<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>Machine learning for predicting pavement roughness and optimising maintenance</title>
      <link>https://trid.trb.org/View/2617999</link>
      <description><![CDATA[This study examines four machine learning algorithms for predicting short-term and long-term International Roughness Index (IRI) changes in pavement performance. Using over 2,700 samples from the Long-Term Pavement Performance database, models are developed to forecast IRI changes under various maintenance scenarios. The approach accounts for immediate IRI changes caused by treatments and includes separate models for predicting weather and traffic variables. Random Forest models demonstrated the best performance, achieving R² values of 80–96% for long-term IRI changes and 85–92% for short-term changes across different maintenance strategies. Subsequently, Support Vector Machine (SVM) models with radial, linear, and polynomial kernels presented R² values as high as 70–84%, 60–92%, and 60–83%, respectively. The methodology enables accurate prediction of pavement roughness, facilitating treatment prioritisation and offering time and cost savings in data collection. It provides a comprehensive schedule for treatment execution, including types, timing, locations, and costs, thereby enhancing pavement management efficiency.]]></description>
      <pubDate>Mon, 09 Feb 2026 13:55:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2617999</guid>
    </item>
    <item>
      <title>Long-Term Pavement Performance FY 2010 to FY 2015</title>
      <link>https://trid.trb.org/View/2635956</link>
      <description><![CDATA[This document summarizes the current status of the Long-Term Pavement Performance (LTPP) program and its major activities (data collection, data storage, data analysis, and product development), describes the work that will be needed beyond 2009 to capitalize on the investment that has been made in developing the world’s most comprehensive pavement research database, presents a framework for completing activities after 2009 and the associated budget, discusses why these activities are necessary and what will be gained when the post-2009 work is completed, and provides recommendations aimed at preserving the LTPP program’s legacy and realizing its full potential.]]></description>
      <pubDate>Mon, 26 Jan 2026 17:40:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2635956</guid>
    </item>
    <item>
      <title>Quantification of Post-Rainfall Moisture Content in Pavement Unbound Layers Using Long-Term Pavement Performance Data</title>
      <link>https://trid.trb.org/View/2625444</link>
      <description><![CDATA[For developing a pavement resilience framework, it is critical to understand and predict the moisture content variation of the unbound layers, which significantly affects pavement response and performance. Utilizing data from the Long-Term Pavement Performance (LTPP) program, two models were developed and compared: a linear regression model and a random forest model. The linear regression model explained 59.5% of moisture content variation, identifying key factors such as maximum single-day precipitation, time since maximum rainfall, and depth of the water table, as well as surface and unbound layers’ material types. The random forest model demonstrated superior performance, explaining 92.3% of moisture content variation. A case study for a LTPP section in Texas demonstrated the models’ ability to simulate moisture distribution over time and depth after a significant rainfall event, providing insights into the drainage behavior of different pavement layers and subgrade materials. The case study also demonstrated the random forest model’s capability to capture different moisture behaviors after precipitation, which the linear model fails to account for. While detailed trends in subterranean layers’ moisture content level can be site-specific, coarser materials tend to handle the excessive water from rainfall better than finer ones, as they experience a shorter duration with elevated moisture concentration. While this was expected, the model allows this aspect to be quantified.]]></description>
      <pubDate>Sat, 15 Nov 2025 18:14:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625444</guid>
    </item>
    <item>
      <title>Improving the Long-Term Condition of Pavements in Massachusetts and Determining Return on Investment: Implementing the AASHTO Mechanistic-Empirical Pavement Design Guide - PHASE III</title>
      <link>https://trid.trb.org/View/2602549</link>
