Ling, C., Chen, P., Chu, Y.-C., & Shen, Q. (2026). Not all teleworkers reduce travel: An intensity-dependent behavioral framework with explainable machine learning. Transport Policy, 187, Article 104267. https://doi.org/10.1016/j.tranpol.2026.104267
View Publication
Abstract
Previous studies have yielded mixed findings on the relationship between teleworking and travel, possibly due to overlooking teleworking intensity and its evolving impacts. This study examines how teleworking is associated with overall vehicle miles traveled (VMT) and vehicle travel time (VTT) across a spectrum of intensities, measured by the number of remote-work days per week. Using travel survey data in the Puget Sound Region, Washington, we estimate four explainable machine learning models (XGBoost with SHAP) that incorporate behavioral, socio-demographic, and built-environmental characteristics. Results find an intensity-dependent relationship among typical workers. Low-intensity teleworking (1 day/week) is associated with increased travel both pre- and post-pandemic, while moderate teleworking (2 days/week) shows near-neutral or marginally positive associations. In contrast, regular teleworking (3–5 days/week) is correlated with reduced travel. In 2023, teleworking intensity ranks among the top six contributors, accounting for 6.84% and 4.08% of model explainability for VMT and VTT, respectively, higher than in 2017. The reductions scale with intensity. Holding other factors constant, high-frequency teleworkers (3 days/week) in 2023 accrued approximately 10 fewer miles and 3 fewer minutes per five-day workweek than fully on-site workers, whereas full teleworkers (5 days/week) saved 19 fewer miles and 23 fewer minutes. These impacts are concentrated among high-frequency teleworkers with longer commute distances, while the effects are mixed among shorter-distance commuters. Teleworking can moderate impacts of other factors, such as commute distance, income, and population density. These findings help reconcile prior inconsistencies, showing that teleworking's role depends on intensity rather than simple adoption.
Research Interests: Machine learning, work from home, urban economics, transportation policy, urban data science, economic inequality
Professor Carrie Sturts Dossick (Construction Management) is on the project team that has created a digital twin model of the I-90 bridge in Seattle. Monitoring this bridge, which now includes the world’s first light rail crossing on a floating bridge, is an innovative and collaborative project evolving in real-time. Read the full feature story on the Civil & Environmental Engineering website here.
Assistant Professor of Architecture Narjes Abbasabadi has been awarded one of 36 seed grants from AI@UW. Narjes’ project entitled “SEED-AI 2026: DesignAI – An AI-Augmented Framework for Design Learning” was selected for funding alongside a range of other projects. The project summary is included below. More information is available here. Artificial intelligence (AI) offers powerful new ways to support design reasoning, exploration, and data-informed decision-making, yet these capabilities remain largely untapped in architectural education. This project addresses a critical dual-literacy…
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.
View Publication
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.
Abbasabadi, N., & Ashayeri, M. (2024). Machine Learning in Urban Building Energy Modeling. In Abbasabadi, N., & Ashayeri, M. (Eds.), Artificial Intelligence in Performance-Driven Design : Theories, Methods, and Tools: Theories, Methods, and Tools. Wiley-Blackwell.
View Publication
Abstract
Urban building energy modeling (UBEM) plays a pivotal role in effective urban energy management and the holistic understanding of citywide energy performance. This book chapter delves into the integration of machine learning (ML) in UBEM, covering applications such as predictive energy consumption modeling and optimization, and providing insights into how ML techniques enhance modeling accuracy and efficiency. It explores current UBEM methods, highlighting their strengths and limitations, and discusses the opportunities presented by ML for advancing UBEM approaches. The chapter also introduces a hybrid UBEM approach that combines data-driven and physics-based simulations to enhance modeling accuracy and reduce uncertainties in capturing urban energy use. This fusion of ML and UBEM offers promising prospects for improving urban energy management practices.
Abbasabadi, N., & Ashayeri, M. (2024). Understanding Social Dynamics in Urban Building and Transportation Energy Behavior. In Abbasabadi, N., & Ashayeri, M. (Eds.), Artificial Intelligence in Performance-Driven Design : Theories, Methods, and Tools: Theories, Methods, and Tools. Wiley-Blackwell.
View Publication
Abstract
This chapter explores the impact of human dynamics, social determinants of public health ( SDPH ), mobility, and occupancy on urban energy use behavior, a topic previously overlooked due to individual buildings or transportation models. A novel, data-driven urban energy model is developed using Artificial Neural Networks ( ANN ), augmented by Garson, Lek's profile and Partial dependence Plot ( PDP ) methods, to holistically evaluate urban energy behavior across Chicago communities, integrating both building and transportation energy use. Utilizing diverse public datasets from the city of Chicago, and validated through cross-validation, the model assesses human dynamics in development of an integrated urban energy modeling. The findings reveal a significant association between SDPH status, mobility, occupancy, and urban energy behavior with household income being a major contributor post accounting for urban spatial patterns and building physical attributes. The study suggests that meeting decarbonization targets in cities requires a broader evaluation encompassing various urban energy determinants. It advocates for emerging technologies and detailed analytical scrutiny, urging researchers and policymakers towards a comprehensive understanding of urban energy use behaviors.
