Road Characteristics Research Articles

A hybrid model for missing traffic flow data imputation based on clustering and attention mechanism optimizing LSTM and AdaBoost

Reliable traffic flow data is not only crucial for traffic management and planning, but also the foundation for many intelligent applications. However, the phenomenon of missing traffic flow data often occurs, so we propose an imputation model for missing traffic flow data to overcome the randomness and instability bands of traffic flow. First, k-means clustering is used to classify road segments with traffic flow belonging to the same pattern into a group to utilize the spatial characteristics of roads fully. Then, the LSTM networks optimized with an attention mechanism are used as the base learner to extract the temporal dependence of the traffic flow. Finally, the AdaBoost algorithm is used to integrate all the LSTM-attention networks into a reinforced learner to impute the missing data. To validate the effectiveness of the proposed model, we use the PeMS dataset for validation, we impute the data with missing data rate from 10 to 60% under three missing modes, and we use multiple baseline models for comparison, which confirms that our proposed model improves the stability and accuracy of imputing the missing data of the traffic flow with different scenarios.

Spatial scale effects of transportation, social and natural attributes of street environments on perceived activity opportunities for older adults

The street environment correlates with perceived activity opportunities for older adults. While numerous studies have examined the transportation and social attributes of street environments, the natural attributes have been less explored. Furthermore, the nonlinear relationship between the street environment and perceived activity opportunities across different spatial scales remains under-researched. We hypothesize that transportation, social, and natural attributes influence perceived activity opportunities, and their nonlinear effects vary across spatial scales. Therefore, we used activity survey data and multi-source big data from Dalian, China. Employing gradient boosted decision tree (GBDT) methods, we evaluated the nonlinear correlation between the street environment and perceived activity opportunities. Our study considered three community life circle scales: 5-min, 10-min, and 15-min. The results indicated that street features varied significantly at different spatial scales. Specifically, factors such as density of street network, diversity of street interface, distance to the nearest public transport station, accessibility of green space, diversion ratio, and distance to the nearest blue space notably influence perceived activity opportunities across these scales. The study also found that the nonlinear correlations between street environments and perceived activity opportunities were prevalent and varied across spatial scales. These results suggest that priorities for street environment improvements should account for these spatial scale variations. Our research provides multi-scale recommendations for the development of sustainable transportation, age-friendly communities, and the promotion of aging in place.

Modeling Crash Risk on Roadway Networks using Bayesian Regression Trees

Statistical modeling of vehicle crashes leads to a better understanding of how and why such crashes occur. Due to the irregular network structure of roadways, analyses are typically confined to a single roadway rather than considering the entire network collectively. Here, we present methodology to model crash risk of vehicle crashes on irregular roadway networks and estimate how that risk varies with road characteristics. We model vehicle crashes observed on a road network as a Poisson point pattern with a piecewise linear intensity surface. Further, we combine Bayesian additive regression trees (BART) and spatial data analysis to accurately explain the intensity surface allowing inference on the effect of road characteristics on crash risk. We illustrate the methodology using a dataset of vehicle crashes on Interstate highways in Utah.

Annual soil erosion characteristics of unpaved roads in the Loess Plateau hilly and gully region, China

The problem of unpaved road erosion is prominent in the Loess Plateau hilly and gully region. Unpaved roads contribute substantially to watershed sediment due to their high soil bulk density, low infiltration rates and extensive network. In this study, a field investigation was conducted on typical unpaved roads within a typical watershed in this region, focusing on assessing the damage state, annual soil loss and the factors influencing erosion in a comparatively wet year. The results showed that the soil erosion from unpaved roads was very severe, with an annual erosion intensity of 470 t hm−2, following three heavy rain events and two rainstorm events in the summer of 2022. The main unpaved roads (MUR) suffered the most severe road erosion, with 22.2 % of road segments experiencing severe erosion with classical gullies. The erosion gullies on the road had an average depth of 16.1 cm and an average width of 36.5 cm, with the widest being 146.0 cm and the deepest being 174.0 cm. The road erosion intensity was significantly related to drainage area, road area, road length and coverage. Road erosion reduced significantly when the land use in the drainage areas of the road was covered with shrub or grass, or road surface was covered with grass or gravel. Our findings offer valuable insights for road construction and erosion prevention in similar terrains.

