Road Maintenance Research Articles

The use of vehicle‐based observations in weather prediction and decision support

AbstractVehicle‐based mobile observations are taken across the world every day by operational and research meteorological organizations, public transportation agencies, and private car manufacturers. Whether directly weather‐related (e.g., air temperature) or not (e.g., wiper speed), the coverage and frequency of these observations holds the promise of filling in gaps between fixed observing stations and greatly improving situational awareness and weather forecasting, from road surface condition‐specific applications and winter road maintenance to urban and street‐level numerical weather prediction and beyond. However, in order to take advantage of these observations, the weather, water, and climate enterprise must work together with the transportation enterprise across academic, public, and private sectors to provide a mechanism for obtaining these data, so that the benefits of using these unconventional observations may be realized.

Analyzing Road Images for Pothole Detection through Machine Learning Algorithms: A Comprehensive Review

The road accident prediction system leverages deep learning techniques, specifically YOLO (You Only Look Once), for the detection of potholes in road footage. By employing YOLO, the system can efficiently identify and localize potholes within video frames, enabling rapid and accurate detection. Furthermore, the system incorporates a severity prediction module that utilizes the dimensions and characteristics of detected potholes to assess their severity levels. This predictive capability empowers authorities and road maintenance teams to prioritize repair efforts and allocate resources effectively, ultimately contributing to the reduction of road accidents and ensuring safer road conditions for motorists and pedestrians alike. Through the seamless integration of pothole detection and severity prediction functionalities, the road accident prediction system offers a proactive approach to road maintenance and safety management, enhancing overall road infrastructure resilience and public safety.

Optimalisasi Pemanfaatan Dana Desa dalam Pembangunan Infrastruktur di Desa La’bo’ Kecamatan Sanggalangi Kabupaten Toraja Utara

The research used an exploratory descriptive-qualitative approach, collecting data through interviews and documentation from La'bo' Village government agencies. Geographical characteristics influence the village's development, with agricultural land covering 39.6% of its area. Infrastructure development, including roads and highways, is crucial for community mobility. Village Funds (APBN) contributed 91.5% of total costs during 2019–2023. Road maintenance is the most expensive type, followed by concrete rebate and irrigation construction. Despite a decrease in funding due to the COVID-19 pandemic, economic recovery in 2021, 2022, and 2023 is expected to resume infrastructure development. The choice of materials and weather conditions also impact the construction and maintenance processes.

Unveiling Anomalies in Surveillance Videos

Abstract: The implementation of Convolutional Neural Network (CNN) algorithm for the detection of anomalies like fire and potholes in images or videos. Leveraging deep learning technique, the model aims to accurately identify fire, potholes, etc. within various contexts. The CNN architecture is trained on a dataset comprising diverse images to enhance its ability to generalize. This proposed project not only addresses safety concerns by promoting helmet usage and proper maintenance of roads but also contributes to the broader field of computer vision and object detection. This implementation involves training the CNN on annotated datasets, fine-tuning the model for optimal performance, and integrating it into a practical application for efficient anomaly identification. With a focus on real-time detection, the system utilizes image processing techniques and a trained CNN model to analyze visual data from cameras or video feeds. The system's versatility allows integration into surveillance systems, industrial sites, or any environment where fire detection is crucial for safety. By automating the detection process, the project contributes to minimizing human error and ensuring consistent monitoring. The proposed solution holds the potential to significantly impact safety protocols, particularly in industries where protective headgear is paramount. Potholes pose a significant threat to both drivers and pedestrians, leading to accidents and infrastructure damage. The proposed solution leverages CNN's ability to effectively process visual data, making it well-suited for image recognition tasks. Our approach involves training the CNN on a diverse dataset of road images to enable it to accurately identify potholes. The model will learn distinctive features and patterns associated with potholes, allowing for robust detection under various environmental conditions. Real-time implementation on embedded systems or cameras along roadways will enable instantaneous identification and alerting.

