International Roughness Index Data Research Articles

Comparative Analysis of Deep Neural Networks and Graph Convolutional Networks for Road Surface Condition Prediction

Road maintenance is essential for supporting road safety and user comfort. Developing predictive models for road surface conditions enables highway agencies to optimize maintenance planning and strategies. The international roughness index (IRI) is widely used as a standard for evaluating road surface quality. This study compares the performance of deep neural networks (DNNs) and graph convolutional networks (GCNs) in predicting IRI values. A unique aspect of this research is the inclusion of additional predictor features, such as the type and timing of recent roadwork, hypothesized to affect IRI values. Findings indicate that, overall, the DNN model performs similarly to the GCN model across the entire highway network. Given the predominantly linear structure of national highways and their limited connectivity, the dataset exhibits a low beta index, ranging from 0.5 to 0.75. Additionally, gaps in IRI data collection and discontinuities in certain highway segments present challenges for modeling spatial dependencies. The performance of DNN and GCN models was assessed across the network, with results indicating that DNN outperforms GCN when highway networks are sparsely connected. This research underscores the suitability of DNN for low-connectivity networks like highways, while also highlighting the potential of GCNs in more densely connected settings.

Artificial Neural Network-based model to predict the International Roughness Index of national highways in Nepal

Reliable predictions of pavement performance are crucial for road maintenance, rehabilitation, and reconstruction planning. To facilitate predictions of the International Roughness Index (IRI) changes over time on national highways in Nepal, this study develops a comprehensive overall model, along with regional models that consider climatic and traffic variations among the highways. The study models IRI over time using the Artificial Neural Network (ANN) approach and compares the results with those obtained from a multiple linear regression-based model. The models are developed using pavement IRI, traffic, and climatic (rainfall and temperature) data specific to national highways of Nepal, encompassing 1745 sections and 3710 total observations. The ANN-based overall model has a coefficient of determination (R2) value of 0.82 and outperforms the regression-based model, which has an R2 value of 0.76. The regional models developed for the Terai, Hill, high volume Terai and low volume Terai highways have R2 values of 0.87, 0.91, 0.85 and 0.88, respectively, indicating a good fit. Analysis of the IRI trend over time, as observed from the performance curves generated from the ANN-based model, revealed an S-shaped pattern and lower Root Mean Square Error (RMSE) compared to the regression-based model. Sensitivity analysis highlighted the initial pavement IRI as the most significant parameter in all cases. High temperature days emerged as the second most influential parameter in most models, except for the high volume Terai model, where the number of commercial vehicles serves as the second most sensitive parameter after the initial IRI.

Penggunaan Metode Pavement Condition Index (PCI) dan Present Serviceability Index (PSI) dalam Penilaian Kerusakan Jalan di Kota Palu (Studi Kasus : Jalan Karanja Lembah, Kota Palu)

Street of Karanja Lembah is a provincial road linking Palu City and Sigi Regency. After a visual survey, the road has suffered a lot of damage, especially on its surface. The purpose of this study was to determine the pavement condition values based on the Pavement Condition Index (PCI) method and the Present Serviceability Index (PSI) method, as well as to determine the type of road handling based on the PCI and PSI values obtained on these roads. The PCI method is carried out directly by dividing the road into several segments called segment units, then recording the type of damage, the dimensions of the damage, and the severity of the damage for each type of damage. In research using the PSI method, the PSI value was calculated using IRI (International Roughness Index) data obtained from the Highways Service of Central Sulawesi Province. From the results of the analysis, it was obtained that the average PCI value for Jalan Karaja Lembah was 79.95% with a "very good" pavement condition, while the average PSI value for Jalan Karaja Lembah was 2.13% with a pavement condition "moderate". For the right type of handling for the PSI and PCI methods, namely the type of periodic maintenance.

