Forty-four students presented original work at the Portland State University (PSU) Summer Research Symposium on August 15, and six of those students chose to focus on transportation topics.

Naomi Cai, River Johnson, Danielle Justo Olivia Wang, Paris Wu, and Rayna Yu all devoted their work during a ten-week research program to solving transportation challenges with the use of advanced computational techniques. Each student was advised by a PSU faculty member.

The National Science Foundation (NSF)-funded Research for Undergraduates (REU) and altREU programs are managed by PSU's Teuscher Lab, a lab focused on next generation computing models and architectures led by professor Christof Teuscher of the Maseeh College of Engineering and Computer Science. The programs are designed for curious, motivated students from any university who are interested in designing, programming, and using computers to benefit society. Students select topics they are interested in and work with their faculty advisors to develop a unique research program and put their knowledge into practice.

 "I'm always impressed by what undergraduate students can learn and achieve in just one summer. Perhaps the most valuable lesson they discover is that research is not a straight line: it requires tremendous patience and resilience. In research, many attempts don't work out, leading to frequent setbacks. Yet it's precisely these setbacks that ultimately pave the way to breakthrough discoveries," Teuscher said.

To see the variety of topics investigated by students this summer, check out all the final presentations. Learn more about the transportation projects below, and join us in congratulating these students on their work improving the future of transportation!

Naomi Cai, Washington University in St. Louis

Advisor: Sirisha Kothuri

Topic: Improving Pedestrian Count Estimation with Machine Learning and Data Fusion

Naomi's research explored improving pedestrian count estimation by applying machine learning techniques to Strava fitness app data, along with static and count data. Her initial experiments revealed that model performance was heavily dependent on data splits, leading her to adopt leave-one-out cross-validation for more stable results. Ultimately, Naomi found that CatBoost and Random Forest models generalized better to higher-count data, indicating a trade-off between accuracy at low versus high counts, and identified speed limit as a top-ranked feature in her analysis. By improving estimation models with machine learning and novel data sources, Naomi’s work can help develop cost-effective ways to understand where people are walking.

"I hope I can do more work on the topic, since I thought it was pretty interesting. I think I can definitely improve on the work I did if I'm able to find more data, perhaps from different cities, to work with," Naomi said.

Watch Naomi's Summer Research Symposium presentation to learn more.

River Johnson, Western Carolina University

Advisor: Tammy Lee

Topic: Comparing Ultralytics YOLOv8 and YOLOv10 for Multimodal Transportation Counts

River's presentation focused on improving multimodal transportation counts using Ultralytics YOLO V8 and YOLO V10 models to better inform pedestrian-friendly urban design. They used a Python script written by Alicia Hopper, an altREU program participant from 2024 who also worked with Tammy Lee. The project aimed to overcome the limitations of traditional manual or specialized device counting methods by leveraging object detection models on video footage. Using the Euro City Persons data set, River found that YOLO V8 generally performed slightly better, particularly for pedestrians and bicyclists, while YOLO V10 was superior for categories with fewer samples, such as wheelchair users.

"It was challenging, in a really constructive way. I learned a lot in just 10 weeks, and it was mostly self-directed, but whenever I got stuck on something there was still plenty of support available," River said.

River also presented this work to the PORTAL Users Group (PUG) on August 7. PORTAL is the official transportation data archive for the Portland-Vancouver Metropolitan region.

"It's really cool that students in this program can build on one another's work from year to year and make it their own. Allie Hopper developed the Python script in 2024, and trained a computer model to predict nonmotorized counts using images from a EuroCity Persons Dataset. This year, River was able to focus on improving the accuracy and versatility of this method. It's wonderful to see how each student tackles a problem differently and what other ideas they can come up with," said advisor Tammy Lee, TREC's Transportation Data Program Manager.

Watch River's Summer Research Symposium presentation to learn more. 