Determinants of driver injury severity in electric vehicle crashes: A random parameters binary probit model with heterogeneity in means and variances

This study aims to investigate the factors significantly affecting occupant injury severity in electric vehicle (EV) accidents, with a particular focus on traffic flow characteristics before accidents, which have often been overlooked in previous research. Using data on EV accidents from January 1, 2021, to December 31, 2021, in Guangdong Province, China, this study considers various vehicle, road, weather, and pre-accident traffic flow characteristics. The research employs the random parameters binary probit model with heterogeneity in means and variances, comparing it with the binary probit model and the random parameters binary probit model to comprehensively address unobserved heterogeneity and further explain the factors contributing to the randomness of random variables. The results indicate that the random parameters binary probit model with heterogeneity in means and variances provides a superior fit. The findings reveal that variables such as the time of day, type of vehicle involved in the collision, color of EV, average morning/evening peak traveling hours significantly impact the severity of injuries in EV accidents. Additionally, the black indicator exhibits heterogeneity in mean and variance during the afternoon period. This study offers an in-depth understanding of the mechanisms behind driver injury severity in EV accidents and contributes to the development of effective countermeasures to protect drivers from severe injuries.

Case–control study of fatal bicycle crashes in peri-urban areas of Delhi

ObjectivesThere is a lack of evidence on interventions to improve the safety of cycling use in low- and middle-income countries. We investigated the impact of road design and traffic characteristics...

Exploring patterns in older pedestrian involved crashes during nighttime

Nighttime crashes involving older pedestrians pose a significant safety concern due to their age-related vulnerabilities such as reduced vision and slower reaction times. This study analyzes crash data from Texas for six years (2017–2022) using Association Rules Mining (ARM) to identify patterns and associations affecting crash severity for older pedestrians aged 65–74 years and those over 74 years under varying lighting conditions. The findings reveal that high-speed limits and complex road environments significantly increase the risk of fatal or severe injuries for both age groups, particularly under inadequate lighting. Additionally, demographic factors, adverse weather conditions, and specific road features further influence crash outcomes. These insights highlight the need for interventions, including lower speed limits, enhanced street lighting, and the implementation of advanced technologies such as modern pedestrian detection systems, sensor technology, pedestrian bags, accessible pedestrian signals, to improve the safety of older pedestrians. Policymakers should leverage these insights to formulate strategies that improve road safety for older pedestrians, addressing their unique vulnerabilities in various nighttime conditions.

Measuring Street Quality: A Human-Centered Exploration Based on Multi-Sourced Data and Classical Urban Design Theories

Advancements in analytical tools have facilitated numerous studies on perceived street quality. However, most have focused on limited aspects of street quality, failing to capture a comprehensive perception. This study introduces a quantitative approach to holistically measure street quality by integrating three key dimensions: visual perception, network accessibility, and functional diversity. Using Beijing and Shanghai as case studies, we employed artificial neural networks to analyze street view images and quantify the visual characteristics of streets. Additionally, street network accessibility was assessed through spatial design network analysis, and functional diversity was evaluated using the entropy of points of interest (POIs) data. The evaluation results were combined using the analytic hierarchy process. The reliability and accuracy of this method were validated through further testing. Our approach offers a human-centered, large-scale measurement framework, providing valuable insights for urban street renewal and design.

A High-Resolution Remote Sensing Road Extraction Method Based on the Coupling of Global Spatial Features and Fourier Domain Features

Remote sensing road extraction based on deep learning is an important method for road extraction. However, in complex remote sensing images, different road information often exhibits varying frequency distributions and texture characteristics, and it is usually difficult to express the comprehensive characteristics of roads effectively from a single spatial domain perspective. To address the aforementioned issues, this article proposes a road extraction method that couples global spatial learning with Fourier frequency domain learning. This method first utilizes a transformer to capture global road features and then applies Fourier transform to separate and enhance high-frequency and low-frequency information. Finally, it integrates spatial and frequency domain features to express road characteristics comprehensively and overcome the effects of intra-class differences and occlusions. Experimental results on HF, MS, and DeepGlobe road datasets show that our method can more comprehensively express road features compared with other deep learning models (e.g., Unet, D-Linknet, DeepLab-v3, DCSwin, SGCN) and extract road boundaries more accurately and coherently. The IOU accuracy of the extracted results also achieved 72.54%, 55.35%, and 71.87%.