ANALISIS LIFE CYCLE COST PERKERASAN KAKU DAN LENTUR JALAN PROVINSI (STUDI KASUS: JALAN RAYA PARE – KEDIRI)

Pare-Kediri Highway is a provincial road which is the main connecting road between Pare and Kediri City. On this road section is often bypassed by vehicles with large loads. However, in existing conditions there is damage that varies. Road planning is generally planned to be used for a certain period of time, for example 10 to 20 years depending on existing transportation needs, in the hope that the road will remain in good condition and suitable for traffic. Road maintenance measures are necessary to ensure good operating conditions throughout the planning period. Maintenance and repair of damaged roads also cost a lot. As a result evaluating road damage and choosing the right type of repair is very important. According to the results of research with the 2017 pavement Design Manual guidelines, flexible pavement thickness was obtained including AC-WC 4 cm, AC-BC 6 cm, AC-Base 16 cm and Class A aggregate foundation layer 15 cm. While the thickness of the rigid pavement using continuous concrete without reinforcement with 30 MPa quality concrete obtained plate thickness of 28.5 cm and a layer of thin concrete foundation (LMC) 10 cm. Based on data processing, the construction cost of flexible pavement amounted to Rp 12,958,812,587.00 while rigid pavement amounted to Rp 30,584,262,345. 00. The Total maintenance cost for flexible pavement is Rp 23,836,678,414.33 while for rigid pavement is Rp 3,208,462,265. 15. So that the results of life cycle cost analysis of this study obtained the total cost during the 20-year life cycle of flexible pavement of Rp 36,795,491,001.33 while rigid pavement of Rp 33,792,724,610. 15. In this case, rigid pavement has a life cycle cost (life cycle cost) which is 8.51% more efficient than flexible pavement.

Optimizing Geotechnical Data Input Based on Light Weight Deflectometer for Road Design and Performance Analysis

This study explores alternative methods for assessing critical parameters in pavement design, specifically Young’s modulus and Poisson’s ratio. While repeated load triaxial testing is traditionally used, its high cost and time requirements drive the search for more efficient methods. Falling weight deflectometer tests are also resource-intensive, leading to the investigation of light weight deflectometer tests. Utilizing EraPave software for analysis, which employs a multi-layer elastic theory back-calculation tool, the research examines material properties through laboratory tests on unbound granular material, sandy soil, silty sand soil, and sandy silty clay soil, providing data for field tests. Field LWD tests, conducted under various moisture contents and dynamic loads, provided data processed through EraPave to predict layer moduli. Results demonstrate LWD’s effectiveness in predicting layer moduli for different construction materials. Despite variations in root mean square error values, LWD data consistently align well with EraPave predictions, underscoring its reliability for pavement evaluation. Case studies illustrate LWD and EraPave’s adaptability to different moisture contents and stresses. This study advocates for LWD tests’ efficiency and highlights the importance of analytical tools like EraPave for accurate pavement assessments, contributing to optimized pavement evaluation processes and informed road construction and maintenance decisions.

Digital sand patch: Using laser scanning and discrete element simulation for rapider pavement texture depth measurement

The sand patch method is one of the most basic methods for measuring pavement texture depth (TD), which is an important reference index for pavement anti-skid performance evaluation and road maintenance. However, manual sand patch method heavily relies on the experience of the operators. The emergence of laser 3D scanning and simulation has made it possible to conduct digital sand patch. This study introduces a digital sand patch framework based on 3D scanning and discrete element simulation for precise TD measurement. We developed a 3D scanner with an accuracy of 0.04 mm to obtain the pavement texture data, along with algorithms for outlier removal and slope correction in point cloud data. The method of 3D reconstruction of triangular meshes was adopted to transform discrete point clouds into continuous 3D models to build 3D pavement models. In addition, the virtual process of rotation-spreading-measurement of the digital sand patch method was constructed by discrete element simulation with reference to the physical principles of the manual sand patch method. At the same time, an adaptive dynamic feedback control logic was proposed to accurately determine the termination conditions of the sand patching process. To validate our method, we collected 126 samples from over 20 km of pavement surfaces with various gradations. The results demonstrated an average relative error of 2.92 % compared to the manual sand patch method, and a correlation coefficient of 0.9926 with the laser scanning Mean Profile Depth (MPD) algorithm. Stability and accuracy tests, including scanning downsampling and volatility assessments, confirmed the robustness of our method. This innovative technique for rapid and precise TD measurement not only offers immediate practical benefits but also sets the stage for future research on pavement skid resistance.

