<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>Analyzing environment-transport relationships in metropolitan areas: A vulnerability-based geographic framework and prediction model</title>
      <link>https://trid.trb.org/View/2686287</link>
      <description><![CDATA[Urban transportation planners manage prediction systems across hundreds of sensors in environmentally heterogeneous metropolitan regions, yet prediction reliability systematically degrades by 15%–28% in complex areas—precisely where accurate forecasting proves most critical. Traditional methods treat all urban areas uniformly, forcing planners into an impossible choice: accept degraded accuracy in complex environments, or develop location-specific models requiring prohibitive computational resources that cannot scale. To address this vulnerability-performance gap, we introduce UEA-MOE (Urban Environmental Adaptation Mixture-of-Experts), an interpretable framework employing vulnerability-guided adaptive prediction. Variational Autoencoders (VAE) quantify environmental heterogeneity into a continuous Urban Environmental Vulnerability Index (UEVI) from multi-source geographic data, which then guides a mixture-of-experts architecture to dynamically adapt analytical strategies based on local environmental complexity. UEA-MOE’s effectiveness stems from three synergistic innovations: (1) interpretable vulnerability quantification validated through SHAP analysis revealing region-specific drivers, (2) morphology-aware mechanisms demonstrating how corridor-concentrated versus polycentric urban structures create fundamentally different vulnerability patterns requiring differentiated strategies, and (3) computational efficiency achieving Pareto-optimal performance. Comprehensive evaluation across 532 traffic sensors in California metropolitan regions demonstrates that vulnerability-aware prediction achieves 17.4–37.7% improvements over graph-based baselines (p<0.001) while reducing computational time by 6.4×. Vulnerability mapping reveals actionable insights: monocentric cities require corridor-focused interventions, while polycentric regions demand distributed strategies. This work establishes a paradigm shift from spatially-uniform to vulnerability-aware forecasting, demonstrating how interpretable AI quantifying environment-performance mechanisms can simultaneously enhance prediction accuracy and explain why certain urban configurations challenge forecasting systems.]]></description>
      <pubDate>Mon, 27 Apr 2026 14:58:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2686287</guid>
    </item>
    <item>
      <title>Measuring Risk of Residential Displacement Around LA Metro's New Light-Rail Stations</title>
      <link>https://trid.trb.org/View/2616201</link>
      <description><![CDATA[If development is to be equitable, policy-makers will need to enact robust policies to ensure that low-income and other vulnerable populations are not displaced and cast aside in the name of progress. The purpose of this study is to assess the risk of displacement around LA Metro's 20 new light rail stations. The goal is to create a method capable of identifying and scoring a community's risk of housing displacement near new public transit stations. This analysis combines elements from prior studies on gentrification around transit stations to identify housing and socioeconomic indicators thought to explain high residential turnover and associated increases in housing costs. The method of analysis is strongly influenced by a 2013 vulnerability index model created by Lisa Bates, a Planning Professor of Portland State University, to assess risk of displacement in Portland. Her analysis identified areas with high concentrations of marginalized populations overlaid with areas experiencing high growth in housing costs. The metrics behind the ranking system outlined in Bates' report have been modified to account for Los Angeles' diverse population and large rental market, substituting many of Bates' displacement indicators with indicators previous research has shown to be associated with displacement in Los Angeles County.]]></description>
      <pubDate>Sat, 20 Dec 2025 17:26:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/2616201</guid>
    </item>
    <item>
      <title>LA Metro Bike Share Program User &amp; Non-User Perceptions: A Survey &amp; Statistical Analysis</title>
      <link>https://trid.trb.org/View/2613655</link>
      <description><![CDATA[LA Metro launched the Downtown Los Angeles (DTLA) pilot of their Metro Bike Share system on July 7, 2016. The downtown launch of the regional bike share system consisted of about 1,000 shared bicycles and 65 stations. This research presents findings from a set of surveys implemented approximately six months after the program launch date. The surveys were conducted to better understand: Perceptions of Metro Bike Share, Metro Bike Share user demographics, and Barriers to bike share use. Surveys were distributed via online and in-person methods, and 1,631 responses were gathered over a five-week period (from January 14, 2017 to March 3, 2017).]]></description>
