M25 Motorway Research Articles

A new spatiotemporal convolutional neural network model for short-term crash prediction

AbstractPredicting short-term traffic crashes is challenging due to an imbalanced data set characterized by excessive zeros in noncrash counts, random crash occurrences, spatiotemporal correlation in crash counts, and inherent heterogeneity. Existing models struggle to effectively address these distinct characteristics in crash data. This paper proposes a new joint model by combining the time-series generalized regression neural network (TGRNN) model and the binomially weighted convolutional neural network (BWCNN) model. The joint model aims to capture all these characteristics in short-term crash prediction. The model was trained and tested using real-world, highly disaggregated traffic data collected with inductive loop detectors on the M1 motorway in the UK in 2019, along with crash data extracted from the UK National Accident Database for the same year. The short-term is defined as a 30-min interval, providing sufficient time for a traffic control center to implement interventions and mitigate potential hazards. The year was segmented into 30-min intervals, resulting in a highly imbalanced data set with over 99.99% noncrash samples. The joint model was applied to predict the probability of a crash occurrence by updating both the crash and traffic data every 30 min. The findings revealed that 75.3% of crashes and 81.6% of noncrash events were correctly predicted in the southbound direction. In the northbound direction, 78.1% of crashes and 80.2% of noncrash events were accurately captured. Causal analysis and model-based interpretation were used to analyze the relative importance of explanatory variables regarding their contribution to crashes. The results reveal that speed variance and speed are the most influential factors contributing to crash occurrence.

The Possibility of Cross-Border Cooperation of Regional Airports Through the Example of Osijek and Pécs-Pogány

Abstract On January 1st 2023, Croatia joined the Schengen area, which means that border controls on persons will no longer be carried out at the common Croatian-Hungarian border. This will facilitate traffic between the counties of Baranya and Osijek-Baranya, which will be further enhanced by the opening of the 20 km final section of the M6 motorway, scheduled for the first quarter of 2024. In this situation, new opportunities will open up for exploiting the mutual benefits of cooperation between these counties, such as the cross-border cooperation between the regional airports near Pécs and Osijek. The study will explore the specificity of both facilities and important conclusions could provide useful lessons to other regional airports facing similar issues.

Assessing temporary traffic management measures on a motorway: Lane closures vs narrow lanes for connected and autonomous vehicles in roadworks

AbstractConnected and automated vehicles (CAVs) are being developed and designed to operate on existing roads. Their safe and efficient operation during roadworks, where traffic management measures are often introduced, is crucial. Two alternative measures are commonly applied during roadworks on motorways: (i) closing one or multiple lanes (ii) narrowing one or all lanes. The former can cause delays and increased emissions, while the latter can pose safety risks. This study uses a VISSIM‐based traffic microsimulation to compare the effectiveness of these two strategies on traffic efficiency and safety, considering various market penetration rates (MPR) of CAVs. The model was calibrated and validated with the data collected from M1 motorway in the United Kingdom. Results show that average delays per vehicle‐kilometre‐travelled decreased from 102.7 to 2.5 s (with lane closure) and 23.6 to 0.6 s (with narrow lanes) with 0% and 100% CAV MPR, respectively. Moreover, safety in narrow lanes improved by 4.8 times compared to 1.5 times improvement in lane closure with a 100% CAV MPR; indicating that narrow lanes would result in better safety performance. These findings could assist transport authorities in designing temporary traffic management measure that results in better CAV performance when navigating through roadworks.

Hybrid short-term traffic flow prediction based on the effect of non-linear sequence noise

<abstract> <p>Short-term traffic flow prediction is crucial for intelligent transport systems and mitigating traffic congestion. Therefore, precise prediction of real-time traffic conditions is becoming more important. Currently, the existing prediction models lack the ability to effectively extract spatio-temporal characteristics and fail to adequately account for the impact of non-linear noise. To address these issues, the study proposes a hybrid short-term traffic flow prediction model based on spatio-temporal characteristics. First, the method decomposes the initial spatio-temporal traffic sequence data into multiple modal components using the complementary ensemble empirical modal decomposition method. Then, spatio-temporal characteristics are extracted from the decomposed spatio-temporal components using a deep residual network. The predicted values of each factor are combined to obtain the final predicted values. To validate the model, traffic flow data that is collected at point 4909A on the M25 motorway in London is used. The results indicate that the proposed model outperforms other models in terms of accuracy metrics such as root mean square error, mean absolute percentage error, mean absolute error, mean squared error, and coefficient of determination. Therefore, the model has high accuracy and practicality and exhibits great potential for short-term traffic flow prediction.</p> </abstract>

