Over the past several years, in a series of research projects, researchers at Portland State University (PSU) have been developing a new approach to estimate active transportation volumes using machine learning.

This emerging method, which can predict how many people will be biking or walking on any given road, trail or segment of a transportation network at any time, offers promising applications for transportation agencies and state departments of transportation (DOTs). These organizations can use accurate bicycle and pedestrian volume information to track changes over time, prioritize projects, plan and design new infrastructure, conduct safety analyses and estimate public health impacts.

"These methods are still evolving, and it's still in the research phase. But I think the time is not far off when we will start using these methods as more mainstream," said Sirisha Kothuri of the Maseeh College of Engineering and Computer Science, the lead researcher on this series of projects.

The method Kothuri and other researchers are developing is referred to as "data fusion" because it involves combining multiple data sources, including traditional permanent and short-term counting methods as well as newer crowdsourced data streams from entities like Strava and Streetlight.

HOW DOES IT WORK?

Traditional permanent and short-term counting methods can directly provide counts, but are limited to certain locations or short periods of time. Meanwhile, crowdsourced data (such as Strava or StreetLight) can cover a wider area but with less accuracy, as they only capture a subset of users.

Fusing the two methods together–potentially with the use of deep learning algorithms–is a promising way to get the best of both.

The researchers train a computer model on existing count data from certain locations, then use that trained model to predict volumes at locations where there is count data that the model hasn't seen. They then compare the model's predictions with the actual count data to see how accurate it is.

Using long short-term memory networks and deep neural networks, the method involves the combining of static variables—such as network characteristics, demographics, and land use— with dynamic crowdsourced data and count data from different regions. The research has shown that crowd-sourced data alone cannot replace traditional count data. For the method to work, both are necessary.

Regional data is also key to the success of the model: the more local count data the model can be trained on, the better its accuracy will be for the area in which it will be used.

The models tend to fare better when using Monthly Average Daily Bicyclists (MADB) as a target, rather than Annual Average Daily Bicyclists (AADB), because breaking each counter down into monthly units gives them more data points to work with.

"Basically, the more data a model has, the smarter it gets," said Banafsheh Rekabdar, an Assistant Professor of Computer Science in the Maseeh College of Engineering and Computer Science who worked with Kothuri on the latest project.

The graphic below offers an overview of the path of data from original sources as it moves through the process developed by the researchers:

A SERIES OF RESEARCH EFFORTS FUNDED BY MULTIPLE ORGANIZATIONS 

These research efforts got underway in 2018 with funding from the National Institute for Transportation and Communities (NITC). NITC launched a pooled fund project with support from the DOTs of Oregon, Virginia, Colorado, Utah, and the District of Columbia, as well as Central Lane MPO and the Cities of Portland and Bend, Oregon. With matching funds from NITC, those agencies came together to fund the initial project Exploring Data Fusion Techniques to Estimate Network-Wide Bicycle Volumes, with a research team led by Kothuri made up of researchers from PSU and the University of Texas at Arlington. The objective of this study was to fuse traditional count data with crowdsourced data, land use and sociodemographic data to estimate bicycle volumes on a network. It was the first large scale of its kind to include data from multiple regions and years to generate bicycle volumes using data fusion techniques.

Next came "Estimating Bicyclist Volumes with Crowdsourced Data," a study funded by the Washington Department of Transportation (WSDOT), which built on the initial efforts and focused on the transferability of bicycle volume models that were estimated as part of the NITC pooled study.. As part of a case study for this project, the researchers showed how bicycle volumes can be estimated for certain high-risk crash corridors rather than the entire network using data fusion techniques, which can be a critical input for safety analyses.

Kothuri and her team then focused on another NITC study which focused on adapting the bicycle volume estimation techniques to the pedestrian context.This study used data fusion techniques to combine crowdsourced data (Strava pedestrian data) along with static contextual data to model 2-hour PM peak pedestrian volumes.

On the bike side, the WSDOT study was followed by a NITC technology transfer initiative aimed at improving the accuracy of the bicycle volume estimates using machine learning techniques.