Field Compaction Characteristics of Ultra-Thin Porous Friction Course Based on Laboratory Simulation

As a preventive maintenance treatment, the ultra-thin porous friction course (UPFC) has been widely recognized and used in road maintenance because of its excellent performance and cost effectiveness. The Marshall compaction method (MCM) has been adopted to design UPFC mixtures worldwide, particularly in China. However, there are few studies concerning the field compaction properties of MCM-designed UPFCs. The laboratory test results of this study from simulating on-site compaction showed that all UPFC specimens with thicknesses of less than 20 mm barely achieved the target compaction thickness, and all UPFC specimens with different thicknesses failed to meet the air void (AV) requirements of UPFC mixes designed using the MCM. According to the results of a virtual compaction test, and using the discrete element method, the strong force chains were strengthened as the UPFC thickness decreased inside the specimen, making it difficult to evenly diffuse and transfer inside the specimen and resulting in insufficient compaction of the UPFC. Furthermore, it was demonstrated that the MCM-designed UPFC specimens showed significant differences in the AV distributions along the vertical and lateral directions from those of the UPFC specimens that simulated field compaction. The UPFCs designed using the MCM had a poor correlation with field compaction.

ROAD SAFETY AS FUNDAMENT IN ROAD INFRASTRUCTURE PLANNING

The road safety is a key indicator for the development of the society. May it be a key factor in the development of the road infrastructure? How will it affect the costs of road planning, construction, and maintenance? Will the “saved costs” from lowering the road accidents cover the higher cost of building and maintaining the roads? All those questions are difficult to answer; some seem even impossible. Nevertheless, it is important to analyse the problem, establish theoretical models, and formulate hypotheses. So we need to analyse the correlation between road safety, all the costs for road infrastructure, and the social effect in a theoretical manner. The paper aims to formulate the basis of the problem, and the potential solutions, analyse the needed data, and establish the theoretical models.

Urban Road Surface Condition Sensing from Crowd-Sourced Trajectories Based on the Detecting and Clustering Framework.

Roads play a crucial role in urban transportation by facilitating the movement of materials within a city. The condition of road surfaces, such as damage and road facilities, directly affects traffic flow and influences decisions related to urban transportation maintenance and planning. To gather this information, we propose the Detecting and Clustering Framework for sensing road surface conditions based on crowd-sourced trajectories, utilizing various sensors (GPS, orientation sensors, and accelerometers) found in smartphones. Initially, smartphones are placed randomly during users' travels on the road to record the road surface conditions. Then, spatial transformations are applied to the accelerometer data based on attitude readings, and heading angles are computed to store movement information. Next, the feature encoding process operates on spatially adjusted accelerations using the wavelet scattering transformation. The resulting encoding results are then input into the designed LSTM neural network to extract bump features of the road surface (BFRSs). Finally, the BFRSs are represented and integrated using the proposed two-stage clustering method, considering distances and directions. Additionally, this procedure is also applied to crowd-sourced trajectories, and the road surface condition is computed and visualized on a map. Moreover, this method can provide valuable insights for urban road maintenance and planning, with significant practical applications.

