<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>An optimal stochastic decision-making model incorporating pavement maintenance and rehabilitation works</title>
      <link>https://trid.trb.org/View/2663620</link>
      <description><![CDATA[An optimal stochastic decision-making model is proposed to generate a long-term maintenance and rehabilitation (M&R) schedule. It applies the discrete-time Markov model which incorporates pavement deterioration and improvement rates via the transition matrix. A transition matrix with 10 condition states includes 17 M&R variables, each representing a distinct M&R treatment. The model aims to optimise the pavement condition rating at the network level while enforcing variable and budget constraints. A simplified efficient procedure is proposed to optimise the model using a cost-effectiveness ratio, CE(𝘟ᵢ), defined as the ratio of a specific M&R treatment cost to the expected improvement outcome. M&R variables with lower CE(𝘟ᵢ)) values are given priority for inclusion in the optimal solutions. The model data requirements include the stochastic parameters represented by the initial state probabilities and transition matrix, and cost units associated with specified M&R treatments. Three case studies are presented to demonstrate the efficacy of the proposed model. The first one employed all 17 M&R variables, the second applied 14 M&R variables with added vehicle operating cost (VOC), and the third only used 8 M&R variables with added VOC. The sample results indicated that more funding is spent on rehabilitation than maintenance as the annual budget increases. The solutions with added VOC provided more rehabilitation works for states with poor/bad pavements. The case with 8 M&R variables resulted in more rehabilitation work at a lower overall M&R cost.]]></description>
      <pubDate>Thu, 14 May 2026 17:04:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2663620</guid>
    </item>
    <item>
      <title>Develop a Methodology for Pavement Drainage System Rating</title>
      <link>https://trid.trb.org/View/2662985</link>
      <description><![CDATA[Effective drainage is critical for preserving pavement integrity and extending service life, yet network-level methods for evaluating pavement drainage conditions remain limited. This study presents a practical methodology for assessing pavement drainage conditions using data from the Louisiana Department of Transportation and Development’s (DOTD) Pavement Management System (PMS). The proposed framework evaluates three key components: (1) pavement surface drainage based on cross-slope, longitudinal grade, and rutting; (2) roadside/shoulder drainage assessed through edge drop-off data and PMS imagery for erosion, vegetation, and debris; and (3) ditch drainage evaluated through PMS imagery for sediment accumulation, erosion, and obstructions. The methodology was applied to five roadway sections to demonstrate implementation and identify correlations between drainage conditions and pavement performance. Results indicate that the pavement surface drainage rating is strongly correlated with actual pavement performance, suggesting its value as a stand-alone monitoring indicator. Fine-scale analysis (0.1-mi. resolution) proved critical for capturing localized drainage deficiencies that disproportionately affect roadway performance. The framework provides actionable insights for maintenance prioritization and early-stage screening of operational deficiencies, although it does not evaluate hydraulic capacity or broader flood risk. Future enhancements, such as artificial intelligence (AI)-powered image analysis and Light Detection and Ranging (LiDAR)-based ditch surveys, could further improve automation, objectivity, and network-level monitoring. Overall, this study demonstrates a practical and scalable approach for integrating drainage condition assessments into network-level pavement management and supporting data-driven maintenance decisions.]]></description>
      <pubDate>Thu, 12 Feb 2026 08:52:13 GMT</pubDate>
      <guid>https://trid.trb.org/View/2662985</guid>
    </item>
    <item>
      <title>Evaluation of MDOT’s Methodologies for both Quantifying Pavement Distress and Modeling Pavement Performance for Life-Cycle Cost and Remaining Service Life Estimation Purposes</title>
      <link>https://trid.trb.org/View/2658082</link>