      <pubDate>Sat, 13 Dec 2025 17:00:39 GMT</pubDate>
      <guid>https://trid.trb.org/View/2613655</guid>
    </item>
    <item>
      <title>Free transit for students to regain ridership: Users and boarding characteristics of LA Metro's GoPass program</title>
      <link>https://trid.trb.org/View/2611343</link>
      <description><![CDATA[The Los Angeles County Metropolitan Transportation Authority (LA Metro) started in October 2021 the largest free transit pass program in the U.S. to date. Known as GoPass, it serves students from kindergarten to community colleges in Los Angeles County, the most populated county in the U.S. Although many free transit pass programs have been created, few have been analyzed from the point of view of transit agencies (i.e., for the characteristics of their users and their impact on ridership). To address this gap, we first examine GoPass' contribution to LA Metro's bus boardings, before comparing selected characteristics of the students enrolled in GoPass in 2023 with census data. We find some opportunities for additional growth, including for female students. To understand GoPass usage, we estimated a generalized spatial regression model that explains annual GoPass boardings aggregated by census tract (detailed usage data are unavailable to protect the students' privacy) using a broad range of socioeconomic and built environment variables. Our results confirm the presence of strong spatial effects. We find that census tracts with more young males, more transit stops, mixed land use, and more participating schools accessible within 30 min by transit have more GoPass boardings. Conversely, the number of GoPass boardings decreases with more access to private vehicles, property crimes, multifamily units, and a higher population density. A better understanding of the characteristics of GoPass users and GoPass usage is useful to improve GoPass and to inform transit agencies interested in creating similar programs.]]></description>
      <pubDate>Tue, 18 Nov 2025 09:30:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2611343</guid>
    </item>
    <item>
      <title>Addressing Mobility-Related Challenges for AAPI Older Adults</title>
      <link>https://trid.trb.org/View/2550452</link>
      <description><![CDATA[This project will use qualitative and quantitative research methods to better understand mobility-related challenges for Asian Americans and Pacific Islanders (AAPI) older adults in order to provide government agencies and organizations such as National Asian Pacific Center on Aging (NAPCA) with recommendations for policy and program changes to pursue. Older adults are typically defined as people aged 55 or older. Programs and policies aimed at encouraging and keeping people healthy, independent, and mobile as they age are based on research and real-life experiences. While the real-life experiences of each person differ, the aging process affects hearing, eyesight, reaction times, balance, and overall ability to engage with and be mobile in their environment. Mobility is typically dependent on transportation options available, including walking, public transportation, various motor vehicles, and cycling. Each option comes with a set of 'providers' including oneself (in the case of walking), family members, public agencies, and private providers. One of the goals of ensuring an older adult continues to have transportation options and mobility is to maintain their life-space mobility, the ability of an older adult to navigate within their community for daily needs. Many factors, such as the built environment and transportation options available and accessible, affect an older adult's life-space mobility. Further, race, ethnicity, economic status, locale, and family composition affect a person's mobility. A few life-space mobility studies go beyond the typical assessment of an older adult's physical ability, determining how the built environment affects mobility, and even suggest transportation policies for older adults. While some AAPI older adults may be included in the research, there is a lack of studies specifically focusing on older AAPI adults, especially factoring in the added safety risk related to Asian hate, which creates additional barriers to transportation and mobility. AAPIs have been the fastest-growing ethnic group in California since 2000, accounting for a significant portion of the state's labor force. Nationwide, the AAPI community will increase to 11 percent of people 65 years and older in the United States by 2050. The transportation and mobility of older AAPI adults is hindered by a range of challenges. These include, but are not limited to, issues such as limited access to private vehicles and public transit, traffic safety and public security concerns, the impact of the Covid-19 pandemic, as well as language, cultural, and technology barriers.