Danielle Justo, Smith College

Advisor: Banafsheh Rekabdar

Topic: Exploring Detection Methods for Adversarial Attacks on Multimodal RL Agents

Danielle's presentation delved into exploring adversarial attack detection methods for multimodal reinforcement learning (RL) agents. While her work is not necessarily specific to transportation, it can be used in a variety of contexts. Advisor Banafsheh Rekabdar conducts research in bicycle and pedestrian detection, among other areas.

Adversarial attacks involve subtle changes to input data that cause models to behave unexpectedly, often leading to misclassification. Danielle's objectives included evaluating detection as an adversarial defense and examining how different combinations of attacked modalities influenced detection effectiveness. She trained a baseline RL agent in the MuJoCo Ant Maze environment and attacked its observation space using the Fast Gradient Sign Method (FGSM). Her experiments with various detection models—including clustering, shallow classifiers, and neural networks—showed that classifiers performed better overall than clustering methods. Notably, angular attacks were more detectable than velocity attacks, and a fully connected neural network (FCN) emerged as the best-performing detector, demonstrating a strong importance towards angular modalities. This research highlighted the disproportionate effect of attacks on different modalities and suggested that adversaries must balance the impact on model performance with detectability.

Watch Danielle's Summer Research Symposium presentation to learn more.

Olivia Wang, Tufts University; Paris Wu, Cornell University; Rayna Yu, Northeastern University

Advisor: Christof Teuscher

Topic: NavigAid

Olivia, Paris, and Rayna presented NavgiAid, a route analysis and navigation model designed to improve pedestrian safety in Boston, addressing the limitations of existing car-centric navigation systems. Their objective was to identify the safest walking routes by integrating features linked to crash risk, including speed limits, crosswalk coverage, lighting, sidewalk width, slope, tree coverage, and pedestrian ramps. 

Using the Open Route Service API, their system generated three candidate routes between user-defined points and flagged safety features along each using Analyze Boston datasets. These features were then processed with a Random Forest classifier trained on 300,000 labeled points with Vision Zero crash data, achieving 94% accuracy and an AUC of 0.99. Speed limit emerged as the most influential factor, with indirect features like lighting and trees contributing less. The resulting app displayed routes ranked by safety scores, highlighting flagged features with color-coded visualizations and allowing users to filter preferences. Future directions included refining route comparisons, expanding to other cities with quality data, and leveraging outputs to identify inequities in pedestrian infrastructure for policy and investment decisions.

"In the course of working together in the altREU program this summer to build NavigAid, a navigation model that is focused on pedestrian safety, we learned a lot about both the research process and the issue of pedestrian accessibility, accident risk factors, and infrastructure in our local neighborhood of Boston. We greatly appreciated the opportunity to present and get feedback on our work from experienced researchers in the field, and to learn from other students in our cohort. Their insights helped us to continuously improve our parameters for pedestrian safety as well as the clarity of our research communication," said Olivia, Rayna, and Paris.

Watch their presentation to learn more.

Header: Image from IEEE Transactions on Pattern Analysis and Machine Detection
Image from Morgunov, Anton. "Object Detection with YOLO: Hands-On Tutorial" April 2025
Image courtesy of Sirisha Kothuri

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. 

The Pacific Northwest Transportation Consortium (PacTrans) and the Transportation Research and Education Center (TREC) at Portland State University are thrilled to welcome David Zipper as keynote speaker for the 11th Annual PacTrans Transportation Conference, taking place this fall on the PSU campus in Portland.

Zipper is a Senior Fellow at the MIT Mobility Initiative and a nationally recognized voice on the intersections of transportation policy, technology, and society. A contributing writer for Vox and Bloomberg CityLab, his work has shed light on critical topics including road safety, oversized vehicles, climate change, and strategies to strengthen transit ridership. His insights draw from extensive experience in city government, venture capital, and startup advising—bringing a unique, pragmatic perspective to how transportation systems can adapt under uncertainty.

This year’s conference theme, “Connecting Communities: Improving Mobility under Uncertainty,” aligns directly with Zipper’s expertise in bridging research, policy, and practice to reimagine mobility for safer, more sustainable communities.