      <description><![CDATA[Michigan Department of Transportation (MDOT) has been using the Distress Index (DI) since the inception of its pavement management system (PMS) in the early 1990s. DI was developed to help MDOT engineers decide, allocate budgets, and prioritize future maintenance or reconstruction activities. However, the raw data requirements for the DI are complicated (and somewhat unique compared to the rest of the nation). Over the last three decades, the pavement industry has seen many advances in data collection, distress identification, performance modeling, and other processes fundamental to PMSs. Consequently, there was a need to revisit the DI used by MDOT and revise it according to modern pavement data collection standards and calculation methodology. This study aimed to develop an enhanced pavement condition score and associated PMS data collection methodology for use by MDOT. To meet this objective, 2081 flexible and 741 rigid pavement sections were selected from MDOT’s performance database. Then, five different condition indices used by other state agencies were computed using the MDOT's PMS data and compared against MDOT’s Distress Index (DI). Maintenance records were used to compare the magnitudes of different indices right before maintenance activities were performed. The new pavement condition parameter was selected to follow the current state of the practice in its rating scale and consider major distresses. Furthermore, various performance models were used to predict the new condition index and International Roughness Index (IRI) data, and pavement fix lives were estimated for both asphalt and rigid pavements. Building on these advancements, network-level modeling methods were developed to project the future condition of MDOT’s pavement network in terms of IRI, cracking, rutting, and faulting. Using Markovian Transition Probability Matrices (TPMs) and multinomial logistic regression, the study established a robust analytical framework to forecast pavement performance under various maintenance and rehabilitation scenarios. These models enable MDOT to evaluate the long-term effects of different funding strategies, set realistic performance targets in alignment with federal requirements, and support data-driven decision-making for statewide pavement management.]]></description>
      <pubDate>Mon, 02 Feb 2026 14:13:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658082</guid>
    </item>
    <item>
      <title>Rapid Assessment of Network-Level Pavement Conditions Using Novel Tools [supporting dataset]</title>
      <link>https://trid.trb.org/View/2643030</link>
      <description><![CDATA[Abstract of the final report is stated below for reference: Efficient network-level pavement condition assessment is essential for optimizing maintenance and rehabilitation strategies. Traditional methods, such as visual inspections and manual distress surveys, are often subjective, time-consuming, and inefficient for large-scale pavement management. The focus of this collaborative project was to evaluate tools for rapidly and cost-effectively assessing network-level pavement conditions for Oklahoma. As part of Oklahoma Department of Transportation's (ODOT's) engagement in a pooled fund study (TPF-5 (385)), pavement conditions data from I-35 and I-40 in Oklahoma were collected recently using a Traffic Speed Deflectometer (TSD). This study focused on analyzing the TSD data for network-level assessment or rating of the associated pavement. A complementary objective of this study was to collect data from the same pavements using in-house technologies, namely Pave3D 8K available at Oklahoma State University (OSU) and an air-coupled Ground Penetrating Radar (GPR) and Fast Falling weight Deflectometer (FFWD) and compare with TSD data. TSD enabled continuous deflection measurements under moving loads, providing a rapid and comprehensive assessment of pavement structural capacity. A total of six pavement sections were selected on the I-35 and I-40 road network in Oklahoma based on the initial TSD rating. These sections were further tested using FFWD, GPR Pave 3D 8K and field investigations. The data from different technologies were used for performing regression analysis using advanced machine learning models. Finally, pavement condition rating parameters and thresholds were proposed for categorizing the pavement sections into good, fair and poor sections. Findings from this research will contribute to the development of a more efficient, data-driven framework for large-scale pavement condition assessment. Data Summary. Contains 120 items including JPGs, excel, DAT, IMG, and PRJ files. Files cover core pictures, FFWD, GRP, Pave3d, Test Section GPR, and TSDD.]]></description>
      <pubDate>Fri, 09 Jan 2026 16:58:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643030</guid>
    </item>
    <item>
      <title>Rapid Assessment of Network-Level Pavement Conditions Using Novel Tools</title>
      <link>https://trid.trb.org/View/2643029</link>