Since transportation and mobility can be limited for older adults, this project will focus on those 55 and older, recognizing the need to identify subgroups of older adults for whom the difference may be significant. The research will study transportation and mobility for AAPI older adults in the Greater Los Angeles Metropolitan Area in California. The research will fill an existing gap within the academic community on the travel behavior of AAPI older adults. The project will include a literature review and a survey with selected follow-up interviews to develop a report with recommendations for government agencies and organizations such as NAPCA to address the transportation and mobility needs of older AAPI people. The project will develop a survey to gain much-needed details on the daily experiences of AAPI older adults in Southern California. Survey research is a well-respected and much-used method to reach many people, especially when offered online effectively. We plan to use a mixed-methods approach, i.e., obtain both quantitative and qualitative information from respondents. The team will carefully design the survey to be understandable in multiple languages and reduce the likelihood of bias. 
]]></description>
      <pubDate>Tue, 06 May 2025 16:20:44 GMT</pubDate>
      <guid>https://trid.trb.org/View/2550452</guid>
    </item>
    <item>
      <title>Quantifying Emissions of Natural Gas Storage Tanks in the Greater Los Angeles Metropolitan Area</title>
      <link>https://trid.trb.org/View/2499016</link>
      <description><![CDATA[Natural gas provides an alternative to petroleum-based fuels as an energy source that is being more widely adopted across multiple sectors in California. The viability of natural gas depends on its total life cycle emissions, specifically of those of methane. This paper addresses the possibility of and reason for fugitive emissions of methane from the transportation sector by surveying and quantifying methane plumes from compressed natural gas (CNG) and liquified natural gas (LNG) storage tanks at vehicle fueling facilities in the greater Los Angeles metropolitan area. This project used methane plume images provided by airborne imaging spectroscopy, collected by NASA’s Airborne Visible/InfraRed Imaging Spectrometer-Next Generation (AVIRIS-NG) mission, to identify large methane point sources originating from CNG and LNG infrastructure. The periodic methane plume observations were converted into emission rates to provide an estimate for potential methane emissions from NG storage facilities across California. For the population of facilities that were analyzed, four had natural gas storage tanks with emission rates that are higher than the maximum rate specified by the tank manufacturers. The significant disparity between the expected emission rate and the actual emission rate can be explained by tank malfunction, as the number of observed plume events are far higher than what would be expected for a fully operational tank. If the tank malfunction rates found in the group that was analyzed were applied to the entire population of California CNG and LNG facilities, total emissions may be up to 1300 kg CH₄ per hour, suggesting a need for leak monitoring and repair to prevent excessive methane emissions from this sector.]]></description>
      <pubDate>Mon, 10 Feb 2025 09:32:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2499016</guid>
    </item>
    <item>
      <title>Investigating the Impacts of Smart Charging on Electric Vehicle
Charging Choices Within an Activity-based Framework
</title>
      <link>https://trid.trb.org/View/2420065</link>
      <description><![CDATA[The objective of this project is to forecast the impacts of spatio-temporal electricity pricing
on electric vehicle (EV) charging behavior, drawing on established EV charging models and
incorporating considerations such as smart charging acceptance and joint charging-activity
time planning decisions. The research team aims to elucidate how current and future electricity rates may
influence EV driver behavior, while accounting for heterogeneity in charging preferences and
value of travel time. Using the Los Angeles metropolitan area as a case study, the team develops future
year scenarios for EV adoption and charging infrastructure access to evaluate the effects of pricing
strategies on the demand for public infrastructure and EV-related trips. The analysis encompasses
a range of smart charging policies, including spatially and temporally-varying electricity prices linked
to factors such as charging speeds, utility control, location, and enrollment in bill assistance
programs. Results, segmented by travel characteristics such as household income, home charger
access, and EV range will quantify the impact of EV charging prices on both aggregate and
disaggregate network metrics (e.g., vehicle miles traveled and charging cost savings, respectively.)