Abbasabadi, N., & Ashayeri, M. (2024). A Hybrid Physics-Based Machine Learning Approach for Integrated Energy and Exposure Modeling. In Abbasabadi, N., & Ashayeri, M. (Eds.), Artificial Intelligence in Performance-Driven Design : Theories, Methods, and Tools: Theories, Methods, and Tools. Wiley-Blackwell.
View Publication
Abstract
This chapter introduces a hybrid framework that brings machine learning (ML) and urban big data analytics into integrated modeling of indoor air quality, building operational energy, and ambient airflow dynamics. This holistic approach allows for more effective and accurate simulation results for the design of built environments that prioritize both climate and health considerations. To validate this framework, we undertook a pilot study on a naturally ventilated, large-size office building prototype, as provided by the U.S. Department of Energy. This prototype was hypothetically placed in a densely populated area of Downtown Chicago, IL. For our computations, we employed tools, including EnergyPlus, CONTAM, CFD0, and artificial neural networks (ANNs). The findings highlighted the proposed framework's robust ability to evaluate the effects of building energy efficiency strategies, such as natural ventilation. Additionally, it took into account the indoor concentration of outdoor pollution resulting from the implementation of such strategies. Employing the hybrid approach, we achieved an accuracy characterized by an R -squared value of up to 0.96, facilitated by ANNs. Compared to conventional physics-based simulation methods, the hybrid approach further accelerated the simulation process by up to 200 times. This novel framework offers valuable insights to architects and engineers during early-stage design decisions, enabling them to harmonize occupant health considerations with energy conservation objectives, thereby placing health and well-being at the forefront of decarbonization goals.
Ashayeri, M., Piri, S., & Abbasabadi, N. (2024). Exploring U.S. Occupant Perception Toward Indoor Air Quality Via Social Media and NLP Analysis. Journal of Environmental Science and Public Health, 8(2). https://doi.org/10.26502/jesph.96120205.
View Publication
Abstract
The global implementation of stay-at-home mandates altered people's activities within the built environment, prompting a slowdown in the spread of covid viruses. Nevertheless, this period shed light on previously unforeseen challenges in achieving "better" indoor air quality (IAQ) within buildings, necessitating a focus on building health resilience for future scenarios. This study aims to evaluate occupants' feedback on the impact of stay-at-home measures on IAQ perception in buildings across the U.S. during the first year of the pandemic (2020) and compare it with the baseline from the previous year (2019) nationwide to assess the changes and identify potential areas for IAQ management strategies. Geo-tagged textual data from X (formerly known as Twitter) platform were collected and analyzed using Natural Language Processing (NLP) based on time series sentiment analysis techniques to compute the feedback. Findings indicate that occupants’ negative feedback on IAQ increased during 2020 compared to the baseline. It was also found that public perception of IAQ in 2020 was notably less favorable, potentially due to deteriorating conditions inside homes as people spent more time indoors. The study underscores the potential of NLP in capturing occupant perception, contributing to data-driven studies that can inform design, engineering, and policy-making for sustainable future.
Keywords
Indoor Air Quality; Occupant Perception; COVID Stay-athome; Natural Language Processing (NLP); Time Series Sentiment Analysis
Worthy, A., Ashayeri, M., Marshall, J., & Abbasabadi, N. (2025). Bridging the simulation-to-reality gap: A comprehensive review of microclimate integration in urban building energy modeling (UBEM). Energy and Buildings, 331, Article 115392. https://doi.org/10.1016/j.enbuild.2025.115392.
View Publication
Abstract
Buildings are significant contributors to global energy consumption, necessitating urgent action to reduce energy use and associated emissions. Urban Building Energy Modeling (UBEM) is a critical tool that provides essential insights into citywide building energy dynamics though generating quantitative energy data and enabling holistic analysis and optimization of energy systems. However, current UBEM methodologies and tools are constrained by their reliance on non-urban-specific and aggregated climate data inputs, leading to discrepancies between modeled and actual energy expenditures. This article presents a comprehensive review of the datasets, tools, methodologies, and novel case studies deployed to integrate microclimates into UBEMs, aiming to bridge the modeling gap and to address the uncertainties due to the absence of real-world microclimate data in the models. It expands beyond conventional methods by elaborating on substitutional observational-based and simulation-based datasets, addressing their spatial and temporal tradeoffs. The review highlights that while remote sensing technologies are extensively utilized for building geometric data UBEM inputs, there remains an underexplored potential in reanalysis and observational-based products for environmental data; specifically, for the inclusion of parameters that are conventionally not included in UBEM analysis such as tree canopy coverage and land surface temperature. Furthermore, adopting a hybrid methodology, which combines observational and simulation-based datasets, may be a promising approach for more accurately representing microclimate conditions in UBEMs; as this process would ensure more representative climate parameter inputs and ground-truthing, while effectively managing computational demands across extensive temporal and spatial simulations. This could be achieved through integrating local earth observation datasets with computational fluid dynamics (CFD) tools or by merging local earth observational data with simulation-based reanalysis products and coupling these weather inputs with simulation-based building energy management models. Finally, this review underscores the importance of validating UBEMs with local microclimate weather data to ensure that model results are actionable, reliable, and accurate.