      <description><![CDATA[Efficient network-level pavement condition assessment is essential for optimizing maintenance and rehabilitation strategies. Traditional methods, such as visual inspections and manual distress surveys, are often subjective, time-consuming, and inefficient for large-scale pavement management. The focus of this collaborative project was to evaluate tools for rapidly and cost-effectively assessing network-level pavement conditions for Oklahoma. As part of Oklahoma Department of Transportation's (ODOT's) engagement in a pooled fund study (TPF-5 (385)), pavement conditions data from I-35 and I-40 in Oklahoma were collected recently using a Traffic Speed Deflectometer (TSD). This study focused on analyzing the TSD data for network-level assessment or rating of the associated pavement. A complementary objective of this study was to collect data from the same pavements using in-house technologies, namely Pave3D 8K available at Oklahoma State University (OSU) and an air-coupled Ground Penetrating Radar (GPR) and Fast Falling Weight Deflectometer (FFWD) and compare with TSD data. TSD enabled continuous deflection measurements under moving loads, providing a rapid and comprehensive assessment of pavement structural capacity. A total of six pavement sections were selected on the I-35 and I-40 road network in Oklahoma based on the initial TSD rating. These sections were further tested using FFWD, GPR Pave 3D 8K and field investigations. The data from different technologies were used for performing regression analysis using advanced machine learning models. Finally, pavement condition rating parameters and thresholds were proposed for categorizing the pavement sections into good, fair and poor sections. Findings from this research will contribute to the development of a more efficient, data-driven framework for large-scale pavement condition assessment.]]></description>
      <pubDate>Fri, 09 Jan 2026 16:58:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643029</guid>
    </item>
    <item>
      <title>Comparing Network-Level Structural Measures Impact on Asphalt Pavement Performance Models</title>
      <link>https://trid.trb.org/View/2612376</link>
      <description><![CDATA[Incorporating structural measures into pavement management systems can enhance the underlying performance models. The traffic speed deflectometer (TSD) offers advantages for network-level testing, but it differs from the traditional falling weight deflectometer (FWD) as a structural measure. It is important to investigate which measure provides the most improvement in pavement performance models. This study compares the impact of four structural measures on pavement performance models of four distress rating dependent variables (cracking, rutting, load distress rating, and critical condition index). Structural measures from the Virginia Department of Transportation pavement management data were analyzed, including ground penetrating radar measure of asphalt thickness, FWD measure of structural number, TSD measure of surface curvature index (SCI), and the site’s pre-treatment rate of deterioration. A multilevel model approach related each structural measure to site-specific performance models of asphalt resurfacing treatments. The TSD measure of SCI demonstrated the greatest impact on the cracking, load distress rating, and critical condition index models with increases in marginal R2 of 0.05, 0.03, and 0.01, respectively. Pavements with higher SCI values reach a failing critical condition index threshold one year sooner. Incorporation of the TSD measure of SCI leads to improved performance models and will benefit pavement management systems.]]></description>
      <pubDate>Thu, 23 Oct 2025 17:02:05 GMT</pubDate>
      <guid>https://trid.trb.org/View/2612376</guid>
    </item>
    <item>
      <title>Automatic Pavement Crack Rating for Network-Level Pavement Management System</title>
      <link>https://trid.trb.org/View/2407389</link>
      <description><![CDATA[Cracking is one of the important distresses that can be used to trigger pavement maintenance treatments. Traditional crack rating is commonly based on the Pavement Condition Index (PCI) approach involving time-consuming visual inspection and manual classification processes. The emergence of automatic and high-speed laser imaging devices significantly improves the efficiency and productivity of pavement crack data collection but it requires suitable methods and concepts for automatic crack ratings. This paper discusses the development of an automatic pavement crack rating using crack data collected from a high speed 3D sensor. Two levels of crack ratings are proposed: Level 1 provides detailed crack information including cracking extent, crack types and severity, and Level 2 is a macro-indicator of general/overall cracking extent on a pavement section of 10 m length. The method and concept were developed and tested initially for Singapore expressway network under the effort of the Land Transport Authority (LTA) of Singapore to integrate crack data into the pavement management system (PMS).]]></description>
      <pubDate>Mon, 22 Sep 2025 08:49:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2407389</guid>
    </item>
    <item>
      <title>A New Approach in Estimating the Overall Condition of Asphalt Pavements Using a Combined Index: An Iranian Case Study</title>
      <link>https://trid.trb.org/View/2301589</link>