      <description><![CDATA[The Massachusetts Department of Transportation (MassDOT) has sponsored multiple projects to implement the Mechanistic-Empirical Pavement Design Guide (MEPDG). Due to the complexity of this research, a four-phase approach spanning several years was proposed. This report focuses on Phase 3. In Phase 3, MassDOT concentrated on using the Long-Term Pavement Performance (LTPP) test pavements in Massachusetts and neighboring states. The LTPP projects provided readily available data on traffic, climate, subgrade, materials, structure, and performance. The objective was to verify the global flexible pavement calibration coefficients using LTPP test sections for predicting distresses and smoothness, and to locally/regionally calibrate the flexible pavement transfer functions (rutting, transverse cracking, fatigue cracking, reflection cracking, and smoothness) if necessary. This report presents the 2024 regional calibration coefficients determined by distress type for new flexible pavements and asphalt overlays, along with a comparison to the global calibration coefficients of version 3 of the Pavement Mechanistic Empirical Design (PMED) software. It is recommended that MassDOT use these regional calibration coefficients for designing and evaluating flexible pavements, as they reflect the performance of flexible pavements and asphalt overlays in Massachusetts. Additionally, the default laboratory coefficients for dense-graded asphalt mixtures are suggested for predicting fatigue, thermal, and reflective cracking in Massachusetts until more comprehensive laboratory mixture test data can be collected. A future phase of this study, Phase 4, will address this shortcoming by incorporating additional roadway segments in Massachusetts and conducting laboratory tests on the asphalt mixtures used in these segments.]]></description>
      <pubDate>Tue, 30 Sep 2025 16:46:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2602549</guid>
    </item>
    <item>
      <title>Assessment of Present Pavement Condition Using Machine Learning Techniques</title>
      <link>https://trid.trb.org/View/2407401</link>
      <description><![CDATA[Quantification of present pavement condition in terms of an index term i.e., Pavement Condition Index (PCI) is one of the most important and primary steps while taking decision related to Maintenance and Rehabilitation of Pavements. PCI as proposed by ASTM D6433 rates pavement in seven conditions viz. Good, Satisfactory, Fair, Poor, Very Poor, Serious and Failed. Determination of rating condition of pavement using distress severity and extent turns out to be tedious process. Hence, present study investigates application machine learning techniques for assessment of present pavement condition. Three different algorithms i.e., Logistic Regression, Naïve Bayes and K-Nearest Neighbor have been tested in the present study using Long Term Pavement Performance database consisting of over 10,000 datapoints. The dataset was divided into 7:3 ratio for training and testing phase. Employed algorithms were tested based on accuracy, precision, recall and f-measure. Logistic Regression Classifier was found to have highest accuracy of 0.92 among three classifiers used in the study.]]></description>
      <pubDate>Mon, 22 Sep 2025 17:13:23 GMT</pubDate>
      <guid>https://trid.trb.org/View/2407401</guid>
    </item>
    <item>
      <title>Evaluation of Flexible Pavement Performance Based on Genetic Neural Network</title>
      <link>https://trid.trb.org/View/2551078</link>
      <description><![CDATA[The distress condition, skid resistance, and structural performance of flexible pavements exhibit simultaneous and interrelated deterioration. This study aimed to evaluate the three aspects of performance quantified by indices as the pavement surface condition index (PCI), skid resistance index (SRI), and structure strength index (PSSI), respectively, using cracking indices that can be rapidly obtained due to advanced cracking detection technologies. Considering the effect of structural design and traffic and climatic conditions, 29 structural, traffic, and climatic indices were selected as well and subsequently reduced to 12 principle components using principal component analysis, which retained more than 80% of the original information. To evaluate the PCI, SRI, and PSSI of flexible pavements, genetic neural networks (GNNs) with inputs of cracking indices and structural, traffic, and climatic principal components were developed by employing genetic algorithms to optimize the hyperparameters of artificial neural networks (ANNs). The GNNs were trained using the data of 287 flexible pavement sections from the Long-Term Pavement Performance program. Results indicate that ANNs using only cracking indices as inputs are of low accuracy, and introducing structural, traffic, and climatic indices into inputs can increase the accuracy of ANNs. Furthermore, replacing these condition indices with their corresponding principal components as inputs reduces the iterations of training ANNs by 63.9%, 45.5%, and 32.8% for flexible pavements with semirigid, granular, and asphalt-bound base layers, respectively, while the decrease in accuracy of ANNs is less than 0.5%. The training efficiency of GNNs is up to 773.8% higher than ANNs. The evaluation accuracy of GNNs for PCI, SRI, and PSSI ranges from 0.944 to 0.954, 0.899 to 0.918, and 0.895 to 0.906, due to various flexible pavement types, which is 0.2% to 4.9% higher than ANNs. This approach can assist in simultaneously evaluating the distress condition, skid resistance, and structural performance of flexible pavements using conveniently detected cracking data, thereby reducing detection cost.]]></description>