Szolnok – Milléri-holtág part I-II. több korszakú lelőhely őrlőkő leletei archeometriai vizsgálatának előzetes eredményei : Új adatok a domoszlói piroxénandezit nyersanyag régészeti elterjedéséhez

The multi-period archaeological site Szolnok – Milléri-holtág part I-II is located in the north-eastern vicinity of Szolnok, approximately 5 km from the town, on the high bank of the Milléri-holtág. The total excavated area is almost 27 000 m2 . The preventive excavation was performed by the staff of the Hungarian National Museum in two campaigns (in 2014 and 2015) connected with the M4 motorway constructions. Most excavated settlement features belonged to a Middle Iron Age (Scythian Period) and a Late Iron Age (Celtic Period) rural settlement with scattered structures. Besides these, other settlement features were found from the Neolithic, Late Bronze Age and Medieval Period (Árpád Period). It has to be mentioned that in the excavated part of the Scythian Period settlement, only circular and oval structures were found. The rectangular features – typical for other settlements of the period – were absent in Milléri-Holtág part I-II. However, the archaeological finds were typical: ceramic assemblages were characterised by long-lasting forms (pots, bowls) of the Iron Age household ceramics. The assemblages of the Late Iron Age features were very similar to the vessel types of the earlier period. The partition of the artefacts can only be made with the help of some characteristic forms and ornamentations that appeared in a close unit. The ground stone assemblage of the site (primarily fragments of grinding stones) was analysed with petrographic and geochemical methods. Based on these investigations, the finds' most frequent raw material type could be identified with the Domoszló-type pyroxene andesite from the Mátra Mountains, studied intensively in the past few years. Other types of andesite were present in the ground stone assemblage in smaller amounts. The identification of the source areas of these different andesite raw material types needs more exploration, not just in the territory of Hungary, but also in some areas beyond the borders, e.g. Subcarpathia (Zakarpatska Oblast, Ukraine), Eastern-Slovakia, Transylvania (Romania).

Spatial distribution of heavy metals, source identification, risk assessment and particulate matter in the M4 motorway.

Metal-containing dust is a potential severe environmental and human health threat. Metals present in dust may originate from car exhausts, tear and wear of tires, and vehicular emissions, which are less manageable. Metal-containing dust from roads can contaminate the soils, and crops alongside motorway. This study aimed to investigate the Pb Cd, Cu, Ni, and Zn concentrations in dust, soil, and vegetation collected from the M4 motorway Faisalabad. The results indicated that average metal concentrations in dust from all sites varies (Pb) 44.01mgkg-1, (Cd) 1.22mgkg-1, (Cu) 49.5mgkg-1, (Ni) 28.3mgkg-1, and (Zn) 113.7mgkg-1. The pollution assessment indices CF and PLI of Industrial city and Painsra had comparatively maximum levels of environmental pollution. Moreover, the geo-accumulation index (Igeo) of metals was high at Chak 115 and Painsra, while Igeo at ten sites was in the following descending order: Cd > Pb > Cu > Ni > Zn. Furthermore, it was identified that the maximum ecological risk index (Eir) was in declining order, i.e., Cd > Pb > Cu > Ni > Zn, at all sites. The potential ecological risk was categorized as high risk in all respective sites. The particulate matter fractions PM2.5 and PM10 represented the maximum risk at the Industrial city site, which was unhealthy, although the Painsra site had poor air quality. The total suspended particulate was classified as hazardous at FDA city and Painsra. In contrast, food crops (maize, sugar cane, and sesame) and soil along the M4 motorway have similar Pb, Cd, Cu, Ni, and Zn contamination patterns like dust. However, two crops, maize and sugarcane, along the M4 motorway were found to be more polluted. The level of metals contamination through dust disposition was consistently higher adjacent to roads, possibly indicating depraved impacts on food crops.

