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

The Bike Bus movement is gaining momentum. All over the country, rain or shine, groups of children with adult supervision are hopping on bikes to ride to school together, and the new organization Bike Bus World, led by Coach Sam Balto, has received official nonprofit status.

Last week, the U.S. Department of Transportation announced a $1.1 million federal grant from the Safe Streets and Roads for All (SS4A) program was awarded to Metro. The funds will be used to boost walking school bus and bike bus programs in north Portland. Read more about the new award on BikePortland.

Benefits of the Bike Bus go beyond physical activity: It's an opportunity for kids and parents to socialize, have fun, start the day on a positive note, and save time on driving, parking, and waiting in school dropoff lines.

According to Portland State University (PSU) researchers, bike buses could be the missing puzzle piece required to complete a robust active transportation to school (ATS) approach. 

A new report published by Evan Howington, John MacArthur, and Nathan McNeil of PSU's Transportation Research and Education Center (TREC) concludes that bike buses have the potential to leverage the last 20 years of Safe Routes To School (SRTS) interventions, ensuring that the miles of bike lanes, sidewalks, and crosswalks funded by districts, communities, states, and the federal government have their full value realized. 

Read more about the research on the Bike Bus Project website: A Better Commute To School.

THE RESEARCH

In addition to reviewing the existing literature around bike buses, the researchers conducted two online surveys and ten video interviews with parent and child participants of bike buses in the Portland, Oregon metro area. They also created a "Bike Bus Tracker" showing bike bus programs around the United States (know of one that's not on the map? Share it with the research team!)

The first survey was targeted at bike bus coordinators and leaders, focusing on logistics, school policies, and the street environment. The second survey was targeted at bike bus parent participants, focusing on perceptions, parent and student attitudes, and the urban environment. The interviews built on both surveys, also bringing child participant voices into the study.

The findings indicate that bike buses can change the narrative about active transportation to school, or ATS. The sense of community and fun often cited by both adults and children, as well as a desire expressed by parents to inculcate a sense of confidence and love of biking in their children, indicate an entirely new slate of attitudes towards ATS compared with what the previous research literature describes. 

FINDINGS

The Final Report (PDF) offers a range of insights on Portland's bike buses, from who coordinates them and how long they've been in operation, to participant demographics and sources of funding and support. A few highlights from the surveys and interviews are below.

Throughout the 10 interviews, approximately nine themes emerged that most participants mentioned: 

1. bike bus logistics, 
2. traffic safety, 
3. convenience/schedule, 
4. socialization/community, 
5. politics/lifestyle, 
6. school support, 
7. fun, 
8. exercise/physical activity/health, and 
9. weather.

All participants, including some of the child participants, mentioned safety concerns at least once during the interview. Commonly cited safety concerns included:

1. Car drivers not appropriately yielding along streets and at intersections or marked crossings, including along neighborhood greenways;
2. Reckless behavior from car drivers, including around school zones;
3. Unsafe riding conditions, including lack of appropriate facilities along the route; and
4. Difficulty managing unsafe crossings, even marked ones with signals.

The highest reported impact of the bike bus on respondents’ children was good exercise (39%), followed by learning traffic safety (19%.) 

Barriers to participating in bike buses still exist, including dissatisfaction with infrastructure and a lack of funding, but this initial research shows promise for expanding the available options for ATS in North America. 

For a deeper dive into the findings, watch a recording of the October 25, 2024 seminar presented by Howington, MacArthur, and McNeil: PSU Transportation Seminar: Bike Buses: An Evaluation of An Emerging Active Transportation to School Intervention.

WHAT'S NEXT?

The results from the first phase of this research informed the development and implementation of schoolwide surveys of parents in four elementary schools with bike buses in Portland (Phase 2 of the study). The school-wide surveys focus on what barriers and opportunities exist for the wider adoption of bike buses through the lens of parent and student perceptions and travel behavior as it relates to school SRTS policies, the street environment, and the urban environment. 

The surveys were conducted in Spring 2024 and findings will be detailed at the 2025 Transportation Research Board Annual Meeting paper and presentation. 