The latest report to come out of these efforts, Improving the Accuracy and Precision of Bicycle Volume Estimates Using Advanced Machine Learning Approaches (PDF) by Sirisha Kothuri, Banafsheh Rekabdar and Joe Broach of Portland State University, pushed the needle forward on using advanced techniques to extrapolate data over a large transportation network. Two PSU graduate students also worked on the project: Saba Izadkhah, who is working toward a PhD in computer science, and Andrew Wagner, a computer science masters student.

A paper based on this work was presented at the Institute of Electrical and Electronics Engineers' International Conference on Artificial Intelligence x Science, Engineering and Technology at the beginning of October. Kothuri also presented updates on the data fusion method at the 2024 Pacific Northwest Transportation Consortium (PacTrans) Conference.

"We know that for pedestrians, injuries and fatalities are at an all time high. Bicyclist safety is also of top concern. So these estimates are really critical for agencies right now," Kothuri said.

Portland State University's Transportation Research and Education Center (TREC) is a multidisciplinary hub for all things transportation. We are home to the Initiative for Bicycle and Pedestrian Innovation (IBPI), the data programs PORTAL and BikePed Portal, the Better Block PSU program, and PSU's membership in PacTrans, the Pacific Northwest Transportation Consortium. Our continuing goal is to produce impactful research and tools for transportation decision makers, expand the diversity and capacity of the workforce, and engage students and professionals through education, seminars, and participation in research. To get updates about what's happening at TREC, sign up for our monthly newsletter or follow us at the links below.

 BlueSky  |  Instagram  |  LinkedIn  |  Facebook  |  TikTok  |  YouTube

Travel time reliability – or the consistency and dependability of travel times from day to day, and at different times of day – is a key metric that significantly affects people’s travel behavior. Since businesses rely heavily on transportation systems, an unreliable transportation network can also impact the economic competitiveness of urban areas. As such, reliable travel times are important for transportation agencies to promote economic stability within a community. Having accurate methods to evaluate reliability is important for both transportation practitioners and researchers.

A new report from Portland State University offers an improved method for determining the confidence interval of travel time reliability metrics. Researchers Avinash Unnikrishnan, Subhash Kochar and Miguel Figliozzi of PSU’s Maseeh College of Engineering and Computer Science used a highway corridor in Portland, Oregon as a case study to evaluate their method, and found that it compared favorably with other methods of evaluating the confidence interval of travel time reliability metrics.

"Traffic engineers can apply this method to come up with a range of estimates for the unknown true travel time reliability metric. The travel time reliability metrics calculated by traffic engineers and transportation planners will have variability due to factors such as road and mode type. The methods proposed in this research can be used to make inferences on travel time reliability metrics which accounts for this variability. Traffic engineers can apply the methods to attach statistical guarantees to the travel time reliability metrics," Unnikrishnan said.

WHY IS IT IMPORTANT?

This research is timely because the COVID-19 pandemic and consequent changes in traffic levels have highlighted the need to quickly compare and better understand the behavior of most commonly used traffic reliability measures.

One challenge for the research team: there is a general lack of consensus on the population distribution of travel times. Depending on the study and the context, a wide variety of distributions have been found to be appropriate. To overcome this difficulty, the researchers developed confidence interval procedures that are general because they are independent of the type of travel time distributions, and can work for a wide range of distribution shapes. This makes the evaluation method more flexible and able to be applied in different situations.

The methods they developed can be used to arrive at practical estimates of changes in traffic, which can help transportation agencies maintain consistent travel times across a roadway network. The outcomes of this project can also help transportation researchers to test other travel time reliability measures, and conduct before-and-after travel time reliability evaluation studies with improved accuracy.

PORTLAND, OREGON CASE STUDY

Next, researchers applied these approaches to a real-world case study. The data for the case study came from the Portland, OR metropolitan region and was originally collected and analyzed as part of an earlier NITC project, Understanding Factors Affecting Arterial Reliability Performance Metrics. In that project, Unnikrishnan worked with PSU civil engineering researchers Sirisha Kothuri and Jason Anderson to understand the temporal variation in travel time reliability metrics on three major arterials in Washington County. 