Lane changing and congestion are mutually reinforcing?

This study presents a comprehensive analysis of the relationship between congestion and lane changing, using vehicle trajectory data from the M1 motorway in Sydney. We establish a connection between the distribution of travel time and lane changing frequency and employ a Poisson process to describe the intensity of lane changing occurrences in different travel time ranges. From an individual perspective, lane changing does not bring significant speed benefits in most cases, except when the speed range is between 45 and 50 ​km/h. From a system perspective, the relationship between lane change rate and speed depends on the purpose of the lane changes. In merging, diverging, and lane restriction areas, for instance, mandatory lane changes dominate. In most sections of the motorway, discretionary lane changes are motivated by the expectation of improving speed and/or safety. Additionally, we demonstrate a mutual causality relationship between lane changing and congestion through the Granger causality test. This relationship is more pronounced in general areas during peak periods and contributes to the deterioration of the driving environment.

Intelligent Road Management System for Autonomous, Non-Autonomous, and VIP Vehicles

Currently, autonomous vehicles, non-autonomous vehicles, and VIP (emergency) autonomous cars are using intelligent road management techniques to interact with one another and enhance the effectiveness of the traffic system. All sorts of vehicles are managed and under control using the intersection management unit approach. This study focuses on transportation networks where VIP cars are a major disruption, accounting for 40% of accidents and 80% of delays. Intelligent Mobility (IM) is a strategy promoted in this study that proposes setting up intelligent channels for all vehicle communication. As part of its function, the IM unit keeps tabs on how often each junction is used so that it may notify drivers on traffic conditions and ease their workload. The suggested layout may drastically cut average wait times at crossings, as shown in SUMO simulations. The entrance of a VIP car should disrupt all traffic, but the IM (intersection management) unit effectively manages all traffic by employing preemptive scheduling and non-preemptive scheduling techniques for all types of vehicles. We are employing Nishtar roads, the M4 motorway, Mexico, and Washington roads in our scenario. In comparison to all other routes, the simulation results demonstrate that the Washington road route is better able to manage all vehicle kinds. Washington’s traffic delays for 50 cars of all sorts are 4.02 s for autonomous vehicles, 3.62 s for VIP autonomous vehicles, and 4.33 s for non-autonomous vehicles.

Digital navigation negates the economic benefits of road widening: The case of the M1 motorway

Cost-benefit analysis of road investments involves models that generate travel time savings as the main economic benefit. Evaluation five years after opening of a scheme to widen a section of England’s M1 motorway between junctions 10 and 13 found that the traffic moved more slowly than before the scheme opened. Comparison was made with forecast flows generated by SATURN variable demand modelling and an associated economic model. Substantial net benefits to business users were forecast, whereas for non-business users time saving benefits were more than offset by increased vehicle operation costs, consistent with diversion of local trips to take advantage of the increase in capacity. There is reason to suppose that such diversion is facilitated by the wide adoption of Digital Navigation (known generally as satnav), which makes evident the fastest route choices, even at the expense of increased fuel costs. Diversion of local trips to utilise new strategic road capacity seems likely to be a general phenomenon, which detracts from the economic case for road investment. There is therefore a good case to treat the strategic road network as mature, focussing on improving operational efficiency and exploiting vehicle-to-infrastructure connectivity in the form of Digital Navigation.

Appraising Machine and Deep Learning Techniques for Traffic Conflict Prediction with Class Imbalance

Predicting traffic conflicts is pivotal for vehicle-based active safety system to prevent crashes. Yet, conflict prediction is a challenging task as correct prediction depends on the nature of data and techniques employed. Moreover, traffic conflicts data are naturally imbalanced with traffic conflicts being the minority class. Working with imbalanced dataset might result in biased and inaccurate predictions. Therefore, this study aims to appraise machine learning and deep learning techniques systematically, to identify the optimal technique which can reliably predict real-time traffic conflicts by making use of cost-sensitive learning. Five machine learning techniques were optimised and utilised including: logistic regression (LR), Support vector machines (SVM), deep neural networks (DNN), long short-term memory (LSTM) and LSTM convolutional neural network (LSTM-CNN) to appraise their predictability performance using a large, imbalanced, and disaggregated traffic dataset. Unlike existing studies, a wide range of interconnected factors are employed for real-time traffic conflict prediction to provide a more reliable prediction outcome. A large heterodox dataset was gathered from the M1 motorway in the UK to evaluate these techniques. Results suggested that DNN outperform other techniques in predicting conflicts with 0.72 sensitivity at 5% false alarm rate. Such promising results reflect that DNNs can be further applied to deepen our understanding in predicting traffic conflicts design more reliable primary safety systems for intelligent vehicles. Moreover, exploring state-of-the-art classification techniques with class imbalance on big data is significant to the future of big data analytics.