Sustainable Reclaimed Asphalt Emulsified Granular Mixture for Pavement Base Stabilization: Prediction of Mechanical Behavior Based on Repeated Load Triaxial Tests

The stabilization of asphalt pavement bases with granular soil and aggregates emulsified with asphalt is a widely used technique in road construction and maintenance. It aims to improve the mechanical properties and durability of the lower pavement layers. Currently, there is no consensus on the most suitable method for designing emulsified granular aggregates with reclaimed asphalt pavement (RAP), as it is very complex. Therefore, the methodology is generally based on compliance with one or more volumetric or mechanical parameters established in the highway regulations for conventional asphalt mixtures, which does not guarantee the optimization and characterization of the recycled mixture in the base course. In this study, granular mixtures were developed, including five with emulsion and one emulsion-free as a control mix. Granular RAP mixes were designed in this study, including five with emulsion and one emulsion-free as a control mix. The five mixes ranged from 1% to 5% emulsion and were characterized by multi-stage triaxial tests with repeated load resilient modulus (RM) and permanent deformation (PD) to evaluate their mechanical behavior. The results showed that the mixes had RM values between 350 and 500 MPa, consistent with literature values. However, they showed similar levels of accumulated deformation to the control mix without RAP emulsion. The sample with 1 % RAP emulsion exhibited a satisfactory RM value and better performance in PD than the control mix (5 mm) and showed accumulated PD values of up to 4 mm. In contrast, the other samples exhibited deformations of up to 6 mm. In this study, the multi-stagge triaxial RM and PD tests were found to be an effective predictive method for characterizing the behavior of RAP materials in base courses, regardless of the types of admixtures contained. Multi-stage resilient modulus and PD tests can be considered as a predictive method for the behavior of milled material in base courses. They were able to provide initial data for interpreting the behavior of ETB mixtures.

Automated crack localization for road safety using contextual u-net with spatial-channel feature integration

Accurate and timely crack localization is crucial for road safety and maintenance, but image processing and hand-crafted feature engineering methods, often fail to distinguish cracks from background noise under diverse lighting and surface conditions. This paper proposes a framework utilizing contextual U-Net deep learning model to automatically localize cracks in road images. The framework design considers crack localization as a task of pixel-level segmenting, and analyzing each pixel in a road image to determine if it belongs to a crack or not. The proposed U-Net model uses a robust EfficientNet encoder to capture crucial details (spatial features) and overall patterns (channel-wise features) within the road image. This balanced approach helps the model learn effectively from both individual elements and the context of the images, leading to improved crack detection. A customized hierarchical attention mechanism is designed to make U-Net model contextually adaptive to focus on relevant features at different scales and resolutions for accurately localizing road cracks that can vary widely in size and shape. The model's effectiveness is demonstrated through extensive evaluations on the benchmarked and custom-made datasets.

The Prediction of Road Condition Value during Maintenance Based on Markov Process

The first step in the road handling effort is to survey to get an accurate road condition value to take correct action in implementing maintenance. As pavement performance is known to be probabilistic, various levels of uncertainty must be assumed. Modern pavement management methods are ineffective without an effective model to predict pavement performance. Discrete-time Markov chains are the most widely used probabilistic models, and examples from different countries worldwide can be found in pavement management systems. This research aims to predict the value of road conditions during maintenance and compare road assessments with real conditions during road maintenance using the IRI, SDI, and PCI methods using the Markov process. The analysis method used is to collect secondary data from related departments and carry out direct data collection in the field to obtain condition values based on IRI, SDI, and PCI to forecast by making a pavement condition prediction model based on the Markov process and then assessing road conditions by comparing the three index values with the slightest deviation value. The analysis showed that the average value of road conditions with the IRI indicator is 4.45, which is moderate, and the most negligible difference between the probability distribution of pavement condition prediction modeling and the actual survey results was the IRI (International Roughness Index) method. This model is closest to the actual conditions during implementation, with a difference value of 5.7%.