The results provide insights into the broader implications of electricity pricing strategies for EV
integration within the transportation network. The findings of this project are expected to contribute
to a deeper understanding of EV charging behavior and access and inform the development of
effective demand management strategies within the evolving landscape of transportation
electrification.]]></description>
      <pubDate>Thu, 22 Aug 2024 16:10:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2420065</guid>
    </item>
    <item>
      <title>Joint planning of charging stations and power systems for heavy-duty drayage trucks</title>
      <link>https://trid.trb.org/View/2408518</link>
      <description><![CDATA[As global concerns about climate change intensify, the transition towards zero-emission freight is becoming increasingly vital. Drayage is an important segment of the freight system, typically involving the transport of goods from seaports or intermodal terminals to nearby warehouses. This sector significantly contributes to not only greenhouse gas emissions, but also pollution in densely populated areas. This study presents a holistic optimization model designed for an efficient transition to zero-emission drayage, offering cost-effective strategies for the coordinated investment planning for power systems, charging infrastructure, and electric drayage trucks. The model is validated in the Greater Los Angeles area, where regulatory goals are among the most ambitious. Furthermore, the model’s design allows for easy adaptation to other regions. By focusing on drayage trucks, this study also paves the way for future research into other freight categories, establishing a foundation for a more extensive exploration in this field.]]></description>
      <pubDate>Mon, 05 Aug 2024 13:53:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2408518</guid>
    </item>
    <item>
      <title>Peaked too soon? Analyzing the shifting patterns of PM peak period travel in Southern California</title>
      <link>https://trid.trb.org/View/2362205</link>
      <description><![CDATA[Daily vehicle travel collapsed with the onset of the COVID-19 pandemic in early 2020 but largely bounced back by late 2021. The pandemic caused dramatic changes to working, schooling, shopping, and leisure activities, and to the travel associated with them. Several of these changes have so far proven enduring. So, while overall vehicle travel had largely returned to pre-pandemic levels by late 2021, the underlying drivers of this travel have likely changed.To examine one element of this issue, the authors analyzed whether patterns of daily trip-making shifted temporally between the fall of 2019 and 2021 in the Greater Los Angeles megaregion. They used location-based service data to examine vehicle trip originations for each hour of the day at the U.S. census block group level in October 2019 and October 2021. The authors observed notable shifts in the timing of post-pandemic PM peak travel, so they examined changes in the ratio of mid-week trips originating in the early afternoon (12–3:59 PM) and the late afternoon/early evening (4–7:59 PM). They found a clear shift in the temporal distribution of PM trip-making, with relatively more late PM peak period trip-making prior to the pandemic, and more early PM peak trip-making in 2021. The peak afternoon/evening trip-making hour shifted from 5–5:59 PM to 3–3:59 PM. The authors also found that afternoon/evening trip-making in each year is largely explained by three workplace-area/school-area factors: (1) the number of schoolchildren in a block group (earlier); (2) block groups with large shares of potential remote workers (earlier), and (3) block groups with large shares of low-wage jobs and workers of color (later, except for Black workers in 2021). The authors found the earlier shift in PM peak travel between pre- and late-pandemic periods to be explained most by (1) higher shares of potential remote workers and (2) higher shares of low-wage jobs and workers of color. These findings suggest that the rise of working from home has likely led to a shift in PM peak travel earlier in the afternoon when school chauffeuring trips are most common. This is especially true for low-income workers and workers of color.]]></description>
      <pubDate>Wed, 01 May 2024 09:45:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2362205</guid>
    </item>
    <item>
      <title>An Investigation of Factors Influencing Solids Transport and Deposition into Highway Drain Inlets</title>
      <link>https://trid.trb.org/View/2153992</link>