Machine learning and multisource data analysis approach towards traffic accident risk prediction

Traffic accidents are continually a concern across the world bringing with them huge economic costs and high rates of fatality and injuries each single year. Predictive modeling can lessen such risks if the accident hotspots and timing can easily be ascertained. This study collects various data including historical accident reports, water and meteorological conditions, road characteristics, and telematics data, to form traffic accident risk predictive models. To construct and analyze these predictive models, we use various machine learning techniques such as logistic regression, decision trees, and ensemble methods (Random Forest and Gradient Boosting). The results bear out as efficient and effective, ensemble models are streets ahead than regression-based techniques with Gradient Boosting achieving AUC-ROC scores of up to 0.89. The results of this research can also assist in applying effective safety measures in a more cost-effective manner as well as facilitate the development of efficient transport management systems and policies.

Wildlife-Vehicle Collisions and Mitigation: Current Status and Factor Analysis in South Korea.

Severe habitat loss and fragmentation due to extensive road development have escalated wildlife-vehicle collisions (WVCs) as one of the major causes of wildlife mortality. This study, spanning 9 years from 2009 to 2017, presents comprehensive WVC data in South Korea, including species composition, seasonal and regional patterns, and road factors influencing WVCs, aiming to analyze their impact and propose effective mitigation strategies. We collected WVC data with road variables for 9 years from 4561 km of nationwide monitoring road sections and analyzed the data to understand the relationship between WVCs and road characteristics, as well as species-specific patterns. A nationwide survey identified 13,606 WVCs involving 143 terrestrial vertebrate species, and patterns and models of the top seven mammal species (raccoon dog (Nyctereutes procyonoides), Siberian chipmunk (Eutamias sibiricus), Siberian weasel (Mustela sibirica), water deer (Hydropotes inermis), red squirrel (Sciurus vulgaris), Korean hare (Lepus coreanus), and leopard cat (Prionailurus bengalensis)) were presented. Patterns revealed declines in WVCs overall, except for water deer. Although spatial differences in WVCs seemed linked more to wildlife habitats, certain road features correlated both positively or negatively with WVC frequency, highlighting complexities in the effectiveness of preventative measures. For effective mitigation and prevention of WVCs, comprehensive strategies considering species traits, seasonality, and road types should be implemented.

Multi-feature fusion and multi-attention deep network for enhancing road extraction in remote sensing images

ABSTRACT Road detection in remote sensing (RS) images plays a critical role in applications ranging from urban planning to autonomous navigation systems. However, accurate road extraction remains a challenging task due to the presence of textual-similar objects that can be visually confused with roads, and shadows that can obscure road features. For this regard, we present a novel end-to-end network that leverages multi-feature fusion and multi-attention. Multi-level dual residual blocks are introduced to capture multi-scale and multi-level road features. A channel attention feature fusion module fuses road features from the decoder while suppressing coarse-grain noises. Moreover, a difference channel feature fusion module filters out the interfering texture-similar features and irrelevant background features. Subsequently, a spatial channel feature enhancement module is designed to identify the mis-segmented regions and reclassify these pixels. We conducted extensive experiments on diverse datasets, demonstrating the effectiveness of our approach in improving road detection accuracy, especially in areas with shadows and textual-similar objects. The results indicate that our approach outperforms state-of-the-art methods in handling textual-similar objects and shadow-occluded roads, making it a valuable contribution to the field of road extraction in remote sensing images.

A Study on the Effect of Urban Form on the Street Interface Rhythm Based on Multisource Data and Waveform Classification

Good-quality urban street space is crucial for improving walkability. Frequency and amplitude are the main spatial characteristics of the street interface rhythm, known as a “virtual–real” relation. Exploring the mechanism influencing the urban street interface rhythm can help grasp the movement trend. In this study, the correlation between frequency and urban form is explored through a Pearson correlation analysis with multisource data, and the factors influencing the urban street interface rhythm are presented. The results indicate that frequency has a moderate negative correlation with the block scale and a moderate positive correlation with the number of pedestrian access entrances (PAE-n); the PAE-n also has a strong negative correlation with the block scale. Some spatial characteristics of outstanding streets from different countries are analyzed and discussed based on waveform classification. The regularities of interface rhythm that exist within multiple streets are found: multiple gaps on the street interface exist, acting as a “beat”, which regularly integrates or separates the street interface rhythm. The frequency and amplitude of the “beat” significantly affect streets’ walkability, and the amplitude is generally low and uniform, with good visual accessibility in all directions. A “Small Block and Dense Grid” becomes a key factor in improving walkability. Basic knowledge of the street interface rhythm in urban walking space research is supplemented by this study. Furthermore, theoretical guidance and parametric evidence are provided to improve walkability and promote the continuation of the traditional context.