Strength characteristics and mix design of full-depth reclamation of asphalt pavement with cement

The research presents the strength characteristics and theoretical mix design of full-depth reclamation (FDR) with cement for road maintenance and rehabilitation. The reclaimed aggregates used in the study were pulverized and blended on the investigation site by the recycler machine. The FDR mix design covered the reclaimed asphalt pavement (RAP), reclaimed base, and reclaimed subbase courses. The unconfined compressive strength (UCS) was tested on the FDR with cement under different mix proportions, cement content, moisture content, and curing time. Two factors that affect the UCS of FDR, viz., moisture-induced packing density and moisture for cement hydration, were observed. The mix proportion with 40 % RAP required at least 6 % cement to stabilize the FDR for use as a bound base course as per the standard, while the effective limit of cement content for FDR was 9 %. The strength prediction model of FDR with cement was presented theoretically based on the modified soil-moisture/cement ratio concept. The verification of the proposed strength model was performed using 7 and 28-day UCS from another investigation site. The design recommendations for FDR with cement were summarized. This discovery could offer a cost-effective and precise method for the mix design of FDR with cement.

Probabilistic rutting model using NGBoost and SHAP: Incorporating other performance indicators

This study focuses on accurately predicting rutting depth (RD) through a probabilistic prediction model, which is crucial for timely road maintenance and traffic safety. Natural Gradient Boosting (NGBoost) technology is employed to achieve this goal as it provides accurate predictions and estimates the uncertainty of predictions. Furthermore, to explain the decision-making process of the proposed prediction model, Shapley Additive Explanations (SHAP) analysis is applied to identify and quantify significant factors affecting RD. Research results show that the NGBoost model surpasses the traditional Gaussian Process and Random Forest model regarding prediction accuracy and performs better regarding certainty of prediction intervals. Meanwhile, SHAP analysis improves the transparency of model decision-making and further validates the model. Explanatory ability elucidates the impact of other characteristics on RD. The two-stage probabilistic prediction model not only enhances the reliability of predictions but also provides an in-depth understanding of the key influencing factors of pavement performance, improving the efficiency and effectiveness of maintenance measures.

Integrating deep learning, satellite image processing, and spatial-temporal analysis for urban flood prediction

Urban flooding is escalating worldwide due to the increasing impervious surfaces from urban developments and frequency of extreme rainfall events by climate change. Traditional flood extent prediction and mapping methods based on physical-based hydrological principles often face limitations due to model complexity and computational burden. In response to these challenges, there has been a notable shift toward satellite image processing and Artificial Intelligence (AI) based approaches, such as Deep Learning (DL) models, including architectures like Convolutional Neural Networks (CNN). The objective of this research is to predict near real-time (NRT) flood extents within urban areas. This research integrated CNN (U-Net) with Sentinel-1 satellite imagery, Digital Elevation Model (DEM), hydrologic soil group (HSG), imperviousness, and rainfall data to create a flood extent prediction model. To detect flooded areas, a binary raster map was created using calibrated backscatter values derived from the VV (vertical transmit and vertical receive) polarization mode of Sentinel-1 imagery, which was highlighted as having a significant impact on backscatter behavior and prediction results. Application of the model was demonstrated in urban areas of Miami-Dade County, Florida. The results demonstrated the capability of the model to provide rapid and accurate flood extent predictions at a spatial resolution of 10 m, with an overall accuracy of 97.05 %, F-1 Score of 92.49 %, and AUC of 93 % in the study area. The U-Net model’s flood predictions were compared with historical floodplain data and then using GIS overlay analysis, resulting in a Ground Truth Index of 84.05 % that shows the accuracy of the model in identifying flooded areas. The research incorporated crucial flood-influencing data (including rainfall) to the flood extent prediction models and expanded the focus models beyond major rainfall events only to encompass a wider range of flood events. The presented NRT flood extent mapping model has a broad range of applicability, including, but not limited to, the continuous monitoring of flood events and their potential impacts on civil infrastructure assets (e.g., construction, operation, and maintenance of roads and bridges), early warning systems for timely evacuation and preparedness measures, and insurance risk assessment.