In addition to his writing, Zipper brings experience from inside city government and startup ecosystems. He previously served as Director of Business Development and Strategy for Washington, D.C. under two mayors, guiding the city’s response to ride-hail and supporting its first startup incubators. He co-hosts the podcast "Look Both Ways with David and Wes," where he brings a pragmatic lens to all things transportation.

About the PacTrans Conference

Want to present at the conference? We are now accepting proposals for posters and lighting talks, due August 27!

Now in its 11th year, the PacTrans Transportation Conference is the premier gathering for transportation research, policy, and practice across US Department of Transportation (USDOT) Federal Region 10. This year’s theme, “Connecting Communities: Improving Mobility under Uncertainty,” addresses the pressing challenges facing the Pacific Northwest’s transportation systems, from climate resilience to equity in access and the rapid evolution of new technologies.

The one-day event will feature a rich agenda of technical breakout sessions, poster presentations, and networking opportunities. Participants include transportation professionals, researchers, faculty, students, and community members, creating a forum for collaboration across disciplines and sectors.

Conference Agenda

The conference will be divided into three tracks: Smart Mobility Analytics; Human-Centered Mobility; and Innovations for Infrastructure Resilience.

Smart Mobility Analytics

This track examines how recent advances in machine learning and sensing systems contribute to new understandings of mobility. Sessions will explore data analytics and autonomous mobility, including using data and analytical tools to achieve Vision Zero.

Human-Centered Mobility

This track explores how users of the transportation system can be engaged in planning, design, implementation, and research, and how to create a transportation system to better support users of all abilities. Sessions will focus on electrification and community engagement.

Innovations for Infrastructure Resilience

This track highlights cutting-edge research and practical solutions aimed at enhancing the resilience of transportation infrastructure in the face of environmental stressors, natural hazards, and extreme weather—especially in cold and remote regions. Presentations will explore advancements in monitoring systems, climate-adaptive materials, AI-informed modeling, and strategies for improving mobility and accessibility under challenging conditions such as earthquakes, permafrost degradation, and freeze-thaw cycles. Attendees will gain insights into scalable innovations that strengthen transportation networks and support long-term reliability and safety across Region 10 and beyond.

Pre-Conference Workshop

On Thursday, October 9, join us for a special workshop on "Human Centered Ai: Ethics, Bias Mitigation, And Cybersecurity." This workshop explores the principles, ethical considerations, and practical applications of Human Centered AI in transportation, with a focus on mitigating bias, ensuring cybersecurity, and fostering responsible AI deployment.

The conference is hosted by PacTrans, the federally designated University Transportation Center for Region 10, and TREC at Portland State University, a national leader in advancing transportation research and education. Partner institutions include the University of Alaska Anchorage, University of Idaho, University of Washington, Washington State University, Portland State University, and the Northwest Indian College.

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. 

Wildlife everywhere faces a growing challenge: moving safely across an increasingly fragmented landscape. Roads, urban development, and other human-made barriers can make it harder for animals to access food, shelter, and breeding areas, while also increasing the risk of wildlife-vehicle collisions. To address this issue, researchers at Portland State University (PSU) worked on a groundbreaking effort to understand and protect the travel patterns of Oregon’s wildlife.

The Oregon Connectivity Assessment and Mapping Project (OCAMP) was a multi-year collaboration aimed at mapping wild species' habitats and travel corridors across the state. The research team created an interactive Priority Wildlife Connectivity Areas Map of Oregon, which can be used to protect wild animals' ability to move from place to place. The project was funded in part by the Oregon Department of Transportation (ODOT), to help the agency identify and mitigate the impacts of transportation infrastructure on Oregon's wildlife.