Development of an Unpiloted Aircraft System–Based Sensing Approach to Detect and Measure Pavement Frost Heaves

Abstract The combination of low temperatures, precipitation, and high-water table causes the formation of subsurface frost in pavements leading to the formation of frost heaves. This leads to significant damage to the structural integrity of the pavements and causes extensive surface roughness. Frost heaving is a common type of distress in cold climate regions, especially for road and airport infrastructures located in remote areas. Research discussed in this article focuses on determining the efficiency and accuracy of photogrammetry-based sensing systems to measure the extent of pavement frost heaves. The sensors are mounted on an unpiloted aircraft system (UAS) capable of providing measurements over large spatial domains in a single flight and are well suited for difficult-to-access regions. Experiments have been conducted on simulated heaves as well as actual cold climate pavement sections. The research described herein provides suitable UAS flight parameters for conducting frost heave measurements. Flight at an altitude of 50 m above the ground surface and a flight speed of 5 m/s with capturing images every 2 s resulted in more than 80 % front and side image overlap. The pavement surface profile has been constructed from extracted photogrammetry elevation data collected in three different seasons. Pavement surface roughness has been measured in terms of the international roughness index (IRI), and variation between measured IRI values has been evaluated during different seasons because of the formation of the frost heave distress. As it is expected, the IRI values increase as the cold season approaches. Moreover, the measured IRI values have been compared with the most recent available IRI data collected by an instrumented vehicle. The key outcomes of this work demonstrate that photogrammetry can reliably detect pavement frost heaves and provide high confidence in the future development of an automated system to measure pavement roughness that is attributable to frost heave distresses.

Predicting Pavement Condition Index Using Machine Learning Algorithms and Conventional Techniques

Government agencies and transportation engineers use pavement management systems (PMS) to evaluate pavement performance and keep pavement above the minimum acceptable performance standards. The Pavement Condition Index (PCI) and the international roughness index (IRI) are among the most commonly used indices to evaluate pavement conditions. Due to IRI data collection being more accessible and less expensive than collecting pavement distress data, this study aims to develop PCI models that can successfully estimate the PCI values based on IRI for flexible pavement using two Machine Learning techniques (ML), namely: Random Forest (RF), and Support Vector Machine (SVM), and three conventional techniques, namely: linear, quadratic, and cubic regression. The study was carried out with the database collected from the Long-Term Pavement Performance (LTPP) program. The results of the dataset reveal that both ML models (RF and SVM) have strong prediction ability with high values of coefficient of determination (R^2 = 99.7 and 96.8) %, and low values of Root Mean Squared Error (RMSE = 1.095 and 3.569) % and Mean Absolute Error (MAE = 0.474 and 2.244). In conclusion, the goodness of fit of the proposed ML models was compared with conventional techniques models previously developed. The results showed that the ML models yielded higher prediction accuracy than conventional techniques.

Correlation of Pavement Distress and Roughness Measurement

Riyadh City established and implemented a Pavement Maintenance Management System (PMMS) through the General Directorate of Maintenance and operation. The system was created to address the difficulties that come with maintaining and reserving the pavement network. To evaluate pavement conditions, Riyadh (PMMS) uses visual checks, structural capacity roughness, and skid resistance. An Urban Distress Index (UDI) is calculated during the visual assessment process. Distressed pavement types, severity, and quantity are taken into account when calculating UDI values. As a result, the procedure gathers extensive data on the pavement’s condition. However, the procedure is time-consuming and very costly. The Automatic Road Analyzer car provides data on road roughness in accordance with the International Roughness Index (IRI). The IRI data are often generated quite quickly and at a cheap cost as compared to the distress survey. This study’s aim is to examine whether a sample of Riyadh city pavement sections can be connected to the IRI depending on the distress type. The research develops statistical models that correlate IRI values with several distress-types associated with roadway classes. Correlating the International Roughness Index values to distress type will eliminate the necessity to implement the manual inspection at a network- level. This saves money and time for PMMS employees when preparing annual maintenance requirements and setting priorities. The finding of the study, of the relationship between the pavement distresses and the International Roughness Index showed a statistically significant relationship between pavement roughness and some ride-quality distresses, like depression and patching, as well as some non-ride quality distresses like potholes and rutting. In addition, for both main and secondary streets, an analysis of variance shows the existence of a correlation between the two variables.