Enhancement of traffic management algorithms for UK motorways

The overall aim of this work is to review and improve traffic CM algorithm to delay the onset of flow breakdown. The results indicated that compared to other two classic models, the Underwood model was able to match the field data on the M25 motorway consistently and capture the speed-flow relationships successfully, in terms of larger R-squared coefficient (R2) and smaller average values of root mean squared error (RMSE). In addition, it was found that Gaussian function can describe the relationship between flow values at the turning points of traffic speed and flow curve and the threshold of the CM algorithm. The fitted traffic speed and flow curve showed that the values at the turning points were significantly reduced under light and heavy rainfall. Thus, the threshold values of the CM algorithm should be optimized according to the determined Gaussian function in the present work.

Wasserstein Generative Adversarial Network to Address the Imbalanced Data Problem in Real-Time Crash Risk Prediction

Real-time crash risk prediction models aim to identify pre-crash conditions as part of active traffic safety management. However, traditional models which were mainly developed through matched case-control sampling have been criticised due to their biased estimations. In this study, the state-of-art class balancing method known as the Wasserstein Generative Adversarial Network (WGAN) was introduced to address the class imbalance problem in the model development. An extremely imbalanced dataset consisted of 257 crashes and over 10 million non-crash cases from M1 Motorway in United Kingdom for 2017 was then utilized to evaluate the proposed method. The real-time crash prediction model was developed by employing Deep Neural Network (DNN) and Logistic Regression (LR). Crash predictions were performed under different crash to non-crash ratios where synthetic crashes were generated by Wasserstein Generative Adversarial Network (WGAN), Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN) sampling respectively. Comparisons were then made with algorithmic-level class balancing methods such as cost-sensitive learning and ensemble methods. Our findings suggest that WGAN clearly outperforms other oversampling methods in terms of handling the extremely imbalanced sample and the DNN model subsequently produces a crash prediction sensitivity of about 70% with a 5% false alarm rate. Based on the findings of this study, proactive traffic management strategies including Variable Speed Limit (VSL) and Dynamic Messing Signs (DMS) could be deployed to reduce the probability of crash occurrence.

Building demolition estimation in urban road widening projects using as-is BIM models

Building demolition caused by urban road widening projects can lead to engineering, economic, and environmental issues and should be planned at the design stage. Based on as-is BIM, this paper proposes a method to estimate the building demolition caused by urban road widening using online map data and statistics on government websites. The as-is BIM models of the existing old road and its surrounding buildings are created, and the BIM models of the newly widened road are built based on the as-is BIM models considering road components in accordance with road engineering expressions to assist building demolition estimation using clash detection. This paper presents a cost-effective building demolition estimation in urban road widening projects without field surveys. It was tested on the M4 Motorway project in London. It has been proved to be a very practical approach to facilitate urban road planning and decision making.

Steels Specimens’ Inspection with Structured Light Scanner

With the recent rapid advances in technology, the use of 3D scanning systems in the engineering world has become more and more prevalent thanks to the ease of use, the improved data collection process, and the increase in the accuracy of the acquired data. During the rebuilding of the Tisza bridge on the M4 motorway, the contractor discovered that the plates used to build the steel superstructure had developed corrosion damage during several years of storage. Plates with a tolerable level of corrosion were intended to be used, but the question was how the increased surface roughness will affect the fatigue life of the plates and the welded steel fabrications made from the plates. As part of this test, fatigue specimens were measured from the material to be used for the bridge and welded with two different geometries with the help of a structured light 3D scanner (SLS scanner). This paper discusses the measurement and inspection of these steel specimens of a highway bridge, before and after the fatigue test of the parts. From the acquired data we examined defects on the surface of the parts, physical deformations by comparing measured data to a CAD model and calculated the amount of material which was lost during stress testing.

