Worthy, A., Ashayeri Mehdi, Marshall, J. D., & Abbasabadi Narjes. (2026). A Framework for Augmenting Simulation-Based Building Energy Models with Earth Observational Microclimate Data Using Machine Learning Predictions. Urban Science, 10(7), 341. https://doi.org/10.3390/urbansci10070341
View Publication
Abstract
Accurate urban building energy modeling (UBEM) is constrained by mismatches between standard climate inputs and actual urban microclimate conditions. This study introduces a scalable, bottom-up, framework that integrates EnergyPlus building energy modeling simulation outputs with Earth observational and geographical-based urban morphology data, which are enhanced through machine learning techniques to improve energy demand predictions in urban settings. Applied to Los Angeles (LA), California, we evaluate the representativeness of typical meteorological year (TMYx) sampling sites against actual urban environmental conditions. We find that while satellite-derived surface temperatures show reasonable alignment with average city conditions, significant discrepancies are observed in urban form metrics such as tree cover, street cover, and building density, suggesting that TMYx stations should be placed in denser urban areas. We augment EnergyPlus simulations for 19 single-family buildings, with remote sensing data using machine learning models, to generate city-wide residential energy consumption heatmaps corrected for microclimate conditions. Models capture substantial intra-urban variation, with predicted energy use differing by approximately 10% between neighborhoods. Feature importance analysis highlights land surface temperature as a key predictor, underscoring its relevance to building energy research. We also find the majority of TMY3 sampling sites to be in low-vulnerability areas, underscoring the structural mismatch that is embedded in urban form and climate. This framework offers a scalable path for integrating urban microclimate effects into energy modeling to enable more precise and equitable energy policy and planning.
Keywords
urban microclimates; urban building energy use; Earth observational data; infrastructure equity
Abbasabadi, N., Worthy, A., Zhang, Z., Zhao, Y., & Liu, Y. (2026). An AI-augmented urban building energy Modeling framework integrating physics-based simulation, machine learning, and computer vision: The CityEnerTwin UBEM module. Energy and Buildings, 369, Article 117984. https://doi.org/10.1016/j.enbuild.2026.117984
View Publication
Abstract
Urban Building Energy Modeling (UBEM) plays a critical role in evaluating urban decarbonization strategies, but its accuracy and scalability are often constrained by simplified building archetype, limited façade-level data, and the computational cost of large-scale scenario analysis. This study presents the CityEnerTwin UBEM module, an artificial intelligence (AI)-augmented, physics-based framework that integrates modular workflows for computer vision–based façade semantic enrichment, localized archetype development, predictive and surrogate machine learning (ML), and climate-informed analysis to support scalable and computationally efficient urban energy modeling. Specifically, these workflows combine validated Vision Transformer (ViT)-based façade feature extraction methods for deriving material properties and window-to-wall ratio (WWR) from street-view imagery, K-means clustering for localized archetype development, and two complementary ML modeling streams: predictive models trained on measured operational energy data and surrogate models trained on synthetic UBEM simulation data for rapid retrofit scenario evaluation. Demonstrated on the University of Washington campus, the framework reduced campus-scale simulation error relative to measured energy consumption from 27.8% to 15.8%, while image-derived WWR inputs improved agreement for representative buildings from 23% to 20%. Predictive modeling using Random Forest (RF) achieved a test R2 of 0.88 and identified occupancy, building scale, and geometric efficiency as the dominant predictors of energy demand. Surrogate modeling using an Artificial Neural Network (ANN) achieved a test R2 of 0.98 and identified roof insulation, WWR, and shading depth as the most influential retrofit parameters, enabling rapid retrofit scenario evaluation. The results demonstrate the potential of integrated physics-based and data-driven workflows to improve UBEM representation, scalability, and computational efficiency for urban decarbonization planning. As the analytical core of the broader CityEnerTwin platform, the module connects spatially indexed building data and model outputs with interactive visualization to support urban-scale energy analysis and decision making.
Keywords
Urban building energy Modeling; Physics-based simulation; Computer vision; Machine learning; Surrogate Modeling; Retrofit scenario analysis
Bourassa, S.C., Hoesli, M., Mayer, M. and Stalder, N. (2025), “Reflections on hedonic price modeling”, Journal of European Real Estate Research, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/JERER-11-2024-0087
View Publication
Abstract
Purpose
This paper provides a critical history of residential hedonic price modeling, highlighting key issues and advances. It is based on the keynote address presented by the first author at the European Real Estate Society Annual Conference in Sopot (Gdańsk), Poland, in June 2024.
