Search Results (40)

This study proposes a vision-based framework to support AVs in maintaining stable lane-keeping by assessing the condition of lane markings. Unlike existing infrastructure standards focused on human visibility, this study addresses the need for criteria suited to sensor-based AV environments. Using real driving data from urban expressways in Seoul, a YOLOv5-based lane detection algorithm was developed and enhanced through multi-label annotation and data augmentation. The model achieved a mean average precision (mAP) of 97.4% and demonstrated strong generalization on external datasets such as KITTI and TuSimple. For lane condition assessment, a pixel occupancy–based method was applied, combined with Canny edge detection and morphological operations. A threshold of 80-pixel occupancy was used to classify lanes as intact or worn. The proposed framework reliably detected lane degradation under various road and lighting conditions. These results suggest that quantitative, image-based indicators can complement traditional standards and guide AV-oriented infrastructure policy. Limitations include a lack of adverse weather data and dataset-specific threshold sensitivity. Full article

Urban forests are very important for the environment and for people, especially in semi-arid cities where there is not much greenery. This makes heat stress worse and makes the city less livable. This paper presents a comprehensive geospatial methodology for selecting afforestation sites in the expanding semi-arid urban area of Şanlıurfa, Turkey, characterized by minimal forest cover, rapid urbanization, and extreme weather conditions. We identified nine ecological and infrastructure criteria using high-resolution Sentinel-2 images and features from the terrain. These criteria include slope, aspect, topography, land surface temperature (LST), solar radiation, flow accumulation, land cover, and proximity to roads and homes. After being normalized to make sure they were ecologically relevant and consistent, all of the datasets were put together into a GIS-based Multi-Criteria Decision Analysis (MCDA) tool. The Analytic Hierarchy Process (AHP) was then used to weight the criteria. A deep learning-based semantic segmentation model was used to create a thorough classification of land cover, primarily to exclude unsuitable areas such as dense urban fabric and water bodies. The final afforestation suitability map showed that 151.33 km² was very suitable and 192.06 km² was suitable, mostly in the northeastern and southeastern urban fringes. This was because the terrain and subclimatic conditions were good. The proposed methodology illustrates that urban green infrastructure planning can be effectively directed within climate adaptation frameworks through the integration of remote sensing and spatial decision-support tools, especially in ecologically sensitive and rapidly urbanizing areas. Full article

Climate change significantly impacts agricultural infrastructure, particularly in communal land farming systems, where socio-economic vulnerabilities intersect with environmental stressors. This study examined the effects of extreme weather events (floods, droughts, strong winds, frost, and hail) on various agricultural infrastructures—including bridges, arable land, soil erosion control structures, dipping tanks, roads, and fences—using an ordered probit model. A survey was conducted using structured questionnaires between August and September 2023, collecting data from communal farmers (n = 60) in oKhahlamba Municipality, Bergville. Key results from respondents showed that roads (87%), bridges (85%), and both arable land and erosion structures were reported as highly affected by extreme weather events, especially flooding and frost. Gender, the type of farmer, access to climate information, and exposure to extreme weather significantly influenced perceived impact severity. The ordered probit regression model results reveal that drought (p = 0.05), floods (p = 0.1), strong winds (p = 0.05), and frost (p = 0.1) significantly influence the perceived impacts on infrastructure. Extreme weather events, including flooding (p = 0.012) and frost (p = 0.018), are critical drivers of infrastructure damage, particularly for smallholder farmers. Cumulative impacts—such as repeated infrastructure failure, access disruptions, and increased repair burdens—compound over time, further weakening resilience. The results underscore the urgent need for investments in flood-resilient roads and bridges, improved erosion control systems, and livestock water infrastructure. Support should also include gender-sensitive adaptation strategies, education on climate risk, and dedicated financial mechanisms for smallholder farmers. These findings contribute to global policy discourses on climate adaptation, aligning with SDGs 2 (Zero Hunger), 9 (Industry, Innovation, and Infrastructure), and 13 (Climate Action), and offer actionable insights for building infrastructure resilience in vulnerable rural contexts. Full article