AREAS FOR FUTURE RESEARCH

Based on the literature review, surveys with bike bus leaders/coordinators, and interviews with parent and student participants, the researchers came up with some recommended areas for additional study and research: 

Infrastructure and Bike Buses 

Participants felt safer biking in a bike bus but expressed dissatisfaction with the existing infrastructure, citing it as inadequate for traffic and driver concerns. Identifying supportive infrastructure could inform future investments.

Convenience and Bike Buses 

Participants gave mixed feedback on bike bus convenience, often citing time and logistics over distance. Addressing barriers like afternoon options and parent involvement could improve participation as bike buses evolve.

Participant Benefits 

The research found that parents cited physical exercise, traffic safety, and bike skills among the primary bike bus benefits, contrasting with literature suggesting academic performance benefits. Understanding this gap between other research on ATS and bike buses will highlight how they differ from other ATS interventions such as walking school buses and walking or biking to school alone. 

Other areas that may be of interest include efforts to institutionalize bike buses (such as through funding paid coordinators); logistical barriers to afternoon bike buses (the commute home or to after-school activities); and how social factors may allow parents to let their students participate in a bike bus without their direct supervision. 

ABOUT THE PROJECT

Exploring Bike Bus Programs in the United States

Principal Investigator: John MacArthur, Portland State University, and co-investigator: Nathan McNeil, Portland State University

• Download the research report (PDF)
• Watch the October 2024 Seminar
• Explore the project website

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

Portland State University (PSU) researchers have partnered with TriMet to evaluate the design of a new shared-use bus platform that incorporates a sidewalk-level bike lane. The project, FX2 Shared Bicycle & Pedestrian Platform Evaluation, assessed how well the new design is working for transit riders and other road users along Portland's Southeast Division Street.

The most common bus and bike lane design typically has a bike lane directly adjacent to the right side of the bus lane with no physical barrier. This presents several safety concerns. In this scenario, a bike behind a bus would have to wait behind or pass the bus by riding into traffic. As vulnerable road users, these conflicts pose a potentially serious risk to bicyclists.

The FX2-Division is a Frequent Express (FX) bus line that runs from downtown Portland to Gresham. The transit service began operations in September 2022. To accommodate passing bicyclists and transit riders accessing the new FX2 line, TriMet worked with the City of Portland and a broad group of stakeholders and partners to create a design that would allow bikes to stay separated from automobile traffic, with the bikeway passing through the platform area next to where people wait for the bus.

The PSU research team consisted of Nathan McNeil and Jennifer Dill of the Transportation Research and Education Center (TREC), with Sirisha Kothuri and Christopher Monsere of the Maseeh College of Engineering and Computer Science (MCECS).

PSU has a good track record of working with the City of Portland and TriMet on innovative designs, including evaluations of the red bus lanes, separated bike lanes, bike signals and bike boxes.

"We love when cities do innovative things and try new ideas to overcome challenges. Division had been identified as an important bike corridor, transit route, and route for motorists. So a new bus platform needed to accommodate all the different users, without forcing bikes to move out into traffic and go into conditions where they felt unsafe. This design was an attempt to bring buses and bikes together without forcing either out into traffic; the tradeoff is that transit riders now are interacting with bikes. The main question behind our evaluation was, how are those tradeoffs working? Are there new risks that need to be considered, minimized, and accommodated for?" said lead researcher Nathan McNeil.

TriMet schematic of standard FX2 platform design

In addition to analyzing hours of video collected in the field, the research process also included surveys and interviews with people with low vision.

Key research questions included: 

• How often are there conflicts between bicyclists and pedestrians, including near misses or collisions?
• What is the nature of the conflicts?
• How often do transit riders wait in the step-out zone or bike zone, instead of in the waiting area?
• How often do bicyclists stop at the stop bar (where the “stop here for pedestrians” sign is located) when a bus is at the stop?
• When bicyclists do not stop at the stop bar, do they still yield to transit riders getting on and off buses, do they go around buses, or behind the platform waiting area?  •
• How do wheelchair users and people with vision impairments navigate the platforms?