Design/methodology/approach
The core of the paper is a high-level review of the methodological literature, focusing on three issues: model specification, multicollinearity and functional form. This review is framed by an early example of hedonic price modeling and a current application. These examples demonstrate key issues and advances in hedonic price modeling.
Findings
Hedonic price research has expanded dramatically with the advent of personal computing. Increased availability of data has enabled better model specification. At the same time, the development of interpretable machine learning techniques has allowed much more flexible modeling of functional form. However, multicollinearity continues to be, by definition, an intractable problem.
Originality/value
This paper presents a review of residential hedonic price modeling intended to provide researchers with a useful high-level perspective on the topic. A case study of Gdańsk illustrates an approach to producing interpretable results from machine learning estimations.
Keywords
Hedonic modeling; house prices; specification issues; multicollinearity; functional form; interpretable machine learning; R31
Dr. Carrie Sturts Dossick, Associate Dean for Research, and Professor in the department of Construction Management has been featured on the Building Innovation: The Podcast. The podcast episode is Season 2, Episode 1, and is part one of the NBIMS-US™ Series, and discusses the new module for Project BIM Requirements. Listen to the Podcast here: https://www.nibs.org/building-innovation-podcast
Kim, M., & Kim, Y.-W. (2024). Applications of blockchain for construction project procurement. Automation in Construction, 165, 105550-. https://doi.org/10.1016/j.autcon.2024.105550
View Publication
Abstract
Blockchain technology has shown potential in enhancing project performance by instilling trust in data sharing among stakeholders, thereby encouraging the stakeholders to ensure a strategic acquisition and resource management through procurement activities. However, despite the recent research efforts on blockchain in the construction sector, there is a lack of knowledge of the status quo in that barely any research investigated the synergy of blockchain and procurement by recognizing the inextricable linkage between procurement management and project delivery system. This paper conducts a systematic review of 54 articles to assess blockchain's potential in addressing issues inherent in the current organizational structures and collaborative efforts. Findings offer profound insight into the current landscape of procurement-specific blockchain research, highlighting areas needing attention. This paper identified opportunities in construction procurement by investigating the extent to which the technology is integrated into the current project management context emphasizing integration and collaboration.
Keywords
Blockchain; Procurement; Construction industry; Procurement process; Project delivery system; Literature review
Wu, L., Mohamed, E., Jafari, P., & AbouRizk, S. (2023). Machine Learning–Based Bayesian Framework for Interval Estimate of Unsafe-Event Prediction in Construction. Journal of Construction Engineering and Management, 149(11). https://doi.org/10.1061/JCEMD4.COENG-13549
View Publication
Abstract
Construction safety is a critical concern for industry and academia, and numerous models and algorithms have been developed to predict incidents or accidents to facilitate proactive decision-making. However, previous studies have been limited due to the inability to account for uncertainties because predictions are given as a single value (i.e., Yes or No) and the failure to integrate subjective judgment. To address these limitations, this research proposes a machine learning–based Bayesian framework for predicting construction incidents using interval estimates. This framework combines a state-of-the-art machine-learning algorithm with a binary Bayesian inference model to develop an incident predictor that considers a range of project characteristics and conditions. Notably, this framework also is capable of incorporating historical or subjective judgment through prior selection and outputs the unsafe event prediction as an interval of possibilities, thus accounting for various uncertainties. The efficacy of our framework was demonstrated in a real-life case study, showcasing its practical implications for proactive decision-making and risk management in the construction industry and representing a valuable contribution to the field of construction safety.