Structural re-design of the Animex Wildlife Bridge for the Hazel Dormouse (Muscardinus avellanarius): lessons learnt from two connectivity mitigation case studies in the UK

Abstract The Hazel Dormouse (Muscardinus avellanarius) is an arboreal mammal present in Europe and Asia minor. The population is declining in the United Kingdom (UK), partially due to habitat fragmentation caused by the development of linear infrastructure such as roads, railways and pipelines. In 2016, we designed and tested an arboreal bridge in Britain that was proven to be effective for Hazel Dormice. Subsequently, the bridge materials were upgraded to meet the technical standards of UK road agencies, so that it could be approved and implemented as mitigation on projects throughout the UK. In the UK, each bridge must be certified for technical approval by the relevant road authority and as the bridge is a unique structure, this can pose challenges on projects. The national safety standards of UK roads would not allow common methods used for arboreal bridges across the world to be applied, so we needed specialised engineering and design adaptations to be implemented. Two overarching installation designs were created: the standalone bridge and the retrofit bridge. Several bridges have now been installed across roads in the UK and we will be discussing the development and implementation process from two case studies: i) a 40-metre retrofit bridge to an underpass in St Athan, Wales and, ii) two 76+ metre bridges retrofit to an overbridge and underpass on the M1 motorway in Gayhurst, Buckinghamshire. The St Athan project was quickly approved and easily installed while the M1 project required several alterations to the design and installation methods to meet specific project requirements. This paper discusses what we have learned from these projects, how these projects have influenced the future designs of the Animex wildlife bridge and how this could be applied to future arboreal wildlife connectivity bridges across the world.

Impact of change in traffic flow on vehicle non-exhaust PM2.5 and PM10 emissions: A case study of the M25 motorway, UK.

This study quantifies the change in traffic flow on the M25 motorway in the UK due to the COVID-19 outbreak. Moreover, the impact of the change in traffic flow on non-exhaust PM2.5 and PM10 emissions for different categories of vehicle was explored. During the year of the COVID-19 outbreak (March 2020 to February 2021), the total traffic flows of passenger cars (PCs), light goods vehicles (LGVs), heavy goods vehicles (HGVs), and long HGVs on the M25 motorway decreased by 38.6%, 27.6%, 15.9% and 7.2%, respectively, in comparison to the previous year. Correspondingly, the total mass of non-exhaust emissions (PM2.5 and PM10) of PCs, LGVs, HGVs, and long HGVs reduced by 38.7%, 27.3%, 16.2% and 7%, respectively. The traffic flows per year before and during the COVID-19 outbreak of long HGVs were 87.2% and 80.7% less than those of PCs. Correspondingly, the long HGVs emitted 10.2% less but 36.3% more PM2.5 emissions, as well as 10.9% and 66.7% more PM10 emissions than the latter, indicating that long HGVs contribute much more to non-exhaust particles than PCs. In addition, it was found that resuspension of road dust on the M25 motorway was the largest contributor to air pollution among non-exhaust emissions, followed by road wear, tyre wear, and brake wear particles.

Structural re-design of the Animex Wildlife Bridge for the Hazel Dormouse (Muscardinus avellanarius): Lessons Learnt from Two Connectivity Mitigation Case Studies in England

The Hazel Dormouse is an arboreal mammal present in Europe and Asia Minor. The population is declining in the United Kingdom (UK), partially due to habitat fragmentation caused by the development of roads and other linear infrastructure. In 2016, we designed and tested an arboreal bridge in Britain that proved to be effective for Hazel Dormice. Subsequently, the bridge materials were upgraded to meet the technical standards of UK road agencies, so that it could be approved and implemented as mitigation on projects throughout the country. In the UK, each bridge must be technically certified by the relevant road authority and, as the bridge is a unique structure, this can pose challenges on projects. Two installation designs were created: the ‘standalone’ bridge and the ‘retrofit’ bridge. Several bridges have now been installed above roads in the UK. We discuss the development and implementation process from two case studies: a 40-metre retrofit bridge to an underpass at St Athan in Wales and two 76+ metre bridges retrofitted to an overbridge and underpass on the M1 motorway at Gayhurst, Buckinghamshire. This poster discusses what we have learned from these projects, how they have influenced the future designs of the Animex wildlife bridge, and the production of best practice guidance to provide a summary of the entire process of implementing a bridge project.

