locale has experienced significant LULC changes during the past two decades. In this study, the spatial distribution of six Level I LULC classes, forest, cropland, orchards, waterbody, built-up, and barren land, in Dong Trieu district at 2000, 2010, and 2019 were obtained from Landsat imageries by maximum likelihood technique. The most significant changes observed over the past twenty years are a decrease of barren land (9.1%) and increases of built-up (8.1%) and orchards (6.8%). Driving factor analysis indicated that the changes of cropland and built-up were dependent on distance from road (DFR), distance from main road (DFMR), distance from urban (DFU), distance from water (DFW), elevation, slope, and population density. The changes of forest were dependent on all the driving forces listed above, except DFMR. The orchards mainly appeared near the high-population-density area. The transformation of the waterbody was affected by geography (elevation and slope) and population density. The higher the population density, the less barren the land would appear. Full article

Central Asia is one of the most challenged places, prone to suffering from various natural hazards, where seismically triggered landslides have caused severe secondary losses. Research on this problem is especially important in the cross-border Mailuu-Suu catchment in Kyrgyzstan, since it is burdened by radioactive legacy sites and frequently affected by earthquakes and landslides. To identify the landslide-prone areas and to quantify the volume of landslide (VOL), Scoops3D was selected to evaluate the slope stability throughout a digital landscape in the Mailuu-Suu catchment. By performing the limit equilibrium analysis, both of landslide susceptibility index (LSI) and VOL were estimated under five earthquake scenarios. The results show that the upstream areas were more seismically vulnerable than the downstream areas. The susceptibility level rose significantly with the increase in earthquake strength, whereas the VOL was significantly higher under the extreme earthquake scenario than under the other four scenarios. After splitting the environmental variables into sub-classes, the spatial variations of LSI and VOL became more clear: the LSI reduced with the increase in elevation, slope, annual precipitation, and distances to faults, roads, and streams, whereas the highest VOL was observed in the areas with moderate elevations, high precipitation, grasslands, and mosaic vegetation. The relative importance analysis indicated that the explanatory power reduced with the increase in earthquake level and it was significant higher for LSI than for VOL. Among nine environmental variables, the distance to faults, annual precipitation, slope, and elevation were identified as important triggers of landslides. By a simultaneous assessment of both LSI and VOL and the identification of important triggers, the proposed modelling approaches can support local decision-makers and householders to identify landslide-prone areas, further design proper landslide hazard and risk management plans and, consequently, contribute to the resolution of transboundary pollution conflicts. Full article

The Himalayan region and hilly areas face severe challenges due to landslide occurrences during the rainy seasons in India, and the study area, i.e., the Rudraprayag district, is no exception. However, the landslide related database and research are still inadequate in these landslide-prone areas. The main purpose of this study is: (1) to prepare the multi-temporal landslide inventory map using geospatial platforms in the data-scarce environment; (2) to evaluate the landslide susceptibility map using weights of evidence (WoE) method in the Geographical Information System (GIS) environment at the district level; and (3) to provide a comprehensive understanding of recent developments, gaps, and future directions related to landslide inventory, susceptibility mapping, and risk assessment in the Indian context. Firstly, 293 landslides polygon were manually digitized using the BHUVAN (Indian earth observation visualization) and Google Earth^® from 2011 to 2013. Secondly, a total of 14 landslide causative factors viz. geology, geomorphology, soil type, soil depth, slope angle, slope aspect, relative relief, distance to faults, distance to thrusts, distance to lineaments, distance to streams, distance to roads, land use/cover, and altitude zones were selected based on the previous study. Then, the WoE method was applied to assign the weights for each class of causative factors to obtain a landslide susceptibility map. Afterward, the final landslide susceptibility map was divided into five susceptibility classes (very high, high, medium, low, and very low classes). Later, the validation of the landslide susceptibility map was checked against randomly selected landslides using IDRISI SELVA 17.0 software. Our study results show that medium to very high landslide susceptibilities had occurred in the non-forest areas, mainly scrubland, pastureland, and barren land. The results show that medium to very high landslide susceptibilities areas are in the upper catchment areas of the Mandakini river and adjacent to the National Highways (107 and 07). The results also show that landslide susceptibility is high in high relative relief areas and shallow soil, near thrusts and faults, and on southeast, south, and west-facing steep slopes. The WoE method achieved a prediction accuracy of 85.7%, indicating good accuracy of the model. Thus, this landslide susceptibility map could help the local governments in landslide hazard mitigation, land use planning, and landscape protection. Full article