A Deep Learning Model for Road Damage Detection After an Earthquake Based on Synthetic Aperture Radar (SAR) and Field Datasets

This study is a new assessment of damaged roads after the Kumamoto earthquake in southern Japan (2016) using remotely sensed synthetic aperture radar (SAR) data, field data and deep learning. Three SAR images from descending orbits of Sentinel-1 in VV (vertical-vertical) polarizations are considered for radiometric calibration, geocoding and interferometric analyses. Field data in terms of the IRI (international roughness index) were gathered over more than 530 km using a smartphone accelerometer and the BumpRecorder application. The relationship between SAR data and IRI data was investigated in a binary (0 and 1) mode to establish a multilayer perceptron (MLP) model of damaged and intact roads. We found the remote sensing SAR datasets suitable, not only for the detection of damaged roads but also as an indicator of road roughness changes. The classification results for damaged and intact roads indicated that our datasets (SAR and field measurements), together with a deep learning model, yielded acceptable overall accuracy (87.1%).

Estimation of IRI from PASER using ANN based on k-means and fuzzy c-means clustering techniques: a case study

ABSTRACT Pavement roughness, commonly estimated by the International Roughness Index (IRI), plays an essential role in pavement assessment. However, accessibility to IRI data requires the operation of profiling equipment, which may be costly for the agencies. In this regard, the use of IRI prediction models from pavement distresses could be an alternative solution. In this research, 507 kilometres of asphalt pavements in Kermanshah, Iran, were investigated using IRI and Pavement Surface and Evaluation Rating (PASER) as a rapid and cost-effective index. The IRI prediction models from PASER were developed using regression (R 2 = 0.66) and Artificial Neural Network (ANN) (R 2 = 0.69). Regarding the restrictions of the results, the data clustering using k-means and fuzzy c-means (FCM) was taken into consideration to acquire the IRI ranges based on the pavement condition. Using the FCM as the superior approach, the IRI prediction model from PASER and the corresponding membership degrees was developed based on ANN. The results of model development (R 2 = 0.97) and validation (R 2 = 0.85) indicated the desirable performance of the ANN model. This case study can be counted as a practical approach for the agencies to economically investigate the pavement condition, predict the roughness, and also make decisions for maintenance targets at the network level.

Development of Regression Models for Predicting Pavement Condition Index from the International Roughness Index

Flexible pavements are considered an essential element of transportation infrastructure. So, evaluations of flexible pavement performance are necessary for the proper management of transportation infrastructure. Pavement condition index (PCI) and international roughness index (IRI) are common indices applied to evaluate pavement surface conditions. However, the pavement condition surveys to calculate PCI are costly and time-consuming as compared to IRI. This article focuses on developing regression models that predict PCI from IRI. Eighty-three flexible pavement sections, with section length equal to 250 m, were selected in Al-Diwaniyah, Iraq, to develop PCI-IRI relationships. In terms of the quantity and severity of each observed distress, the pavement condition surveys were conducted by actually walking through all the sections. Using these data, PCI was calculated utilizing Micro PAVER software. Dynatest Road Surface Profiler (RSP) was used to collect IRI data of all the sections. Using the SPSS software, linear and nonlinear regressions have been used for developing two models between PCI and IRI based on the collected data. These models have the coefficients of determination (R2) equal to 0.715 and 0.722 for linear and quadratic models. Finally, the results indicate the linear and quadratic models are acceptable to predict PCI from IRI directly.