ABOUT THE PROJECT 

In June of 2019, the Oregon Legislative Assembly passed House Bill 2834, which mandated that the Oregon Department of Fish and Wildlife (ODFW) develop a Wildlife Corridor Action Plan to provide guidance for the designation and protection of wildlife corridors in Oregon. The bill also directed the Oregon Department of Transportation (ODOT) to establish a program to reduce wildlife-vehicle collisions in areas where wildlife corridors identified in the Wildlife Corridor Action Plan intersect with proposed or existing public roads. 

Rachel Wheat, the Wildlife Connectivity Coordinator for ODFW, was the project coordinator. The PSU research team was led by Martin Lafrenz of the Geography department, Catherine De Rivera of Environmental Sciences and Management, and Daniel Taylor-Rodriguez of the Department of Mathematics and Statistics. Lafrenz is a geomorphologist who studies human alteration of the water cycle and the landscape, De Rivera studies how anthropogenic changes in habitat connectivity affect animal populations and ecosystems, and Taylor-Rodriguex focuses on applying statistical methods to large scale problems, with an emphasis on ecological applications. The research was supported by PSU masters students Amanda Temple, Claire Brumbaugh-Smith, and Alana Simmons, and PhD students Leslie Bliss Ketchum and Jacob Schultz.

A large number of researchers, conservation groups, agencies and others were involved in helping to complete OCAMP – part of Oregon's larger conservation strategy – and the data used in the project came from many sources.

"A lot of biologists worked on this project, and many of them know each other. So we reached out to certain people, and then they reached out to more people. There were a lot of connections that happened, for over a year, and people supplied us with whatever data they had on animal presence or tracking," Lafrenz said. Lafrenz's team mapped out key habitats and travel routes used by different species, and Taylor-Rodriguez's team used the data to ensure that the maps aligned with real-world species movement and habitat use.

CONNECTING SCIENCE TO TRANSPORTATION SOLUTIONS

While the Priority Wildlife Connectivity Areas map has many applications — from land conservation to renewable energy siting — one of the most immediate uses is in transportation planning. ODOT can use this map to identify road segments that pose the greatest risk for wildlife-vehicle collisions and determine the best locations for wildlife crossings, such as underpasses or overpasses.

Wildlife-vehicle collisions are not only a danger to animals but can also endanger human safety, and can be costly. Strategic planning informed by OCAMP data means transportation agencies can reduce these risks while supporting Oregon’s biodiversity.

In the past, connectivity mapping in Oregon relied heavily on expert opinion, which left decision-makers without the robust data needed to guide policy and planning. The OCAMP project filled a major knowledge gap, with science-based connectivity models for 54 species representing different movement patterns and habitat needs. These models were combined to create the Priority Wildlife Connectivity Areas Map, which offers a statewide picture of the most critical areas for wildlife movement.

"We used tracking data where we had it, and presence and absence data to validate where the animals were. Then we put all the species together. In the final map, what you notice about it is that it's not for a particular species. It's just animal corridors, generalized. If we are really interested in a specific animal, we can always drill back in the data. But what the Legislature wanted was just a map of animal corridors in general that they could use to say, Okay, you're going to do this project. It's going to impact this corridor. So you need to put some kind of a crossing structure or fencing or some sort of mitigation," Lafrenz said.

WHO CAN USE THIS RESEARCH?

"Now that we have this information, the next big step is to shift into implementation. So how do we make sure that this tool is being used effectively? There are a lot of ways that we've done that, within the State government specifically. We're working with ODOT, to make them aware of where those Priority Wildlife Connectivity Areas intersect with our state highway system. We're also working with the Department of Land Conservation and Development, to guide siting and mitigation for new developments," Wheat said. 

ODFW has presented the Priority Wildlife Connectivity Areas map and tools to organizations including the Association of Oregon Counties and the League of Oregon Cities, as well as Federal land management agency partners.

"There are applications for the Bureau of Land Management, the U.S. Forest Service, the Fish and Wildlife Service, Land Trusts, soil and water conservation districts, watershed councils; basically anyone that's working in the conservation realm can benefit from this specific tool. There are also use cases for members of the public," Wheat said.

