The Population Health Initiative has awarded eight early-stage pilot grants in November 2025. The project, “Embodied Nature Engagement: Developing the Interaction Pattern Preference Inventory (IPPI) for Nature Prescriptions in Primary Care” includes Sebastian Tong (Department of Family Medicine), Peter Kahn (Department of Psychology & School of Environmental and Forest Sciences), Ashley Park (Department of Family Medicine), and Hongfei Li (College of Built Environments). Hongfei Li is a lecturer and interdisciplinary PhD student in the Landscape Architecture department. Congratulations to Hongfei…
Department: College of Built Environments
An outlook on ride-sourcing price changes: Implications for future transit agency-TNC partnerships
Ashour, L., & Shen, Q. (2025). An outlook on ride-sourcing price changes: Implications for future transit agency-TNC partnerships. Transport Policy, 173, Article 103790. https://doi.org/10.1016/j.tranpol.2025.103790
Abstract
Ride-sourcing trip prices charged by transportation network companies (TNCs) have increased significantly compared to before the pandemic, causing concerns about the effectiveness of existing and planned transit agency-TNC partnerships. This paper explores three scenarios of future TNC price changes: (1) price trend extension using forecasting models, (2) price increase in response to local policy changes, and (3) TNC/taxi price convergence due to increased competition. We then investigate the impact of TNC price change on the prospect of transit agency-TNC partnerships, using a case study in the Seattle region. For the first scenario, we employ two time-series models, namely ARIMA and PROPHET, to forecast price changes within the next three years (Oct 2022–Oct 2025) using publicly available Chicago TNC trip data. The results show that TNC's daily average price would reach $3.23 per mile, increasing by 40 % from 2019 average rates. For the second scenario, we track significant policies that directly impacted TNC prices in Seattle and incorporate reported price increases. The resulting estimations indicate that TNC prices would increase by an extra 25 % in response to changes in the minimum wage law. For the third scenario, we use publicly available taxi trip data of the city of Chicago and forecast future taxi prices by estimating time-series models comparable to those for TNC prices. The analysis suggests that due to increased competition, TNC and taxi prices are converging and that the average TNC fare per mile could add another 50 % to the forecasted price if TNC and taxi prices become similar in the upcoming three years. These price changes are shown to have a considerable negative impact on the expected cost-effectiveness of transit agency-TNC partnerships. Although such partnerships could still provide many benefits, transportation planners and policymakers should carefully examine the implications of TNC price increases resulting from changing market and policy environments.
Incorporating equity into the cost-effectiveness evaluation of new mobility: A comparative analysis
Ashour, L., & Shen, Q. (2025). Incorporating equity into the cost-effectiveness evaluation of new mobility: A comparative analysis. Transportation Research. Part D, Transport and Environment, 147, Article 104959. https://doi.org/10.1016/j.trd.2025.104959
Abstract
Public transportation in suburban areas faces challenges in providing efficient mobility. Transit Incorporating Mobility on Demand (TIMOD) services have emerged as a potential solution, yet equity considerations remain underexplored. This study incorporates equity into the cost-effectiveness evaluation of TIMOD services, analyzing two suburban areas in the Seattle metropolitan region where a TIMOD service is implemented. Using distributional cost-effectiveness analysis (DCEA), we assess the comparative costs of TIMOD, fixed-route transit, and drive-alone across different income groups and built environments. The study shows that although TIMOD services offer equity benefits for lower-income travelers, they are more equitable in high-density, low-income suburbs. In contrast, their cost-effectiveness is more limited in affluent, low-density areas. These insights highlight the importance of context-specific planning for TIMOD interventions and employ tools such as DCEA for transit agencies to prioritize the deployment of such services in areas where they can maximize social welfare and reduce transportation inequities.
Incorporating mobility-on-demand into public transit in suburban areas: A comparative cost-effectiveness evaluation
Cai, M., Ashour, L. A., Shen, Q., & Chen, C. (2025). Incorporating mobility-on-demand into public transit in suburban areas: A comparative cost-effectiveness evaluation. Transportation Research. Part D, Transport and Environment, 144, Article 104775. https://doi.org/10.1016/j.trd.2025.104775
Abstract
Transit Incorporating Mobility-on-Demand (TIMOD) represents the public–private partnerships in which transit agencies incorporate MOD services to supplement fixed-route transit. This study evaluates the cost-effectiveness of TIMOD compared to buses, driving, and ride-hailing in suburban settings. For each alternative, it estimates the marginal costs for travelers, service providers, and transportation externalities, which constitute the marginal social cost. In the study cases, TIMOD is the least cost-effective option, with marginal social cost approximately 20% higher than TNCs and over three times higher than driving. For travelers, TIMOD costs more than driving but less than buses and ride-hailing when considering time value and fare. The cost of TIMOD declines as population density increases. Suburbs with less bus services and higher income residents benefit more from TIMOD, realizing greater reductions in time costs compared to buses. Transit agencies should explore alternative ways to improve mobility for disadvantaged suburban residents by offsetting driving costs and subsidizing TNCs fares.
Keywords
Transit Incorporating Mobility-On-Demand (TIMOD); Public transit; Transportation simulation; Suburban areas; Marginal social cost of travel
Eunice Akowuah
My research interests include housing policy, affordable housing, smart cities, housing markets, real estate markets, appraisals, development, sustainability and investments. Other areas that are of interest to me include facilities management, urban and city planning, and real estate economics.
Enhancing urban building energy models with Vision Transformers: A Case study in material classification from Google street view
Liu, Y., & Abbasabadi, N. (2025). Enhancing urban building energy models with Vision Transformers: A Case study in material classification from Google street view. Energy and Buildings, 333, Article 115457. https://doi.org/10.1016/j.enbuild.2025.115457.