Capacity analysis of short-distance continuous diversion areas on mountainous urban expressways.

The short-distance continuous diversion area plays a crucial role within mountainous urban expressway systems, significantly enhancing the efficiency of specialized road sections through capacity analysis. This study develops a capacity calculation model tailored to the diversion area's unique characteristics and principal capacity-influencing factors. Initially, the research focuses on a specific short-distance continuous diversion area of a mountainous urban expressway, employing video trajectory tracking technology to gather trajectory data. This data serves as the basis for analyzing road and traffic characteristics. Subsequently, the model computes the capacity influenced by eight variables, including diversion point spacing and deceleration lane length, using VISSIM simulation experiments. A gray correlation analysis identifies key factors, which guide the establishment of the model's fundamental structure through two-factor surface fitting results. Mathematical statistical methods are then applied to resolve the model's parameters, culminating in a robust capacity calculation model. The findings reveal that diversion point spacing, along with primary and secondary diversion ratios, significantly influence capacity. Notably, the capacity exhibits a marked quadratic polynomial relationship with the primary diversion ratio and diversion point spacing, and a linear relationship with the secondary diversion ratio. The model's validity is confirmed through a case study at the diversion area north of Huacun Interchange in Chongqing Municipality, where the discrepancy between calculated and actual capacities is under 5%, underscoring the model's high accuracy. These results offer valuable theoretical and methodological support for the planning, design, and traffic management of diversion areas.

Do Smart Loading Zones help reduce traffic congestion? A causal analysis in Pittsburgh

Rising demand for ride-hailing services and e-commerce delivery intensifies competition for urban curbside spaces, leading to uncoordinated travel behavior, increased traffic congestion and social costs. One possible solution to address those issues is Smart Loading Zones (SLZs), equipped with advanced technologies to optimize curbside use. Yet, the real-world impact of SLZs on traffic flow is unclear due to a lack of real-world data and rigorous studies investigating SLZ’s causal effect on traffic speed. With granular speed data and real-world implementations of SLZs from Pittsburgh, PA, this study applies the regression discontinuity design method to rigorously examine the causal impact of SLZs on traffic speed in the downtown network. The results showed that the introduction of SLZs could enhance the traffic speed of the nearby road segments by 4.5%, while controlling for the underlying trend of speed and multiple influential factors such as time, weather, and road characteristics. In addition, SLZs with a short length could statistically improve traffic speed but those with a long length exert no significant effect. These heterogenous effects might be attributed to the weak enforcement at the time of SLZ deployment in Pittsburgh. The results confirmed the overall positive impact of SLZs on improving congestion. However, policies such as effective dimension planning and robust enforcement policies are essential to maximize the benefits of SLZs.

Study on territory-wide application of low noise road surface in Hong Kong

Hong Kong is one of the metropolitan cities in the world, with highly concentrated road network system and densely populated developments. At times, it is inevitable to build residential buildings near noisy roads, and traffic noise is one of the environmental problems affecting the locals. The Government strives to pre-empt traffic noise issue through planning new road projects or new residential developments. Concerning traffic noise from existing roads, the Government has implemented noise mitigation measures, for instance, to resurface existing roads with Low Noise Road Surface (LNRS) materials, retrofitting of noise barrier or enclosure, to alleviate traffic noise impact. Moreover, the Government is continuously developing and trialing different LNRS materials such as Polymer Modified Stone Mastic Asphalt (PMSMA6) on roads in Hong Kong, which aims for wider application of LNRS. To explore the feasibility and effectiveness of the wider application of LNRS on local roads, the Government has recently conducted a territory-wide study on the application of LNRS on local roads in Hong Kong. This paper attempts to share the common local road characteristics of applying LNRS material and the latest technical findings, such as the effect on population exposure, of the territory-wide study in Hong Kong.

Urban street clusters: unraveling the associations of street characteristics on urban vibrancy dynamics in age, time, and day

Understanding urban vibrancy has been considered crucial to promoting human activities and interactions in public open spaces. Recent advancements in urban big data have facilitated the potential to understand and measure vibrancy patterns throughout cities. While streets are considered the center stage of human activity, previous studies have often overlooked their multifaceted nature and their association with urban vibrancy. In this study, we incorporate multi-source big data and combine a set of features that comprehensively describe the scale, function, and topology of street segments in two Seoul districts: Jung-gu and Gangnam-gu. Using these features, we employ a machine learning clustering technique to classify them into five distinct typologies. Then, with street-level aggregated mobile phone tracking data, we investigate whether street typology characteristics are associated with urban vibrancy with respect to age groups, time of day, and day types (weekends/weekdays). The results show varying relationships between street characteristics with age-, time- and day-vibrancy measures by the identified street typology. Further, we contrast the results of the two districts to evaluate urban vibrancy differences in organic and planned urban layouts. This study enables a more nuanced understanding of urban streets to better comprehend their impact on people’s use of street space. The derived novel insights could assist planners and designers to better pinpoint street management solutions for different age- and time-dependent needs based on the complexities in urban vibrancy dynamics.