      <pubDate>Mon, 16 Jun 2025 09:17:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2551078</guid>
    </item>
    <item>
      <title>Advanced Hybrid CNN-GRU Model for IRI Prediction in Flexible Asphalt Pavements</title>
      <link>https://trid.trb.org/View/2505736</link>
      <description><![CDATA[The international roughness index (IRI) is an important parameter for road surface roughness assessment, which is crucial for road safety. This study developed a road roughness prediction model for predicting the IRI of asphalt pavement with deep learning technology. A gate recurrent unit (GRU) and convolutional neural network (CNN) model are integrated, forming a novel hybrid CNN-GRU model for the IRI prediction. The Long-Term Pavement Performance (LTPP) database is adopted to acquire pavement data considering various variables, such as road age, traffic load, pavement performance, and climate condition. The correlation coefficients between these variables were analyzed and generated. The database consisted of 4,782 observations from 975 road sections in the LTPP program. From the data set, 80% of the data were randomly sampled for training the hybrid CNN-GRU model and the other 20% were used for testing. The coefficient of determination R² for training and testing can reach 0.903 and 0.893, respectively. Compared with the random forest model, the R² of the CNN-GRU model are 0.108 and 0.130 larger for the training set and the testing set, an increase of 13.58% and 17.04%, respectively. Moreover, the Shapley additive explanations (SHAP) method was employed to assess the significance of variables, revealing that the initial IRI holds the most substantial influence on prediction outcomes. Rutting and transverse cracking also exhibit a considerable impact. The effect of climate parameters on IRI prediction was also investigated. When not considering climate parameters, the R² for the training set and testing set are 0.893 and 0.886, respectively, which is lower than the results when considering climate parameters. The results indicate that the climatic parameters indeed play a vital role in the prediction model.]]></description>
      <pubDate>Tue, 25 Mar 2025 16:57:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2505736</guid>
    </item>
    <item>
      <title>Development of superpave asphalt binder specifications to meet climate conditions in the UAE</title>
      <link>https://trid.trb.org/View/2487639</link>
      <description><![CDATA[Asphalt binder's performance is highly sensitive to temperature fluctuations and climatic conditions. The selection of an inappropriate asphalt binder leads to considerable damage and impacts roads' longevity. The current selection practice of asphalt binder in the United Arab Emirates (UAE) is mainly according to the penetration grading system, which does not consider local temperature conditions. The Superpave Performance Grade (PG) system considers extreme pavement temperatures to define appropriate asphalt binder PG. This study aimed at developing the Superpave asphalt binder PG map for the UAE. The Strategic Highway Research Program (SHRP) and Long-Term Pavement Performance Program (LTPP) Superpave models were used to calculate the pavement temperatures employing air temperature records collected from 20 weather stations across the UAE. The result of the Superpave PG map highlights three distinct asphalt binder grades at 98% reliability: PG 76-10, PG 70-10, and PG 64-10. The PG 76-10 asphalt binder is the most prevalent PG, covering more than 85% of the UAE map. However, the current construction practice utilizes penetration grades 40/50 and 60/70, though both asphalt binders are equivalent to PG 64-xx. This necessitates the use of different modifier technologies to achieve the Superpave requirements of PG 76-10 and PG 70-10.]]></description>
      <pubDate>Sat, 08 Feb 2025 16:48:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2487639</guid>
    </item>
    <item>
      <title>LTPP Data Analysis: Improving Use of FWD and Longitudinal Profile Measurements</title>
      <link>https://trid.trb.org/View/2446973</link>
      <description><![CDATA[This report presents the development of an approach to adjust falling weight deflectometer measurements to account for changes in temporal and diurnal temperature and moisture conditions for asphalt pavements and to evaluate longitudinal profile measurements to account for curl and warp of jointed plain concrete pavements. The approaches were based on the data contained within the Long-Term Pavement Performance (LTPP), Seasonal Monitoring Program (SMP). The effort included describing the effects of climate on pavement properties and performance, assessing and extracting the needed SMP data from the LTPP database, evaluating climate conditions, developing approaches for the analysis and adjustment of falling weight deflectometer (FWD) deflections and longitudinal profile according to temporal and diurnal changes in temperature and moisture conditions, and preparing guidelines to improve the use of FWD and longitudinal profile measurements.]]></description>