Energy management strategies (EMS) in the context of electric or hybrid vehicles can optimize the available energy by minimizing consumption. Most optimization-based EMS are not real-time-applicable for an accurate estimation of future consumption. The performance of these strategies also strongly depends on the driving patterns, which may be influenced by road and traffic conditions, among other factors such as driving style, weather, vehicle type, etc. The primary contribution of this work is to develop a novel two-layer driving pattern recognition (DPR) system for roadway type and traffic classification, thus enabling the identification of unknown patterns for the enhancement of the prediction of energy consumption of an electric vehicle (EV). The novelty of this work lies in the development of a strategy based on real-time data which is capable of classifying driving patterns and implementing an optimized EMS based on the results of the DPR. In the approach, first, labels are defined based on statistical features related to speed followed by the creation of representative driving patterns (RDPs). A neural network-based classifier is then employed for classification into six classes based on four features. A training accuracy of 97.7% is achieved with the classification of unknown speed profiles into the known RDPs. Testing with patterns from two different test routes shows an accuracy of 97.45% and 96.98% during morning and 96.65% and 94.12% during evening hours, respectively. Apart from the route and time of data collection, accuracy is also a function of sampling time horizon and the threshold values chosen for the features. A sensitivity analysis was also performed to evaluate the relative importance of each feature. An EMS based on sequential quadratic programming (SQP) was combined with DPR for the computation of optimal energy consumption. Simulation results show that maximum and minimum energy savings of 61% and 18% were obtained under suburban low traffic and highway high traffic conditions, respectively. An eco-driving or driver speed advisory system may further be developed based on information obtained from multiple routes and varying traffic scenarios. Full article

Avalanches present substantial hazard risk in mountainous regions, particularly when avalanches obstruct roads, either hitting vehicles directly or leaving traffic exposed to subsequent avalanches during cycles. Traditional detection methods often are designed to cover only a limited section of a road stretch, hampering effective risk management. This research introduces a novel approach using Distributed Acoustic Sensing (DAS) for avalanche detection. The monitoring site in Northern Norway is known to be frequently impacted by avalanches. Between 2022–2024, we continuously monitored the road for avalanches blocking the traffic. The automated alert system identifies avalanches affecting the road and estimates accumulated snow. The system provides continuous, real-time monitoring with competitive sensitivity and accuracy over large areas (up to 170 km) and for multiple sites on parallel. DAS powered alert system can work unaffected by visual barriers or adverse weather conditions. The system successfully identified 10 road-impacting avalanches (100% detection rate). Our results via DAS align with the previous works and indicate that low frequency part of the signal (<20 Hz) is crucial for detection and size estimation of avalanche events. Alternative fiber installation methods are evaluated for optimal sensitivity to avalanches. Consequently, this study demonstrates its durability and lower maintenance requirements, especially when compared to the high setup costs and coverage limitations of radar systems, or the weather and lighting vulnerabilities of cameras. Furthermore the system can detect vehicles on the road as important supplemental information for search and rescue operations, and thus the authorities can be alerted, thereby playing a vital role in urgent rescue efforts. Full article

Business Finland 6G Visible project’s objective is the development of 6G-era service and architecture solutions utilizing autonomous and semi-autonomous driving, with both physical and logical computational elements and with use cases for real-life verification and validation. Finnish Meteorological Institute is focusing especially on weather- and safety-related services for autonomous vehicles. We are tailoring our road weather services for the special needs of autonomous driving, keeping in mind that autonomous vehicles are more sensitive to the harsh winter weather conditions and benefit from more accurate weather information considering the sensor systems of each vehicle. Employing weather radar-based nowcasting of more accurate short-term precipitation forecasting benefits autonomous traffic, especially in cases of heavy local precipitation by re-routing/route planning and avoiding heaviest precipitation. Evaluation of autonomous vehicles’ sensor systems’ sensitivity to harsh weather conditions allows for weather forecasting based on the real vulnerability of each vehicle. Full article