Comparison of road inequality values using roughometer III and roadroid applications

Roads are essential in the development of an area, where driving safety and comfort are a measure of road construction. We can check road construction by getting an IRI value on a road segment. IRI (International Roughness Index) is the roughness index that most commonly obtained from measured longitudinal road profiles. Roughometer III and Roadroid applications are the tolls to collect IRI data. Roughometer III has more precision than Roadroid, but the Roughometer III is more expensive and more complex than Roadroid. This study tries to make a comparison of IRI values and their correlation between the Roughometer III and Roadroid. The results show that the comparison of IRI Roughometer III values and Roadroid Applications is slightly different. The linear correlation analysis of IRI values on Roughometer III and eIRI values on Roadroid is IRI = 0.8999eIRI + 0.5786 with a correlation level of = 0.8391.

Pavement Deterioration Model Using Markov Chain and International Roughness Index

Pavement deterioration leads to drop in serviceability and possibly failure of pavement sections due to initiation and expansion of distresses such as cracks and rutting. This paper aimed at predicting the future condition of pavement sections based on Markov chain model and the international roughness index (IRI). Developing this model can facilitate life cycle analysis and selecting the correct treatment at the right time. The historical IRI data of Canadian pavement sections were collected from Long term pavement performance (LTPP) database. IRI values were used to assess condition of the pavement sections based on the recommended ranges by the Federal highway administration (FHWA). The transition probabilities were estimated using the percentage prediction method based on historical condition data extracted from the LTPP. These probabilities are assembled in a transition probability matrix essential for the Markov chain model. The developed matrix can be used to forecast pavement conditions after any number of transition periods. The developed method assists in predicting pavement performance and facilitates the decision-making process. The method is applied to a real case study to examine its validity. The model can be expanded further by considering additional data from additional pavement networks.

Artificial neural network modelling to predict international roughness index of rigid pavements

This research focuses on predicting the International Roughness Index (IRI) of rigid pavements using the Artificial Neural Network (ANN) model that uses climate and traffic parameters as inputs. A Long-Term Pavement Performance (LTPP) database is used to extract data from wet-freeze, wet no-freeze, dry-freeze, and dry no-freeze climatic zones. The climate and traffic parameters are Mean Annual Air Temperature, Annual Average Freezing Index, Annual Average Maximum and Minimum Humidity, Annual Average Precipitation, Annual Average Daily Traffic, and Annual Average Daily Truck Traffic. The ANN model is trained with 70% of climate, traffic and IRI data, rest 15% data is used to test the model, and remaining 15% data is used to validate the model. The trained and the validated models are compared by calculating Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among many results, the datasets that are tested with 7–9–9–1 ANN structure with hyperbolic tangent sigmoidal transfer function generated the best prediction models with an RMSE value of 0.01 and MAPE value of 0.01 (1% error) for a rigid pavement located in the wet no-freeze climatic zone.

Comparison of Master Sigmoidal Curve and Markov Chain Techniques for Pavement Performance Prediction

Recently, highway agencies have become in need to enhance their pavement management systems (PMSs) using sound engineering and economic principles that find more prudent solutions to support wise investment choices and preserve the value of infrastructure assets. As pavement performance prediction models are one of the most important and fundamental components in any PMS, this paper focuses on comparing the master sigmoidal curve-based model as a deterministic technique with the Markov chain-based model as a probabilistic technique for the prediction of the international roughness index (IRI) as a pavement performance indicator. The IRI data obtained from the long-term pavement performance (LTPP) program were used to evaluate and compare both methods. In this paper, 44 flexible pavement sections from the GPS-1 experiment incorporating 432 IRI measurements ranging from 0.32 to 5.12 m/km were selected. Results showed that the predictive ability of the investigated models for the selected LTPP data was good with a reasonable coincidence ratio of about 65 percent between the predicted results of the two modeling techniques.