Impact of urban road characteristics on vehicle speed: Insights from Brescia, Italy

In managing road infrastructures, a key benchmark is the 85th percentile of vehicle speeds (V85). While V85 can be derived from spot speed samples, these are often lacking on each urban road. Thus, prediction models become valuable tools for examining the relationship between V85 and road characteristics. Although various models exist for rural roads, the impact of roadside characteristics and markings on V85 in urban road networks has been partially investigated, and the effect of traffic calming measures remains fragmented.This study aims to address these gaps by applying a methodology that sheds light on the effects of some variables that influence V85 on urban roads. Specifically, the methodology selects and segments roads along the urban road network of the municipality of Brescia (Italy) and collects data on both road characteristics and 48,000+ spot speed information. Following data cleansing, it processes these data according to three different multiple regression models to analyse the influence of various predictors on V85. Once the best model is estimated, its performance is evaluated, and the final list of significant predictors is obtained.The results revealed that V85 increases with longer homogeneous segments, greater distance to successive intersections, bituminous conglomerate roads with more lanes, and the presence of trees, visible road markings, and posted speed limits. Conversely, V85 decreases in the presence of on-street parking and other obstacles (e.g., walls and road posts), when the density of road intersections and pedestrian crossings increases, when the left crossbar width increases and when the land use crossed is commercial or office, residential or industrial. Nevertheless, no significant effect was found for several traffic calming measures included in the model.These findings can assist road authorities in verifying road operating conditions and planning infrastructure interventions to reduce speeds, thereby creating a safer urban environment for all users.

Integrating Streetscape Images, Machine Learning, and Space Syntax to Enhance Walkability: A Case Study of Seongbuk District, Seoul

As urbanization rapidly progresses, streets have transitioned from mere transportation corridors to crucial spaces for daily life and social interaction. While past research has examined the impact of physical street characteristics on walkability, there is still a lack of large-scale quantitative assessments. This study systematically evaluates street walkability in Seongbuk District, Seoul, through the integration of streetscape images, machine learning, and space syntax. The physical characteristics of streets were extracted and analyzed in conjunction with space syntax to assess street accessibility, leading to a combined analysis of walkability and accessibility. The results reveal that the central and western regions of Seongbuk District outperform the eastern regions in overall street performance. Additionally, the study identifies four distinct street types based on their spatial distribution: high accessibility–high overall score, high accessibility–low overall score, low accessibility–high overall score, and low accessibility–low overall score. The findings not only provide a scientific basis for street development in Seongbuk District but also offer valuable insights for assessing and enhancing walkability in cities globally.

A systematic risk assessment approach for urban roadside infrastructure assets

Revealing potential risks and the influence of these risks on urban roadside vulnerable/risky zones has been a great deal for the last decades owing to increasing vehicular mobility. This study aimed to develop a risk assessment methodology for urban roadside infrastructure assets. In this context, seven risk parameters that are likely to affect hazardous aboveground assets installed on urban roadsides were determined, and weights of each parameter (order of importance) were presented based on expert surveys and literature information using the Analytic Hierarchy Process (AHP) method. Mathematical models were set up for each risk parameter using real field data, The American Association of State Highway and Transportation Officials (AASHTO), literature, related standards, and expert surveys by linear, nonlinear, and binary logistic regression analyses. Risk groups were created, and precautions were offered. The efficiency of the models was verified based on the 28 accident records and field observations in 172 assets. When considering the assets that undergo traffic accidents, 71% of the total assets are ranked in the critical and high-risk group. This ratio is consistent with the risk group definitions assigned in this study; thus, the model proposed is accurate and can be applied reliably. The verification process of the total risk model was sufficiently successful to be used in practice and can be generalized by considering the road and traffic characteristics, infrastructure facilities, and future requirements of the regions or countries that reflect similar historical and cultural concerns. Practitioners, governmental institutes, and researchers can apply this methodology to provide their own data with high transparency and reliability.