      <pubDate>Sat, 02 Nov 2024 16:43:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2446973</guid>
    </item>
    <item>
      <title>Imporved [sic] model for pavement performance prediction based on recurrent neural network using LTPP database</title>
      <link>https://trid.trb.org/View/2426574</link>
      <description><![CDATA[Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments, enabling the achievement of better pavement performance with limited financial resources. However, due to the intricate influence of numerous factors on pavement performance deterioration, improving the accuracy of pavement performance prediction poses a challenge for conventional models. Therefore, the aim of this study is to establish a machine learning-based model pavement performance prediction model. First, this study considers five factors that affect pavement performance, including pavement initial performance indicators, traffic loads, weather, pavement structure, and maintenance measures, and identifies 15 specific indicators that affect pavement performance based on these five factors. Then, based on the Long-Term Pavement Performance (LTPP) database, the study screens and summarizes these indicators, obtaining 2464 high-quality pavement performance data for Pavement Conditions Index (PCI) prediction and 3238 high-quality pavement performance data for IRI prediction. Finally, three distinct prediction models are established, namely, the Fully Connected Neural Network (FCNN) model, the Long Short-Term Memory (LSTM) model, and the combined LSTM-Attention model. The study shows that the LSTM-Attention model performs significantly better than the FCNN and LSTM models, with an R² coefficient of determination of 0.81 for PCI and 0.79 for IRI. The innovation of this paper is that the authors have introduced the Attention mechanism on the basic of LSTM model, which makes the fitting accuracy of the prediction model further improved.]]></description>
      <pubDate>Mon, 07 Oct 2024 16:55:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2426574</guid>
    </item>
    <item>
      <title>Local Verification of AASHTOWareTM Pavement ME Design for Flexible Pavement</title>
      <link>https://trid.trb.org/View/2427602</link>
      <description><![CDATA[This research project conducted a local verification to assess the accuracy of globally calibrated Pavement ME Design distress and smoothness models for asphalt pavements in Alabama. Pavement sections included LTPP test sections in Alabama and neighboring states, as well as sections tested at the NCAT Test Track. Results showed significant bias in the rutting prediction model for both LTPP and NCAT Test Track sections. The PMED software underpredicted fatigue cracking percentages for general LTPP pavement sections while overpredicting fatigue cracking percentages for NCAT Test Track pavement sections. The IRI prediction model also exhibited significant bias, indicating higher predicted values than measured values. Based on the findings, local calibration of the PMED performance models is essential for accurate predictions under Alabama conditions. Other implementation activities may include validation with independent datasets and training on Pavement ME Design. This project highlights the importance of local verification and calibration to improve prediction accuracy, ensuring more reliable and cost-effective pavement structures.]]></description>
      <pubDate>Fri, 13 Sep 2024 10:33:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2427602</guid>
    </item>
    <item>
      <title>Comparison of Flexible Pavement Designs: Mechanistic-Empirical (NCHRP1-37A) Versus Empirical (AASHTO 1993) Flexible Pavement Design Using Available Local Calibration Models</title>
      <link>https://trid.trb.org/View/2366826</link>
      <description><![CDATA[This paper focuses on conducting a comparative study between mechanistic empirical (NCHRP1-37A) design method and empirical 1993 AASHTO design method. The flexible pavement sections selected for the study are from different regions in the United States with varying climatic conditions. The typical data required for defining and characterizing the pavement structure were gathered from FHWA's Long-Term Pavement Performance (LTPP) program. The pavement sections are initially designed using 1993 AASHTO design method at various conditions including different traffic levels, percentage of overloaded vehicles, and environmental conditions. Both default and available local calibration models for the selected regions are used to predict the performance of flexible pavement by mechanistic empirical pavement design guide (MEPDG) software. The results reveal that despite selecting the same serviceability loss in designing flexible pavement using 1993 AASHTO empirical method, the obtained results showed a noticeable variation in the predicted pavement performance while analyzing these sections using MEPDG design approach. The computed performance of AASHTO designed pavements using local and default calibration models are significantly different. Furthermore, as the percentage of overloaded trucks increases, pavement distresses computed at the end of the service life exceed the permissible distress limit in most cases. For pavements located in regions with higher average temperatures, the pavement performance exhibits the least total rutting performance. Finally, the worst pavement performance for alligator cracking distresses is observed for pavement sections designed with a strong subgrade for moderate and high traffic volume in warm climates.]]></description>