Wavelength sensitivity of roughness measurements using connected vehicles

ABSTRACTResearchers previously demonstrated that a roughness index called the road impact factor (RIF) is directly proportional to the international roughness index (IRI) when measured under identical conditions. A RIF-transform converts inertial signals from connected vehicle accelerometers and speed sensors to produce RIF-indices in real time. This research examines the relative sensitivities of the RIF and the IRI to variations in dominant profile wavelengths. The findings are that both indices characterise roughness from spatial wavelengths up to 2 m with equal sensitivity. However, the RIF-transform maintains its sensitivity when characterising roughness from wavelengths beyond that. The case studies used a certified inertial profiler to collect both RIF and IRI data simultaneously from five different pavement surface types. The RIF/IRI proportionality factors distributed normally among the profiles tested. This result affirms that the RIF and IRI generally agrees. However, differences in the dominant profile wavelength among pavements will produce some spread in the degree of roughness that the indices express.

Measuring and evaluating of road roughness conditions with a compact road profiler and ArcGIS

With a wide range of requirements throughout the world, high-quality road management is subject to increasing demand from a perspective of customer-oriented levels of service. In recent years, road administrators are requested to create a visual map of a road network to monitor conditions. To fulfill these requirements, this study conducted as follows. Firstly, this paper introduces a new compact road profiler to collect the profile data at ease. Using the international roughness index (IRI) to assess public roads in local cities of Japan's Hokkaido prefecture, this study also provides real-time monitoring of pavement roughness conditions. Moreover, this study deals with an effective method for visualizing collected IRI data as an attribute in a geographic information system (GIS) and the database of Japan digital road map (DRM). Secondly, the authors present the measurement results of IRI at two different cities during different seasons by using GIS to compare the road conditions. According to the results clarified on different statistical characteristics of road profiles, this study recommends that it is necessary to establish pavement management system (PMS) in consideration of road class, network of local city, and evaluation and management of road conditions in winter quantitatively. Finally, the authors measure and evaluate ride quality by assessing differences between the inner wheel path (IWP) and outer wheel path (OWP) of the vehicle into account, using the previously mentioned profilers and the driving simulator, which is called KITDS. Results show that information from both wheel paths contributes to improve current monitoring process regarding pavement surface, and expects to construct a high level of PMS for road administration in the future.

IRI performance models for recently constructed low and medium-traffic two lane roads of the province of Biscay

Reliable pavement prediction models are needed for pavement management systems (PMS), as they are a key component to forecast future conditions of the pavement and to prioritize maintenance, rehabilitation and reconstruction strategies. The International Roughness Index (IRI) is the most used parameter worldwide for calibrating pavement roughness and measures reasonably the ride comfort perceived by occupants of passenger cars. The Regional Government of Biscay also collects this value on the road network under its control These surveys are carried out regularly in the XXI century. Several IRI performance models have been proposed by different authors and administrations, varying greatly in their comprehensiveness, the ability to predict performance with accurancy and input data requirements. The aim of this paper is to develop a roughness performance model for Biscay's roads, based on availablbe IRI data, taking into account heavy traffic volume and the age of pavement. Local characteristics as climate conditions and average rainfall are not considered. IRI performance models have been suggested for regional two lane highways with low and medium heavy traffic constructed in the last 20 years in the province of Biscay, with no treatments during their life. They can be applied for flexible pavements, but no logical coherent results have been concluded for semi-rigid pavements. DOI: http://dx.doi.org/10.4995/CIT2016.2016.4108

Detection of Motorway Disorders by Processing and Classification of Smartphone Signals Using Artificial Neural Networks