Abstract
The growing urbanization and increased urban energy consumption highlight the need for energy use and greenhouse gas emissions reduction strategies. Urban Building Energy Modeling (UBEM) emerged as a valuable tool for managing and optimizing energy consumption at the neighborhood and city scales to support carbon reduction goals. However, the accuracy of the UBEM is often limited by the lack of large-scale building façade material dataset. This study introduces a new approach to enhance UBEM by integrating an automatic deep learning material classification pipeline. The pipeline leverages multiple views of Google Street View Images (SVIs) to extract building façade material information, utilizing two Swin Vision Transformer (ViT) models to capture both global and local features from the SVIs. The pipeline achieved a main material classification accuracy reached 97.08%, and the sub-category accuracy reached 91.56% in a multi-class classification task. As the first study to apply a deep learning model for material classification to enhance the UBEM framework, this work was tested on the University of Washington campus, which features diverse facade materials. The model demonstrated its effectiveness by achieving an overall accuracy increase of 11.4% in year-round total operational energy simulations. The scalability of this material classification pipeline enables a more accurate and cost-effective application of UBEM at broader urban scales.
Yingjie Liu
My interest lies in urban-scale building energy modeling and carbon accounting for climate mitigation. Specifically, I am focused on how digital documentation of the built environment can automate and enhance the accuracy of current accounting methods. Moreover, I am intrigued by how these advancements enable the broader application of bottom-up accounting approaches, informing early-stage design and influencing energy policy decisions.
AI-driven control algorithm using machine learning and genetic optimization for enhancing visual comfort in adaptive façades
Tabatabaei Manesh, M., Rajaian Hoonejani, M., Ghafari Gousheh, S., Abdolmaleki, A., Nikkhah Dehnavi, A., & Shahrashoob, A. (2025). AI-driven control algorithm using machine learning and genetic optimization for enhancing visual comfort in adaptive façades. Automation in Construction, 179, Article 106474. https://doi.org/10.1016/j.autcon.2025.106474.
Abstract
Effective management of daylight and visual comfort in office spaces remains a challenge, as existing shading systems often lack adaptability to changing environmental conditions and occupant needs. This paper presents an AI-driven real-time shading control algorithm that optimizes visual comfort using machine learning-based surrogate models and evolutionary optimization. A non-conventional adaptive façade was simulated using Radiance and Ladybug Tools across nine U.S. climates. Four machine learning models were evaluated for predicting Task Illuminance (Et) and Vertical Eye Illuminance (Ev), with Extra Trees achieving the highest accuracy (R2
= 0.95). A Non-dominated Sorting Genetic Algorithm II (NSGA-II) balances glare reduction and daylight utilization by optimizing façade configurations in real time. In contrast to prior approaches constrained to fixed geometries and single-objective control, this paper introduces a generalizable multi-objective control framework. Results show that AI-driven optimization significantly improves adaptive façade performance, offering a scalable solution for intelligent daylight and comfort management.
Keywords
Smart façade control; Machine learning; Surrogate models; Visual comfort; Task illuminance; Vertical eye illuminance; Dynamic shading
A Comparative Evaluation of Polymer-Modified Rapid-Set Calcium Sulfoaluminate Concrete: Bridging the Gap Between Laboratory Shrinkage and the Field Strain Performance
Akerele, D. D., & Aguayo, F. (2025). A Comparative Evaluation of Polymer-Modified Rapid-Set Calcium Sulfoaluminate Concrete: Bridging the Gap Between Laboratory Shrinkage and the Field Strain Performance. Buildings (Basel), 15(15), 2759. https://doi.org/10.3390/buildings15152759.
Abstract
Rapid pavement repair demands materials that combine accelerated strength gains, dimensional stability, long-term durability, and sustainability. However, finding materials or formulations that offer these balances remains a critical challenge. This study systematically evaluates two polymer-modified belitic calcium sulfoaluminate (CSA) concretes—CSAP (powdered polymer) and CSA-LLP (liquid polymer admixture)—against a traditional Type III Portland cement (OPC) control under both laboratory and realistic outdoor conditions. Laboratory specimens were tested for fresh properties, early-age and later-age compressive, flexural, and splitting tensile strengths, as well as drying shrinkage according to ASTM standards. Outdoor 5 × 4 × 12-inch slabs mimicking typical jointed plain concrete panels (JPCPs), instrumented with vibrating wire strain gauges and thermocouples, recorded the strain and temperature at 5 min intervals over 16 weeks, with 24 h wet-burlap curing to replicate field practices. Laboratory findings show that CSA mixes exceeded 3200 psi of compressive strength at 4 h, but cold outdoor casting (~48 °F) delayed the early-age strength development. The CSA-LLP exhibited the lowest drying shrinkage (0.036% at 16 weeks), and outdoor CSA slabs captured the initial ettringite-driven expansion, resulting in a net expansion (+200 µε) rather than contraction. Approximately 80% of the total strain evolved within the first 48 h, driven by autogenous and plastic effects. CSA mixes generated lower peak internal temperatures and reduced thermal strain amplitudes compared to the OPC, improving dimensional stability and mitigating restraint-induced cracking. These results underscore the necessity of field validation for shrinkage compensation mechanisms and highlight the critical roles of the polymer type and curing protocol in optimizing CSA-based repairs for durable, low-carbon pavement rehabilitation.
Keywords
calcium sulfoaluminate cement (CSA); polymer-modified confrete (PMC); rapid-set concrete; early-age shrinkage; temperature-induced strain; outdoor vs. laboratory performance; sustainable concrete; field performance; mechanical properties
Office of Research FY25 Annual Report Published
The College of Built Environments Office of Research has published the FY25 annual report. The graphic summary below along with the full report are available on the CBE Intranet Office of Research website here.