With increasing global concerns related to global warming, air pollution, and environmental health, South Korea is actively implementing various particulate matter (PM) reduction policies to improve air quality. Accurate data analysis, including the investigation of weather phenomena, monitoring, and integrated prediction, is essential for effective PM reduction. However, the factors influencing the PM generated from domestic road sections have not yet been systematically analyzed, and currently, no predictive models utilize weather and traffic data. This study analyzed the correlations among factors influencing PM to develop models for estimating fine and coarse PM (PM_2.5 and PM₁₀, respectively) concentrations in road sections. Regression analysis models were used to assess the sensitivity of PM_2.5 and PM₁₀ concentrations to the traffic volume, whereas machine learning-based models, including linear regression, convolutional neural networks, and random forest models, were constructed and compared. The random forest models outperformed the other models, with coefficients of determination of 0.74 and 0.71 and mean absolute errors of 5.78 and 9.60 for PM_2.5 and PM₁₀, respectively. These results indicate that the random forest model provides the most accurate PM concentration estimates for road sections. The practical applications of the developed models were considered to inform effective transportation policies aimed at reducing PM. The developed model has practical applications in the formulation of transportation policies aimed at reducing PM. In particular, the model will play an important role in data-driven policymaking for sustainable urban development and environmental protection. By analyzing the correlation between traffic volume and weather conditions, policymakers can formulate more effective and sustainable strategies for reducing air pollution. Full article

National Highway G559 is the first highway in Southeast Tibet into Motuo County, which has not only greatly improved the difficult situation of local roads, but also promoted the economic development of Tibet. However, rainfall-induced shallow landslides occur frequently along the Bomi–Motuo section, which seriously affects the safe operation and construction work of the highway. Therefore, it is urgent to carry out geological disaster assessment and zoning along the highway. Based on remote-sensing interpretation and field investigation, the distribution characteristics and sliding-prone rock mass of shallow landslides along the Bomi–Motuo Highway were identified. Three-dimensional stability analysis of regional landslides along the Bomi-Motuo Highway under different rainfall scenarios was carried out based on the TRIGRS and Scoops3D coupled model (T-S model). The temporal and spatial distribution of potential rainfall landslides in this area is effectively predicted, and the reliability of the predicted results is also evaluated. The results show that: (1) The slope structure along the highway is mainly composed of loose gravel soil on the upper part and a strong weathering layer of bedrock on the lower part. The sliding surface is mostly a circular and plane type, and the main failure types are creep–tensile failure and flexural–tensile failure. (2) Based on the T-S coupling model, it is predicted that the potential landslide along the Bomi–Motuo Highway in the natural state is scattered. The distribution area of extremely unstable and unstable areas accounts for 4.92% of the total area. In the case of extreme rainfall once in a hundred years, the proportion of instability area (Fs < 1) predicted by the T-S coupling model 1 h after rainfall is 7.74%, which is 1.57 times that of the natural instability area. The instability area (Fs < 1) accounted for 43.40% of the total area after 12 h of rainfall. The potential landslides were mainly distributed in the Bangxin–Zhamu section and the East Gedang section. (3) The TRIGRS and T-S coupling model is both suitable for predicting the temporal–spatial distribution of rainfall-induced shallow landslides, but the TRIGRS model has the problem of over-prediction. The instability area predicted by the T-S coupling model accounted for 43.30%, and 74% of the historical landslide disaster points in the area were correctly predicted. (4) In terms of rainfall response, the T-S coupling model shows higher sensitivity. The %LR_class (Fs < 1) index of the T-S coupling model is above 50% in different time periods, and its landslide-prediction effect (%LR_class = 78.80%) was significantly better than that of the one-dimensional TRIGRS model (%LR_class = 45.50%) under a 12 h rainfall scenario. The research results have important reference significance for risk identification and disaster reduction along the G559 Bomi–Motuo Highway. Full article