      <description><![CDATA[Maintenance activities are of the utmost importance during the pavement lifecycle. Pavement assessment methods can be implemented to discover the leading cause of deterioration and select a proper maintenance activity. Agencies use economical and rapid pavement condition assessment approaches to address maintenance needs. It is understood that recruiting pavement engineers or technicians for field surveys or using automatic equipment for data acquisition are costly approaches. Past studies suggest that a more attractive solution can be using pavement surface images to inspect the condition based on an inclusive subjective index such as Pavement Surface Evaluation and Rating (PASER). Besides, it is also understood that any individual indices do not represent the overall condition of the pavement. The use of only the International Roughness Index (IRI) or visual surface distresses in the maintenance decisions may not be adequate. Therefore, this study proposed a new combined condition index that compensates for the insufficiency of each index. The pavement conditions in 367 sections in Kermanshah, Iran, were evaluated using PASER and IRI. Then, by combining both indices using a weighted summation approach, an Overall Surface Condition Index (OSCI) was developed that can supremely express the overall condition of the pavement and propose a superior maintenance strategy compared to PASER and IRI. The outcome or result gained from this study could be a practical approach for road agencies to estimate the road network condition cost-effectively and make proper decisions for pavement maintenance at the network level]]></description>
      <pubDate>Mon, 04 Dec 2023 16:47:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2301589</guid>
    </item>
    <item>
      <title>Rapid Assessment of Network-Level Pavement Conditions Using Novel Tools</title>
      <link>https://trid.trb.org/View/2291289</link>
      <description><![CDATA[In this collaborative project, two leading Oklahoma universities – the University of Oklahoma (OU) and Oklahoma State University (OSU) – will work with the Texas A&M Transportation Institute (TTI) to assess network-level pavement conditions rapidly and cost-effectively, using novel tools. Roadway pavements constitute a critical element of surface transportation infrastructure. With a large portion of pavements in poor condition and reaching the end of their service lives, pavement maintenance and rehabilitation are becoming increasingly challenging tasks for many state DOTs, including DOTs in Region 6. 
Recent developments have spotlighted the Traffic Speed Deflection (TSD) Device as a valuable technology for measuring surface deflections at short intervals and capturing data on roughness, texture, and rutting at traffic speed. The evaluation of pavement conditions and their rating typically depend on such parameters as deflections, slope deflection indices, structural considerations, and remaining service life. In this context, the potential advantages of deriving network-level pavement condition ratings from TSD data could be enhanced through the implementation of other novel technologies developed by the consortium members collaborating on this project. Lack of access to a TSD device and high cost associated with data collection necessitate the pursuit of innovative in-house technologies, which will not only increase efficiency but reduce costs significantly.
As part of a pooled fund study (TPF-5 (385)) participated by ODOT, pavement conditions data from I-35 and I-40 in Oklahoma were collected recently using a TSD. The proposed study focuses on developing tools for analyzing these TSD data for network-level assessment or rating of the associated pavements. A complementary objective is to collect data from the same pavements using in-house technologies, namely Pave3D 8K available at OSU and an air-coupled Ground Penetrating Radar (GPR) and Fast Falling Weight Deflectometer (FFWD) available at TTI. 
For this purpose, with assistance of the Strategic Asset and Performance Management (SAPM) personnel at ODOT, the research team seeks to gain access to the TSD data from I-35 and I-40 and review these data closely. Leveraging different pavement condition indicators, the I-35 and I-40 pavement sections will be divided into five different categories, namely very poor, poor, fair, good, and excellent. This categorization will facilitate the subsequent selection of experimental sites for an in-depth evaluation, each spanning 3 to 5 miles. The OSU team will employ Pave3D 8K for the acquisition of 2D/3D surface images and detailed pavement roughness and texture data from the evaluation sites. The OSU team will then analyze the Pave3D 8K data and compare them with the TSD data. The results of these comparisons will assist in the establishment of definitive rating thresholds.
FFWD tests will be conducted by TTI at the selected I-35 and I-40 sections. Measured deﬂections will be used to determine structural conditions and remaining life and to compare with the corresponding TSD results. A subsurface GPR survey will be conducted on the above mentioned I-35 and I-40 sections with the help of TTI. The GPR data will be used to determine layer thicknesses and used to identify areas with subsurface defects. 