Jesse Stemmler is the Design Manager and Urban Design Lead for TriMet's Division Transit Project. With the introduction of a new station typology, one which has potential application across the region, his team at TriMet approached the design process with intention. Partners from the TriMet Operations Group and its Committee on Accessible Transit, the Portland Bureau of Transportation (PBOT) Bicycle Advisory Committee, the PBOT Pedestrian Advisory Committee, the Oregon Commission for the Blind, the Oregon Department of Transportation, and local design firms all contributed input to the initial design of the new station. 

Once it was deployed in the real world, the partnership with PSU continued the same spirit of rigor and commitment to implementing the best design for all road users.

"There aren't many opportunities in our world to be able to do this extensive amount of design study and then have that followed by real-world analysis and evaluation. So this work has been recognized as something very unique. It's not to say that everything in this design is perfect, but it represents a level of commitment to study and analysis of how we can more safely construct transit stops, where we're also accommodating bikes and pedestrians in these very constrained corridors. It is an important touchpoint, not only for how our region addresses transit and bicycle infrastructure, but it's now contributing to the national conversation in a meaningful way, " Stemmler said.

Some key overall findings from the analysis include: 

• The primary conflicts which gave rise to the need for this design, including bikes moving out into automobile traffic, have been largely alleviated. Only 2% of bicyclists and other micromobility users used motor vehicle travel lanes.
• Bicyclists and other micromobility users rarely stop for transit passengers, but they do slow down when passengers and buses are present.
• Interactions between bicyclists and transit passengers generally occurred at slow speeds with each user aware of one another, negotiating for space.
• Some additional warning about when bicyclists are passing would be helpful, particularly for visually impaired transit passengers and pedestrians.
• Overall, surveyed FX2 passengers like the platform design. Green color was generally preferred for the bike lane.
• Inconsistency in design is a detriment for passengers with vision impairments.  

ABOUT THE PROJECT

Division Street Transit Project: FX2 Shared Bicycle & Pedestrian Platform Evaluation

Principal Investigator: Nathan McNeil, Portland State University;

Co-investigators: Sirisha Kothuri, Christopher Monsere, and Jennifer Dill, Portland State University

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 on social media.

Our annual summer Bikeway Design workshop, offered through the Initiative for Bicycle and Pedestrian Innovation (IBPI), was held last August at Portland State University. Eighteen professionals attended, learning from local active transportation experts on topics including bicycle facility design, traffic engineering techniques that support active travel, and designing for suburban environments. Check out some photos from this year's workshop.

The week-long workshop also included field tours of bicycle infrastructure in Portland and its surrounding communities. The final day of the workshop, students convened in PSU's Engineering Building to confer together about design problems they were currently being challenged by at work, in their home communities.

One of this year's participants was Portlander Aaron Kuehn, the outgoing chair of BikeLoud PDX, a local bike advocacy nonprofit. Inspired by what he learned in the workshop, he wrote a three-part guest post on the popular BikePortland blog, titled "How to Design a Bikeway." The three posts offer an overview of the Bikeway Design workshop and invite readers to participate in imagining their own bikeway solutions.

"I think everyone has a role to play in designing great streets," Kuehn wrote. 

Workshop attendees putting their heads together on the final day to help each other problem-solve their own design challenges is typically a favorite among participants, sometimes laughingly described as a "peer support group."

The image above shows students displaying projects in their hometowns via Google maps, indicating exactly where the problem areas are and what solutions have been considered. Advice and questions flowed freely, and many said that they came away from the workshop feeling excited to go back home and start putting their new knowledge into practice.

Here are a couple of quotes from workshop participants:

"The IBPI Bikeway Design Course gives tangible examples of policies and standards in action. The Neighborhood Greenways are a wonderful example of how walking and bicycling has been prioritized by policy, and then you physically ride a bike and see the diverters and traffic calming measures realizing this vision. I would highly recommend anyone attend this course to learn and experience the practical design implementation of a great cycling city."

"Participating in the IBPI Bikeway Design Workshop left me rejuvenated and excited to improve my own town! The magic of implementing safe, connected, and attractive bike infrastructure was revealed by the expert planners and passionate engineers leading the engaging and interactive course."

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 going on at TREC, sign up for our monthly newsletter or follow us on social media.