The proliferation of autonomous trucking demands a sophisticated understanding of the risks associated with the diverse U.S. interstate system. Traditional risk assessment models, while beneficial, do not adequately address the state and regional variations in factors that significantly impact the safety and efficiency of autonomous freight transport. This study addresses the problem by developing a composite risk index that evaluates the safety of U.S. interstate routes for autonomous trucking, considering both state and regional differences in traffic volumes, road conditions, safety records, and weather patterns. The potential for autonomous trucking to transform the freight industry necessitates a risk assessment model that is as dynamic and multifaceted as the system it aims to navigate. This work contributes a regionally sensitive risk index using GIS methodologies, integrating data from national databases, and applying statistical analysis to normalize risk factors. The findings reveal significant state and regional disparities in risk factors, such as the predominance of precipitation-related risks in the Southeast and traffic in the Far West. This work provides a targeted approach to risk assessment for policymakers and infrastructure planners and offers a strategic tool for logistics companies in optimizing autonomous trucking routes. The long-term benefit is a scalable model that can adapt to evolving data inputs and contribute to the broader application of risk assessment strategies in various domains. Full article

With the development of autonomous driving and the emergence of various intelligent traffic scenarios, object detection technology based on deep learning is more and more widely applied to real traffic scenarios. Commonly used detection devices include LiDAR and cameras. Since the implementation of traffic scene target detection technology requires mass production, the advantages of millimeter-wave radar have emerged, such as low cost and no interference from the external environment. The performance of LiDAR and cameras is greatly reduced due to their sensitivity to light, which affects target detection at night and in bad weather. However, millimeter-wave radar can overcome the influence of these harsh environments and has a great auxiliary effect on safe driving on the road. In this work, we propose a deep-learning-based object detection method considering the radar range–Doppler spectrum in traffic scenarios. The algorithm uses YOLOv8 as the basic architecture, makes full use of the time series characteristics of range–Doppler spectrum data in traffic scenarios, introduces the ConvLSTM network, and exerts the ability to process time series data. In order to improve the model’s ability to detect small objects, an efficient and lightweight Efficient Channel Attention (ECA) module is introduced. Through extensive experiments, our model shows better performance on two publicly available radar datasets, CARRADA and RADDet, compared to other state-of-the-art methods. Compared with other mainstream methods that can only achieve 30–60% mAP performance when the IOU is 0.3, our model can achieve 74.51% and 75.62% on the RADDet and CARRADA datasets, respectively, and has better robustness and generalization ability. Full article

The development of triboelectric nanogenerators (TENGs) over time has resulted in considerable improvements to the efficiency, effectiveness, and sensitivity of self-powered sensing. Triboelectric nanogenerators have low restriction and high sensitivity while also having high efficiency. The vast majority of previous research has found that accidents on the road can be attributed to road conditions. For instance, extreme weather conditions, such as heavy winds or rain, can reduce the safety of the roads, while excessive temperatures might make it unpleasant to be behind the wheel. Air pollution also has a negative impact on visibility while driving. As a result, sensing road surroundings is the most important technical system that is used to evaluate a vehicle and make decisions. This paper discusses both monitoring driving behavior and self-powered sensors influenced by triboelectric nanogenerators (TENGs). It also considers energy harvesting and sustainability in smart road environments such as bridges, tunnels, and highways. Furthermore, the information gathered in this study can help readers enhance their knowledge concerning the advantages of employing these technologies for innovative uses of their powers. Full article