Map of the study corridor; a stretch of Tualatin-Sherwood road from OR 99W to SW Nyberg Street.

Map of the study corridor; a stretch of Tualatin-Sherwood road from OR 99W to SW Nyberg Street.

Using the data from one of those three arterials—Tualatin-Sherwood Road from OR 99W to SW Nyberg Street—the research team of the current study estimated confidence intervals for three different travel time reliability metrics: buffer index, modified buffer index, and the relative width of travel time distributions. 

Where a travel time index is the average additional time required during peak times as compared to times of light traffic, the buffer index represents the additional time that is necessary above the average peak travel time. In this project, researchers considered two forms of buffer index. First, the ratio of 95th percentile travel time to sample average travel time minus one. The modified buffer index refers to the ratio of 95th percentile travel time to median travel time minus one. 

The relative width of travel time distributions is defined as the ratio of the range of travel times in which 80% of the observations around the median fall into the median travel time. In another NITC project focused on buses, PSU researchers Travis Glick and Miguel Figliozzi used a similar metric for understanding transit reliability using speed data

The research team compared their new methods against several existing methods and found that they worked well: Numerical tests showed a positive performance and high statistical power for analyzing the available travel time data. More details about the process can be found in the final report.

Photo courtesy of Google Streetview

This research was funded by the National Institute for Transportation and Communities, with additional support from the Oregon Department of Transportation.

ABOUT THE PROJECT

Statistical Inference for Multimodal Travel Time Reliability

Avinash Unnikrishnan, Miguel Andres Figliozzi and Subhash Kochar; Portland State University

RELATED RESEARCH

To learn more about this and other NITC research, sign up for our monthly research newsletter.

The National Institute for Transportation and Communities (NITC) is one of seven U.S. Department of Transportation national university transportation centers. NITC is a program of the Transportation Research and Education Center (TREC) at Portland State University. This PSU-led research partnership also includes the Oregon Institute of Technology, University of Arizona, University of Oregon, University of Texas at Arlington and University of Utah. We pursue our theme — improving mobility of people and goods to build strong communities — through research, education and technology transfer.

Projects
1403
Researchers
uavinash@pdx.edu

Tags

"Transformative Transportation Survey Methods: Enhancing Household Transportation Survey Methods for Hard-To-Reach Populations," is a new article published in the September 2021 issue of Transportation Research Part D. It was co-authored by Amy Lubitow, a sociology faculty member at Portland State University, Erika Carpenter, a sociology graduate student, and Julius McGee, a faculty member in urban studies and planning.

The study explores the challenges that hard-to-reach populations face in completing household activity surveys. Researchers drew on qualitative data from hard-to-reach populations regarding the limits of the Oregon Household Activity Survey and found evidence that the survey methods lack social, cultural, and linguistic applicability for Black, Indigenous and other people of color, as well as low-income populations. The authors argue that Oregon’s household travel survey prioritizes certain ways of understanding and experiencing mobility that are, by default, exclusionary. The article concludes in sharing insights regarding how transportation professionals might improve data collection efforts. Broader efforts for transportation equity (and ultimately towards transportation justice) cannot be achieved when the data used to inform transportation planning fails to accurately reflect all populations.

The paper draws on findings from a NITC research project led by Lubitow: Advancing Transportation Equity through Inclusive Travel Survey Data Methods

Photo by santypan/iStock

The National Institute for Transportation and Communities (NITC) is one of seven U.S. Department of Transportation national university transportation centers. NITC is a program of the Transportation Research and Education Center (TREC) at Portland State University. This PSU-led research partnership also includes the Oregon Institute of Technology, University of Arizona, University of Oregon, University of Texas at Arlington and University of Utah. We pursue our theme — improving mobility of people and goods to build strong communities — through research, education and technology transfer.

Projects
1122
Researchers
alubitow@pdx.edu