      <description><![CDATA[The Solids Transport and Deposition Study (STDS) was designed to characterize the rates and patterns of solids transfer to, and the collection within, storm water drain inlets located along Caltrans highway facilities. Litter, vegetation and sediment accumulations in 72 drain inlets in the Los Angeles area were monitored biweekly for a year. Sediment samples were collected monthly and analyzed for copper, lead, zinc, chromium, total extractable petroleum hydrocarbons (TEPH), total petroleum hydrocarbons (gasoline range) and BTEX. The primary study objective was to determine if certain distinguishable site characteristics, or factors, controlled the transport and deposition of sediment, metals, vegetation, litter, and petroleum hydrocarbons to highway drain inlets. The factors included in tile study were erosion control/sediment loading (vegetation factor), litter management (litter factor), toxic pollutant generation potential (adjacent land use factor), and roadway design (design factor). Analysis of variance (ANOVA) was the primary statistical method. The ANOVA results indicated that the four primary factors likely had little overall control on solids accumulation or metals mass accumulation, although roadway design and litter management were possibly important in some cases. Additional analyses indicated that other external factors (not included in the study design) were probably also contributing to solids accumulation and metals mass accumulation. This study is considered a first step in characterizing the important factors controlling solids accumulation in highway drain inlets.]]></description>
      <pubDate>Tue, 13 Feb 2024 09:15:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/2153992</guid>
    </item>
    <item>
      <title>Evaluating Accessibility of Los Angeles Metropolitan Area Using Data-Driven Time-Dependent Reachability Analysis</title>
      <link>https://trid.trb.org/View/2206430</link>
      <description><![CDATA[This project is to investigate how accessibility of city blocks is quantified through the transport systems and real traffic flow data from the Los Angeles Metropolitan Area. The authors investigate the reachability problem and provide a solution with a functional system that is capable of visualizing the reachability map (isochrone). Unlike other studies, this approach is data-driven and does not depend on mathematical graph-theory to compute the isochrone which requires intensive computation. Instead, it focuses on directly processing the large amount of traffic flow data that the Integrated Media Systems Center at the University of Southern California (USC) has collected from the Regional Integration of Intelligent Transportation Systems (RIITS) for more than 10 years under the Center’s existing Archived Traffic Data Management System (ADMS) project. The reachability map construction is based on vehicle trajectories so the researchers devised the Data-Driven Trajectory Generator (DDTG), a data-driven, model-free, and parameter-less algorithm for generating realistic vehicle trajectory datasets from ADMS data. Since real world traffic is incomplete with lots of temporal and spatial missing data, the researchers studied imputation and interpolation methods to complete the dataset. Their experiments with real-world trajectory and traffic data show that the datasets generated by DDTG follow distributions that are very close to the distributions of a real trajectory dataset. Furthermore, to demonstrate the results from the proposed research, a web application was developed in which users can select a location, travel time, and the time of year to see the evaluated accessibility info in the form of an isochrone map. The outcomes of this project—synthetic vehicle trajectory dataset and reachability map construction—will be helpful in evaluating accessibility of city blocks for transport systems over a large area, essential for policymakers for effective city planning as well as to improve the well-being of citizens.]]></description>
      <pubDate>Mon, 17 Jul 2023 09:13:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2206430</guid>
    </item>
    <item>
      <title>Commute distance and jobs-housing fit</title>
      <link>https://trid.trb.org/View/2160630</link>
      <description><![CDATA[Anecdotal evidence suggests that the affordable housing crisis is forcing households to seek lower cost housing in the outer reaches of major metropolitan areas, helping to explain recent increases in commute distance. To test this relationship, we use spatial regression to examine the relationship between the availability of affordable housing in close proximity to jobs (jobs-housing fit) and commute distance in the Los Angeles metropolitan area. The analysis draws on 2015 Longitudinal Employer-Household Dynamics (LEHD) Origin–Destination Employment Statistics (LODES) by workplace supplemented with data from the 2013–2017 5-Year American Community Survey on affordable housing units. We find substantial variation in jobs-housing fit across Los Angeles neighborhoods. The imbalance is greatest in higher-income neighborhoods located along the coast and in Orange County, south of Los Angeles. Controlling for other determinants of commute distance, a higher ratio of jobs to affordable housing is associated with longer distance commutes. To address growing commute distances, policymakers must greatly expand and protect the supply of long-term rental housing particularly in job-rich neighborhoods.]]></description>
      <pubDate>Sun, 30 Apr 2023 16:54:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2160630</guid>
    </item>
    <item>