Infrared (IR) land surface emissivity (LSE) plays an important role in numerical weather prediction (NWP) models through the satellite radiance assimilation. However, due to the large uncertainties in LSE over the desert, many land-surface sensitive channels of satellite IR sensors are not assimilated. This calls for further assessments of the quality of satellite-retrieved LSE in these desert regions. A set of LSE observations were made from field experiments conducted on 16–18 October 2013 along a south/north desert road in the Taklimakan Desert (TD), China. The observed LSEs (EOBS) are thus used in this study as the reference values to evaluate the quality of Combined ASTER MODIS Emissivity over Land (CAMEL) data. Analysis of these data shows four main results. First, the CAMEL datasets appear to sufficiently capture the spatial variations in LSE from the oasis to the hinterland of the TD (this is especially the case in the quartz reststrahlen band). From site 1 at the southern edge of the Taklimakan Desert to site 10 at the northern edge, the measured LSE and the corresponding CAMEL observation in the quartz reststrahlen band first decrease and reach their minimum around sites 4–6 in the hinterland of the Taklimakan Desert. Then, the LSE increases gradually and finally reaches its maximum at site 10, which has a clay ground surface, showing that the LSE is higher at the edges of the desert and lower in the center. Second, the CAMEL values at 11.3 μm have a zonal distribution characterized by a northeast–southwest strike, though such an artifact might have been introduced by ASTER LSE data during the merging process that created the CAMEL dataset. Third, the unrealistic variation of the original EOBS can be filtered out with useful signals, as identified by the first six principal components of the PCA conducted on the laboratory-measured hyperspectral emissivity spectra (ELAB). Fourth, the CAMEL results correlate well with the measured LSE at the 10 observation sites, with the observed LSE being slightly smaller than the CAMEL values in general. Full article

In this study, the spatiotemporal distributions of highway blockage and the low-visibility weather events in eastern China are studied by taking Jiangsu Province as an example. Based on the record table data of highway-blocking events, a vulnerability evaluation model for the highway network in Jiangsu Province is established using the weight assignment methods of the fuzzy analytic hierarchy process (FAHP) and criteria importance though intercriteria correlation (CRITIC). By using the geographic information system, the vulnerability evaluation map of road network in low-visibility weather in Jiangsu Province is finally drawn. The results show that the monthly blockage events on Jiangsu highways are more frequent in the north than in the south and are more frequent along the coast than inland, with the highest occurrence number in winter and a second peak in May. There are basically no blockage events from July to October. Traffic blockage on Jiangsu highways mainly occurs between 22:00 and 08:00 Beijing time. In the afternoon, there are almost no highway-blocking events caused by low-visibility weather. The vulnerability of highway blockage in Jiangsu Province is high in the north and low in the south and high in coastal areas and relatively low in inland. The section K6-K99 of the G30 Lianhuo Highway is the most sensitive. Full article

Climate change is contributing to extreme weather conditions, which transform the scale and degree of flood events. Therefore, it is important for relevant government agencies to effectively respond to both extreme climate conditions and their impacts by providing more efficient asset management strategies. Although international research projects on water-sensitive urban design and rural drainage design have provided partial solutions to this problem, road networks commonly serve unique combinations of urban-rural residential and undeveloped areas; these areas often have diverse hydrology, geology, and climates. Resultantly, applying a one-size-fits-all solution to asset management is ineffective. This paper focuses on data-driven flood modelling that can be used to mitigate or prevent floodwater-related damage in Western Australia. In particular, a holistic and coherent view of data-driven asset management is presented and multi-criteria analysis (MCA) is used to define the high-risk hotspots for asset damage in Western Australia. These state-wide hotspots are validated using road closure data obtained from the relevant government agency. The proposed approach offers important insights with regard to factors influencing the risk of damage in the stormwater management system. Full article

The core task of any autonomous driving system is to transform sensory inputs into driving commands. In end-to-end driving, this is achieved via a neural network, with one or multiple cameras as the most commonly used input and low-level driving commands, e.g., steering angle, as output. However, simulation studies have shown that depth-sensing can make the end-to-end driving task easier. On a real car, combining depth and visual information can be challenging due to the difficulty of obtaining good spatial and temporal alignment of the sensors. To alleviate alignment problems, Ouster LiDARs can output surround-view LiDAR images with depth, intensity, and ambient radiation channels. These measurements originate from the same sensor, rendering them perfectly aligned in time and space. The main goal of our study is to investigate how useful such images are as inputs to a self-driving neural network. We demonstrate that such LiDAR images are sufficient for the real-car road-following task. Models using these images as input perform at least as well as camera-based models in the tested conditions. Moreover, LiDAR images are less sensitive to weather conditions and lead to better generalization. In a secondary research direction, we reveal that the temporal smoothness of off-policy prediction sequences correlates with the actual on-policy driving ability equally well as the commonly used mean absolute error. Full article