Potholes, debris, sunken manhole covers and others are common street safety hazards which drivers experience daily as they bump into them unexpectedly while driving. Pavement roughness is usually evaluated based on the International Roughness Index (IRI), which is considered the most prevalent metric. In this work, IRI values are collected by using a smartphone, with built-in vibration sensor, placed on the car’s dashboard while driving around the city. The classification process of IRI values is primarily performed using an Artificial Neural Network (ANN) for the detection of diverse predefined street safety hazards. The designed ANN is a backpropagation pattern classifier, that must be trained to yield either a detected “disorder” area of the road or “normal” area based on the IRI data collected. The process of preparing the training and testing datasets involves a number of pre-processing operations. The IRI values are pre-processed in order to extract the most effective features. Then the network is trained with the normalized feature set by using supervised learning method. The performance of the designed network is compared to a similar works in the literature. Results show that the designed network can successfully classify the street conditions by using IRI values with a success rate that outperforms the classification rates obtained by other works.

The Data Mining Applied for the Prediction of Highway Roughness due to Overloaded Trucks

Currently, the quality of the Indonesian national road network is inadequate due to several constraints, including overcapacity and overloaded trucks. The high deterioration rate of the road infrastructure in developing countries along with major budgetary restrictions and high growth in traffic have led to an emerging need for improving the perfo rmance of the highway maintenance system. However, the high number of intervening factors and their complex effects require advanced tools to successfully solve this problem. The high learning capabilities of Data Mining (DM) are a powerful solution to thi s problem. In the past, these tools have been successfully applied to solve complex and multi -dimensional problems in various scientific fields. Therefore, it is expected that DM can be used to analyze the large amount of data regarding the pavement and traffic, identify the relationship between variables, and provide information regarding the prediction of the data. In this paper, we present a new approach to predict the International Roughness Index (IRI) of pavement based on DM techniques. DM was used to analyze the initial IRI data, including age, Equivalent Single Axle Load (ESAL), crack, potholes, rutting, and long cracks. This model was developed and verified using data from an Integrated Indonesia Road Management System (IIRMS) that was measured with the National Association of Australian State Road Authorities ( NAASRA) roughness meter. The results of the proposed approach are compared with the IIRMS analytical model adapted to the IRI, and the advantages of the new approach are highlighted. We show that the novel data -driven model is able to learn (with high accuracy) the complex relationships between the IRI and the contributing factors of overloaded trucks .

Road roughness evaluation using in-pavement strain sensors

The international roughness index (IRI) is a characterization of road roughness or ride quality that transportation agencies most often report. The prevalent method of acquiring IRI data requires instrumented vehicles and technicians with specialized training to interpret the results. The extensive labor and high cost requirements associated with the existing approaches limit data collection to at most once per year for portions of the national highway system. Agencies characterize roughness only for some secondary roads but much less frequently, such as once every five years, resulting in outdated roughness information. This research developed a real-time roughness evaluation approach that links the output of durable in-pavement strain sensors to prevailing indices that summarize road roughness. Field experiments validated the high consistency of the approach by showing that it is within 3.3% of relative IRI estimates. After their installation and calibration during road construction, the ruggedized strain sensors will report road roughness continuously. Thus, the solution will provide agencies a real-time roughness monitoring solution over the remaining service life of road assets.

Evaluation of low-cost consumer-level mobile phone technology for measuring international roughness index (IRI) values

International roughness index (IRI) values were calculated from multi-step processing of accelerometer data collected using three smartphone devices in three consumer vehicles under 11 test scenarios on a 1000 m stretch of secondary highway in New Brunswick. These data were compared to IRI data from a Class 1 inertial profiler averaged over 1000 m (2.60 m/km, std. dev. = 0.029). The combinations of factors producing average IRI values closest to Class 1 inertial profiler were the compact car, Galaxy SIII, windshield mount, at 80 km/h (2.58 m/km, std. dev. = 0.075) and the SUV, iPhone 5, windshield mount, at 50 km/h (2.63 m/km, std. dev. = 0.054). Changes in device type, vehicle type, and mounting arrangement significantly impacted IRI variance, while vehicle speed (50 km/h and 80 km/h) did not. The development of correction factors and analysis automation could make these devices a low-cost option for real-time network-level pavement management.