Based on the pavement conditions, cores will be extracted selectively from distressed locations as well as from some good locations. A visual observation of the extracted cores and limited laboratory test results will be used to validate the pavement rating from the TSD data and Pave3D 8K and FFWD data. The research teams from all three institutions will work together to establish pavement condition thresholds. These thresholds can be used readily by ODOT and other DOTs in Region 6. These thresholds can be adjusted in the future as more network-level data becomes available.

]]></description>
      <pubDate>Wed, 15 Nov 2023 21:46:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2291289</guid>
    </item>
    <item>
      <title>Estimation of IRI from PASER using ANN based on k-means and fuzzy c-means clustering techniques: a case study</title>
      <link>https://trid.trb.org/View/2083827</link>
      <description><![CDATA[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 Evaluation and Rating (PASER) as a rapid and cost-effective index. The IRI prediction models from PASER were developed using regression (R² = 0.66) and Artificial Neural Network (ANN) (R² = 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 (R² = 0.97) and validation (R² = 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.]]></description>
      <pubDate>Thu, 22 Dec 2022 10:08:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2083827</guid>
    </item>
    <item>
      <title>Development and evaluation of relationships between surface condition rating and objective pavement condition parameters</title>
      <link>https://trid.trb.org/View/2026373</link>
      <description><![CDATA[Highway authorities make efforts to relate visual ratings with directly measured pavement condition data to reduce or remove the necessity of manual pavement condition surveys that involve subjectivity and potential safety risk of assessors. This research develops a set of relationships between pavement surface condition rating and objective pavement condition parameters to assist road asset managers in triggering periodic bituminous resurfacing programs at the network level. These condition parameters include cracking (% area affected), rutting (mm), texture loss (% of left wheel path texture), and roughness (m/km). In the literature, deterministic and probabilistic modelling approaches are used to predict visual surface inspection rating (SIR) from directly measured pavement distresses. The Factorial ANOVA results that are typically used have inferred that cracking and rutting interact with each other significantly for the asphalt surfaced road network. However, the percentages of variation explained by the linear regression models that predict SIR from cracking/rutting are low (24–31%). Alternatively, developed ordinal logistic models for predicting the probability of a road section being in any particular surface condition, with any quantified cracking/rutting data, prove to be statistically better with overall success rates of 46% and 51% for sprayed sealed and asphalt surfaced network, respectively.]]></description>
      <pubDate>Tue, 27 Sep 2022 12:51:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/2026373</guid>
    </item>
    <item>
      <title>Investigation Into Collection Variability of Surface Crack Data for Network-Level Asphalt Pavement Evaluation</title>
      <link>https://trid.trb.org/View/1996208</link>
      <description><![CDATA[Surface cracking is a major type of pavement distress that is of interest to pavement engineers. Cracks are generally categorized in relation to patterns, orientations, and locations. Each type of crack is associated with one or more failure modes of pavements. Accurately detecting and rating surface cracks is crucial in pavement condition surveying. Currently, many State Highway Agencies employ automated survey methods to collect pavement condition data at network level. As network-level pavement evaluation is based on a single run, the traditional way of characterizing data variation based on multiple runs is no longer valid. Therefore, it is necessary to introduce a new method to evaluate the variability of pavement condition data at the network level. In this study, the variability of network-level surface crack data was evaluated by means of network-level sample parallel tests. The parallel test was conducted from 2018 to 2020 using two vehicles equipped with identical automated survey systems which consisted of a 3-D imaging system and automated distress identification system. A matrix-based method was proposed to evaluate the variations of crack data obtained from two testing vehicles. Crack data investigated in this study included fatigue cracks, longitudinal wheel-path and non-wheel-path cracks, and transverse cracks. Results indicated that change of testing speed could potentially influence the variation of automated crack data. The variations between severity levels for fatigue cracking were higher than other types of cracks. The variation of crack data decreased with the increase of reporting intervals.]]></description>
      <pubDate>Mon, 18 Jul 2022 16:47:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/1996208</guid>
    </item>
    <item>
      <title>Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning</title>
      <link>https://trid.trb.org/View/1852292</link>