A paper by the research team, Visualizing Connectivity for Wildlife in a World Without Roads, was published in the journal Frontiers in Environmental Science.

"In that paper, we took southwestern Oregon and erased all the roads. And then we reran our model and compared, where would animals move if there were no roads as opposed to where we think they're moving now? We found that roads had a strong impact on connectivity. Roads influenced connectivity well beyond the footprint of the roadway," Lafrenz said.

Modeling wildlife movement in the absence of existing roads allowed for critical evaluation of where mitigation activities, such as wildlife crossing structures and fencing, could be most beneficial. This novel approach has practical applications for increasing connectivity for wildlife across roads. The high-resolution Priority Wildlife Connectivity Areas map also represents a new innovation in connectivity mapping; an area in which other states might follow Oregon's lead.

"Other states have engaged in statewide connectivity planning and mapping. One thing that sets OCAMP apart is that we used a much newer modeling approach, with much finer-scale spatial data. A lot of the tools that have been produced in other states in the past are at a very coarse spatial scale.Our maps are at a 30 meter resolution. So you can scale down to very small-scale efforts and get into very fine detail," Wheat said.

HOW INDIVIDUALS CAN HELP

ODFW developed a project specifically for roadkill in Oregon which makes use of data from iNaturalist, an online social network for recording observations of wildlife. 

"One of the things that we get asked a lot in our public communication is, how can the average person help provide information for connectivity? And one of the best ways that we found to do that is with iNaturalist," Wheat said.

The state has some information on where large-bodied wildlife, like deer and elk, are killed on roadways, because their maintenance crews remove them. But ODFW has very little information on smaller-bodied species. That's where iNaturalist comes in.

"Anyone with a cell phone can go out and snap a photo of a roadkill observation that they see. And then we can draw on that information to help identify roadkill hotspots and find the areas where we really need to focus on doing some sort of mitigation, whether that's crossing structures, habitat modification, or fencing to try to keep wildlife from getting killed on the road," Wheat said.

With a wide variety of applications for individuals, organizations, and governments, the Priority Wildlife Connectivity Areas map provides a critical tool for planning a connected future. For PSU researchers, OCAMP is an example of how science can inform policy and deliver real-world benefits.

Katherine Keeling graduated from Portland State University (PSU) in 2022 with a Master's in civil engineering. She is now a Senior Analyst in Operations & Finance Planning at TriMet.

Connect with Katherine on LinkedIn

What do you do in your current role, and what does a typical day look like? 

I am a Senior Analyst for Operations & Finance Planning. As this title suggests, my main focus is estimating the operations & maintenance costs associated with a change in transit operations. Depending on the impetus, I might be collaborating with transit planners, maintenance experts, executives, or engineering & construction project managers.

How did your experience at PSU shape your path into the transportation field?

I actually keep my PSU transportation engineering notes at my cubicle desk! When I joined a team of analysts, I felt lacking in my understanding of data structures. But I decided to lean into my experience as a researcher to vet assumptions/methodologies, elevate the communication of findings, and to integrate scholarly knowledge into the interpretation of TriMet’s internal data. This became my professional voice!

What advice would you give to current students or recent grads interested in a career in transportation? 

Don’t let fear hold you back from asking all the questions that you need answered! For me, it was tough to be vulnerable enough to ask questions in a large meetings with seasoned professionals, but demonstrating a genuine intent to understand and engage will always pay off! Plus, transportation folks appreciate enthusiasm and heart, not just technical skills.

What’s one project or accomplishment you’re especially proud of in your career so far?

A fun project was drumming up ridership studies to help TriMet negotiate a Ticket-to-Ride campaign with Providence Park; now any Timbers/Thorns/concert ticket is valid fare on event days! It’s a fun way to make transit a part of people’s memories.

Photo courtesy of TriMet. This is an installment in a Transportation Alumni Highlight series, showcasing Portland State University (PSU) graduates who are making a difference in the world of transportation. 

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.