      <title>Adoption of Telecommuting and Changes in Travel Behavior in Southern California During the COVID-19 Pandemic</title>
      <link>https://trid.trb.org/View/2012409</link>
      <description><![CDATA[One of the major impacts of the COVID-19 pandemic on society has been the massive adoption of telecommuting, and its related changes in travel choices. Using data collected in the greater Los Angeles region in the Fall 2020, this chapter examines the topic through the analysis of the changes in travel behavior among workers who adopted telecommuting in some capacity versus workers who did not telecommute during the pandemic. The authors analyze data from a cross-sectional survey conducted among 4,045 local residents to examine key sociodemographic characteristics of these two groups and their changes in travel behavior. The authors observe some major demographic differences between the telecommuting and non-telecommuting respondent groups, with non-telecommuters more likely to be non-white, younger, and with lower household income than telecommuters. At the time of the data collection, all groups reported lower average trip frequency across all travel modes and trip purposes, and reduced vehicle-miles traveled (VMT) as well. However, the authors observed high average monthly frequency of use of private vehicles and active travel modes for non-commute travel, in some cases indicating an increase from the previous year during the same period, as travelers avoided shared modes of travel during the pandemic.]]></description>
      <pubDate>Wed, 07 Sep 2022 09:25:36 GMT</pubDate>
      <guid>https://trid.trb.org/View/2012409</guid>
    </item>
    <item>
      <title>Using Big Data to estimate the Environmental Benefits of Congestion Pricing in the Los Angeles Metropolitan Area</title>
      <link>https://trid.trb.org/View/1882063</link>
      <description><![CDATA[The purpose of this project is to measure the magnitude of the pollution reduction co-benefit generated by pricing congestion. Specifically, the authors estimate two empirical models: First, a model that examines the effects of traffic congestion, measured by cars per miles, on NO and NO₂ emissions of vehicles in freeways. Second, a model that relates speed with NO and NO₂ emissions from vehicles on local roads. The results suggest important relationships between traffic congestion and NO and NO₂ in both freeways and local roads, and results are reported for different time periods. Such estimates can serve as an important input in order to calculate the pollution benefits of congestion pricing. Therefore, the authors take their estimates and illustrate the pollution benefits from removing vehicles from the freeways. For example, removing 500 cars in the morning peak in a typical freeway translates roughly into a 10% reduction of NO emissions in freeways.]]></description>
      <pubDate>Fri, 22 Oct 2021 09:18:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/1882063</guid>
    </item>
    <item>
      <title>Large-scale and Long-term Forecasting of Performance Measurement of Public Transportation Systems</title>
      <link>https://trid.trb.org/View/1882622</link>
      <description><![CDATA[Accurate forecasting of public transportation metrics is critical towards the high reliability and efficiency of the public transportation system. However, deploying a forecasting system to serve city-level public transportation with long-term forecasting is challenging. In this project, the authors develop the capability for processing the entire Los Angeles Metropolitan Area (LAMA) for long-term forecasting of a variety of public transportation system performance metrics. First, the authors explore both spatial statistical methods and machine learning methods to estimate traffic flows for the road segments that do not have traffic sensors. Second, the authors develop methods to enable traffic forecasting with a deep learning model designed for small networks for the entire LAMA road network. The authors also study various training strategies (e.g., teacher forcing) to enable accurate long-term forecasting of traffic flows and bus arrival times. Lastly, the authors develop an end-to-end deep learning approach that combines the estimation and forecasting of traffic flow with data imputation methods for estimating bus arrival time for each stop in individual bus routes in LAMA. Using the real-world data in the University of Southern California Archived Transportation Data Management System (ADMS), the authors show that the proposed approach and system are capable of predicting bus arrival times with a city-level spatial coverage and a route-level temporal forecasting horizon. The authors also demonstrate the overall result of the bus arrival time estimation in a web dashboard. This dashboard enables users at all levels of technical skills to benefit from the developed machine learning approach and access to valuable information for trip planning, vehicle management, and policymaking.]]></description>
      <pubDate>Fri, 22 Oct 2021 09:18:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/1882622</guid>
    </item>
  </channel>
</rss>