CBE researchers worked with the Charles Pankow Foundation to develop a new Building Owner Assessment Tool (BOAT). Team members included CBE Dean Renée Cheng, FAIA; Associate Dean for Research Carrie Sturts Dossick, Ph.D, P.E.; and Laura Osburn, Ph.D. Other team members included Lingzi Wu, Ph.D. Daniel Dimitrov, and Xianxiang Sean Zhao. The tool was developed in partnership with the American Institute of Architects and the Integrated Project Delivery Alliance. The Building Owner Assessment Tool (BOAT): Helping You Understand Your Culture and Its…
Research Interests: urban eco-evolutionary dynamics, urban complexity, landscape ecology, scenario planning, and nature’s contributions to people/nature-based solutions
Abdel Aziz, A. M. (2023). Statistical Analysis and Representation Models of Working-Days Liquidated Damages. Journal of Construction Engineering and Management, 149(7). https://doi.org/10.1061/JCEMD4.COENG-13330
View Publication
Abstract
Contractors tend to challenge the enforceability of liquidated damages (LDs), claiming they are unreasonable, excessive, penalty statements, or concurrently caused. States customarily assert that the LD rates are a genuine reflection of the expenses expected to be suffered when a project gets delayed due to noncompletion. While there are common practices among the states for articulating LD specifications, which generally follow the Federal Code of Regulations, there are no published studies that assist states in comparing their LD rates to those of other states so that the LD rates might be defended. Further, there are no studies that offer models that would uncover the relationship between the LD rates and the contract sizes so that the LD rates might be justified. This work addresses such gaps in the body of knowledge (BOK) in LDs. With emphasis on the working-days (WD) LD rate schedules, the objectives of this work are to characterize the LD rate schedules across the states and to model a formula(s) that would represent the relationship between the WD LD rates and the contract amounts. The data set for the work represents the LD schedules in the standard specifications of all departments of transportation in the United States. Descriptive and cluster statistical analyses were used for the LD rate characterization. For model development, several linear and nonlinear regression models were employed. The results highlighted considerable LDs variability in the smaller contract sizes and exceptional LD rates stability in the larger sizes. Despite the economic differences among the states, it is found that the LD rate is, on average, 0.02 ¢/$ for projects $20 million or above. Below that, the rate increases between 0.03 ¢/$ and 0.18 ¢/$ until the contracts reach $750,000. LD rates tend to decrease sharply with the increase in contract sizes, forming an L or reverse J shape. This pattern proved complex, and only nonlinear regression with transformed variables successfully modeled it. Credible models were obtained after satisfying the least-squares regression assumptions. The work contributes to the BOK by adding a new statistical dimension to understanding LDs and developing regression model(s) that explain the relationships between the LD rates and the contract sizes. The work should help SHAs create, evaluate, and justify their LD rates.
In the United States, flooding is a leading cause of natural disasters, with congressional budget office estimates of $54 billion in loss each year. Although both urban and rural areas are highly vulnerable to flood hazards, most natural disaster resilience studies have focused primarily on urban areas, overlooking rural communities. One such area that has been overlooked are the numerous rural communities bordering the Great Lakes. These communities face unprecedented challenges due to rising water levels, particularly since 2012, which have resulted in increased coastal flood hazard. Despite their flooding risk, they continue to lack flood hazard assessments and inundation maps, exacerbating their vulnerability. The Federal Emergency Management Agency (FEMA) commonly recommend counties to use a freely available tool—called HAZUS to develop hazard mitigation plans and enhance community resilience and adaptation. However, the usage of HAZUS for rural communities is challenging due to existing data gaps that limit the analytical potential of HAZUS in these communities. Continued use of standard datasets for HAZUS analysis by rural counties could likely leave the communities underprepared for future flood events. The proposed project’s vision is to develop methods that use remote sensing data resources and citizen engagement (crowdsourcing) to address current data gaps for improved flood hazard modeling and visualization that is scalable and transferable to rural communities.
The results of the project will expand the traditional frontiers of preparedness and resilience to natural disasters by drawing on the expertise and backgrounds of investigators working at the interface of geological engineering, civil engineering, computer science, marine engineering, urban planning, social science, and remote sensing. Specifically, the proposed research will promote intellectual discovery by i) improving our understanding of remote sensing data sources and open-source processing methods to assist rural communities in addressing the data gaps in flood hazard modeling, ii) developing sustainable geospatial visualization tools for communicating hazards to communities, iii) advancing our understanding of the utility of combining remote sensing and crowdsourcing to flood hazard delineation, iv) understanding ways to incentives the crowd for greater participation and accuracy in hazard in addressing natural disasters, and v) identifying critical community resilience indicators through crowdsourcing. These advancements will lead to prepared and resilient rural communities that can effectively mitigate hazards related to lake level rise and flooding.