A method to detect uniformity of road base course based on impact imaging technology

The damage of road base course has the characteristics of strong concealment and difficulty in detecting. For this reason, the impact imaging method has been used for detection of road base course. This paper discussed systematically collection points setting, excitation mode and data processing method. Through the application in testing for highway pavement base before and after grouting maintenance, the results show that the method is simple and accurate. The detection results can be displayed in a two-dimensional image form and it is easy to be used in road maintenance. This method can be used to identify and locate the damages of the pavement base, to judge the uniformity of the pavement base structure. It can also be used to evaluate the effectiveness of internal damage after grouting repairing.

DETECTION OF ROAD DAMAGES(CRACKS) IN IRAQ BASED ON MACHINE LEARNING

That research aims to develop road maintenance operations that include the road survey process to determine types of defects, knowing the type of proposed maintenance, solving the problem of reporting road problems, and also seeks to facilitate the process of road maintenance at the lowest possible costs To achieve these goals, a project is being designed that automates road maintenance and uses artificial intelligence to determine kind of defect in the way by using the libraries (tensorflow with Detection Object). The proposed study will reach a number of results, which are identifying the defect, knowing its type, , and conducting some engineering operations and calculations to determine the state of the roadway, as a final output. This study will use a deep learning-based object detection method to identify road cracks under different shooting, weather, and illumination scenarios. This makes it possible to identify any cracks in a very short amount of time and at a low cost. Images will take in different weather conditions, such as the intensity of brightness being high, medium or very low. They will also be taken in foggy, rainy and dark conditions. Pictures are also taken at different distances (such as one meter, half a meter, one and a half meters) to study the behavior of the pictures and the possibility of extracting defects from them in different circumstances.

Socialization of Environmental Road Maintenance in Settlements with the Application of Biopores to Reduce Water Runoff to the Road Surface

As a result of rapid population growth, the Montong Are area in Mandalika Village, Mataram City experienced a change in land use from rice fields to residential land. The main obstacle faced is inadequate drainage due to the low position of the location and the height of the ground water level. Therefore, water often overflows onto the road surface during the rainy season, hampering traffic and causing damage to infrastructure. Water runoff can be reduced and drainage can be improved with the use of low-tech solutions such as biopores. Biopores outreach and training is needed to build a sustainable housing environment and reduce the negative impact of water runoff on road infrastructure. The stages of socialization activities include: Preliminary Survey; Preparation for implementation; Implementation of Socialization; evaluation stage; and Preparation of Reports and Outputs. The socialization activity began with the delivery of material about biopores and discussion, followed by a demonstration on how to make biopores. The community has been successfully educated about biopores and their function in absorbing rainwater into the soil and reducing the possibility of erosion and flooding. The community was very enthusiastic about taking part in the socialization of biopores making activities considering its benefits for use in road maintenance activities. The knowledge gained can increase public awareness of utilizing this concept as a solution that can be applied to overcome the problem of runoff and flooding on the road surface. So that people can actively participate in the construction and maintenance of biopores around where they live because of the benefits they experience

An Android Sensors-Based Portable Road Health Monitoring System Utilizing Measurement Uncertainty Analysis

Abstract Road health monitoring systems aim to obtain the technical indexes of roads, and then analyze the usage and the degree of damage of the roads, which can provide an important basis for road construction, maintenance, and management. Road roughness is one of the main technical indexes for road quality evaluation and road health monitoring. This study built a system and implemented it as an application to measure and analyze road longitudinal profiles simply and conveniently using the sensors in a mobile phone. The application uses the accelerometer sensor and the gravity sensor to obtain vertical acceleration by a projection method, then denoises through empirical mode decompositions and a Butterworth filter, which has a repeated measurement error of 11%. Different filters were compared and the repeatability, accuracy, robustness, and effectiveness of the system were analyzed. An index to evaluated road longitudinal profiles is given, so that the results can be analyzed and viewed interactively in the application, and a series of cases are given in this paper.