      <description><![CDATA[This paper presents the research results of using Google Earth imagery for visual condition surveying of highway pavement in the United States. A screenshot tool is developed to automatically track the highway for collecting end-to-end images and Global Position System (GPS). A highway segmentation tool based on a deep convolutional neural network (DCNN) is developed to segment the collected highway images into the predefined object categories, where the cracks are identified and labeled in each small patch of the overlapping assembled label-image prediction. Then, the longitudinal cracks and transverse cracks are detected using the x-gradient and y-gradient from the Sobel operator, and the developed pavement evaluation tool rates the longitudinal cracking in 0.3048  m/30.48  m-Station (linear feet per 100 ft. station) and transverse cracking in number per 30.48  m-Station (100 ft. station), which can be visualized in ArcGIS Online. Experiments were conducted on Interstate 43 (I-43) in Milwaukee County with pavement in both defective and sound visual conditions. Experimental results showed the patch-wise highway segmentation in Google Earth imagery from the 16×16-pixel DCNN model has as precise pixel accuracy as the U-net-based pixelwise crack/noncrack classifier. Compared to the manually crafted label image in the experimental area, the rated longitudinal cracking has an average error of overrating 20%, while transverse cracking has an average error of underrating 7%. This research project contributes to visual pavement condition surveying methodology with the free-to-access Google Earth imagery, which is a feasible, cost-effective option for accurately rating and geographically visualizing both project-level and network-level pavement.]]></description>
      <pubDate>Thu, 24 Jun 2021 16:40:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/1852292</guid>
    </item>
    <item>
      <title>Development of a Probabilistic Pavement Performance Prediction Model</title>
      <link>https://trid.trb.org/View/1759359</link>
      <description><![CDATA[With increasing demands on existing transportation infrastructure, agencies face a growing challenge to cost-effectively rehabilitate and preserve the integrity and reliability of their transportation systems. The need to effectively manage transportation infrastructure investments has led to a recognition of the benefits of a data-driven systematic approach. Regarding pavement infrastructure, this methodical and data-driven approach includes the periodic network-level assessment of pavement condition, performance prediction models, maintenance and rehabilitation thresholds, and a decision-support tool to make data-driven and cost-effective management decisions such as appropriate funding needs determination and less subjective prioritized listings of pavement segments for programming maintenance, rehabilitation and resurfacing. As with any data-driven approach, regular review and improvement in each step of the methodology is required to keep pace with evolving needs, knowledge, and challenges. This paper documents the development and validation of a probability-based performance prediction model for use as part of a pavement management system. The model considers historical performance data and uses the current pavement condition rating of a pavement network to determine the number of lane miles that will require rehabilitation over a 5-year period. This methodology is intuitive and can be easily adopted by highway agencies.]]></description>
      <pubDate>Thu, 04 Feb 2021 10:57:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/1759359</guid>
    </item>
    <item>
      <title>Evaluation of Network-Level Data Collection Variability and its Influence on Pavement Evaluation Utilizing Random Forest Method</title>
      <link>https://trid.trb.org/View/1764029</link>
      <description><![CDATA[The use of pavement condition data to support maintenance and resurfacing strategies and justify budget needs becomes more crucial as more data-driven approaches are being used by the state highway agencies (SHAs). Therefore, it is important to understand and thus evaluate the influence of data variability on pavement management activities. However, owing to a huge amount of data collected annually, it is a challenge for SHAs to evaluate the influence of data collection variability on network-level pavement evaluation. In this paper, network-level parallel tests were employed to evaluate data collection variability. Based on the data sets from the parallel tests, classification models were constructed to identify the segments that were subject to inconsistent rating resulting from data collection variability. These models were then used to evaluate the influence of data variability on pavement evaluation. The results indicated that the variability of longitudinal cracks was influenced by longitudinal lane joints, lateral wandering, and lane measurement zones. The influence of data variability on condition evaluation for state routes was more significant than that for interstates. However, high variability of individual metrics may not necessarily lead to high variability of combined metrics.]]></description>
      <pubDate>Sun, 24 Jan 2021 17:25:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/1764029</guid>
    </item>
  </channel>
</rss>