Early Avar cemetery in Babarc : Preliminary report

Archaeological investigations preceded the construction of a maintenance centre by the M6 motorway near Babarc (Baranya County, South-east Hungary) between August 2021 and January 2022. The works included trial excavations, followed by a full excavation of the area. The first phase was carried out by Zsolt Tóth and his team from the Janus Pannonius Museum in Pécs, while the full-scale excavations were conducted by Zsolt Gallina and Gyöngyi Gulyás from the Ásatárs Ltd. in cooperation with Réka Neményi, who participated in the project as an expert of the Museum. The quadrangular uninterrupted excavation area, of more than three hectares, in the multi-period site, comprised a total of 41 Early Avar burials (Fig. 1). The burials were scattered all over the excavation area, representing only part of a cemetery that is, currently, one of the most important sites of the period not only because of the abundance and richness of grave goods but due also to the complexity of the funerary customs observed and the fact that the graves were very little plundered.

THE CHINA-PAKISTAN ECONOMIC CORRIDOR (CPEC) IS A GATEWAY TO PEACE, STABILITY, AND TOURISM SUSTAINABILITY

Tourism development and flow are directly influenced by the travel and transportation linkages. Transit routes are a vivacious segment of the world trade, places connectivity, tourism, and travellers comfortability, reducing price and time between destinations. The 1,878-kilometer route from Khunjrab Pass will connect the Brahma Bahtar Interchange on the M1 Motorway with the city of Gwadar on the Western Alignment. The new trade and business dimensions are arising from the CPEC transit route between Pakistan and China. Gwadar Port has the potential to undertake a critical position in Pakistan’s economic resurgence. This study is established on the qualitative method based on the case studies technique as secondary data analysis. CPEC would offer several direct and indirect benefits to the country, people and especially the local community by securing employment, growing wages, and establishing SMTEs. The CPEC’s economic growth and incentives will enable the provinces into the process of national change. Tourism increases awareness, understanding, poverty reduction, promote development, increase jobs, peace. Keywords: CPEC, Pakistan, China, Tourism, Gawadar, Connectivity, Transit route

Transfer learning for spatio-temporal transferability of real-time crash prediction models

Real-time crash prediction is a heavily studied area given their potential applications in proactive traffic safety management in which a plethora of statistical and machine learning (ML) models have been developed to predict traffic crashes in real-time. However, one of the fundamental issues relating to the application of these models is spatio-temporal transferability. The present paper attempts to address this gap of knowledge by combining Generative Adversarial Network (GAN) and transfer learning to examine the transferability of real-time crash prediction models under an extremely imbalanced data setting. Initially, a baseline model was developed using Deep Neural Network (DNN) with crash and microscopic traffic data collected from M1 Motorway in the UK in 2017. The dataset utilised in the baseline model is naturally imbalanced with 257 crash cases and 16,359,163 non-crash cases. To overcome data imbalance issue, Wasserstein GAN (WGAN) was utilised to generate synthetic crash data. Non-crash data were randomly undersampled due to computational limitations. The calibrated model was then applied to predict traffic crashes for five other datasets obtained from M1 (2018), M4 (2017 & 2018 separately) and M6 Motorway (2017 & 2018 separately) by using transfer learning. Model transferability was compared with standalone models and direct transfer from the baseline model. The study revealed that direct transfer is not feasible. However, models become transferable temporally, spatially, and spatio-temporally if transfer learning is applied. The predictability of the transferred models outperformed existing studies by achieving high Area Under Curve (AUC) values ranging between 0.69 and 0.95. The best transferred model can predict nearly 95% crashes with only a 5% false alarm rate by tuning thresholds. Furthermore, the performances of transferred models are on par with or better than the standalone model. The findings of this study proves that transfer learning can improve model transferability under extremely imbalanced settings which helps traffic engineers in developing highly transferable models in future.