      <pubDate>Fri, 10 May 2024 16:50:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2366826</guid>
    </item>
    <item>
      <title>Study on Development Law of Rutting Based on Long-Term Detecting Data</title>
      <link>https://trid.trb.org/View/2237778</link>
      <description><![CDATA[This study aims at investigating the long-term development law of asphalt pavement rutting. The data of typical cross-sections were extracted and optimized from Long-Term Pavement Performance (LTPP) database. Rutting depth, filling area, positive area, and negative area were adopted as indicators to evaluate pavement rutting. Then the changing trend of rutting was further analyzed under different temperatures and loading conditions, thus determining the development law of rutting with the increase of pavement service life. It was found that most rutted cross-sections gradually became type Ⅲ and type Ⅳ cross-sections after long-term changes. The development trends of rutting depth were consistent with the filling area, which showed several phases, including rapid development period and relatively stable period. The segments with increasing rate of rutting depth greater than 1.5 mm/year and increasing rate of filling area up to 1,200 mm2/year were in rapid development period, in which appropriate preventive maintenance needs to be taken.]]></description>
      <pubDate>Wed, 31 Jan 2024 16:01:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2237778</guid>
    </item>
    <item>
      <title>Analyses of Frost Susceptible Flexible Pavement Adaption for Climate Change</title>
      <link>https://trid.trb.org/View/2216513</link>
      <description><![CDATA[Climate change has major implications on the durability and performance of a pavement. The smoothness of pavement in freeze climate zone is affected by seasonal frost heave and thaw weakening, which are subjected to the effects of climate change. This paper proposed a new empirical International Roughness Index (IRI) model, which captures seasonal environmental influence on road sections. The model was nationally calibrated for flexible pavements deal with seasonal freezing/thawing via data from the Long-Term Pavement Performance (LTTP). The calibrated new model is suitable for analyzing the climatic impacts of frost action to flexible pavement. The future climate conditions are predicted based on different climate scenarios. The new IRI model is combined with the climate forecast to analyze the effects of climate change on the pavement. Case studies for three sites at different climatic regions were conducted, from which the regional climate adaptation is suggested. The analyses provide guidance on planning and adaptation for flexible pavement with respect to climate change.]]></description>
      <pubDate>Tue, 19 Dec 2023 09:14:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2216513</guid>
    </item>
    <item>
      <title>Factors Influencing the Design of Semirigid Pavement in Different Climatic Regions Using LTPP Data, MEPDG Software, and the Design of the Experiment Method</title>
      <link>https://trid.trb.org/View/2278452</link>
      <description><![CDATA[Semirigid pavements are gaining importance in the pavement design field due to their improved performance in freezing zones. These semirigid pavements are constructed similarly to asphalt pavements, but with a cement-stabilized base layer. However, there is a limited study that quantifies the influence of design factors on the performance of semirigid pavements. Therefore, an attempt was made to investigate the role of subgrade, temperature, moisture, traffic, crack joint spacing, speed, asphalt thickness, cement-treated base (CTB) layer thickness, elastic modulus, and modulus of rupture of CTB layer on semirigid pavement design. Different combinations of factors were formulated using fractional factorial design in the design of the experiment (DoE). All factors influencing the design of semirigid pavements were considered on two levels (low and high). This analysis used data from the Federal Highway Administration’s (FHWA’s) Long-Term Pavement Performance Program (LTPP). These data were incorporated into the AASHTOWare Pavement ME Design 2.6.1 (MEPDG) software. Design-Expert was used to determine the significance of various factors on the performance indexes. In addition, an optimization technique was used to determine the optimal design thickness for cement-treated base under various subgrade and climatic conditions. The result suggests that the thickness of a CTB layer is greater on fine-grained soil than on coarse-grained soil.]]></description>
      <pubDate>Wed, 22 Nov 2023 12:47:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2278452</guid>
    </item>
  </channel>
</rss>