About

Professor Baabak Ashuri is an Executive Director of the Professional Master’s in Occupational Safety and Health (PMOSH), a Professor of Civil and Environmental Engineering, and a Professor of Building Construction at Georgia Tech. He is also a Fellow of the Brook Byers Institute for Sustainable Systems (BBISS). His research has advanced theoretical foundations and applications of data analytics, economic decision analysis, and quantitative methods for infrastructure systems and construction engineering and management. His work enables other researchers to enhance infrastructure operations performance in areas such as artificial intelligence (AI), design automation, alternative contracting methods, infrastructure finance, public-private partnerships (P3), and energy technology investments. Dr. Ashuri has a prolific publication record with over 242 publications, including journal articles, conference papers, reports, and book chapters. He has secured over $17 million in research funding from various agencies and organizations, including NSF, FHWA, DOE, and several state transportation departments. His contributions have been recognized through numerous awards, such as the Thomas Fitch Rowland paper award from ASCE, the AASHTO High Value Research “Sweet Sixteen” Award, and the DBIA Distinguished Leadership award. He has served in leadership roles within professional organizations, including chairing the ASCE Construction Research Council and serving on the ASCE Construction Institute Board of Governors. Currently, he serves as the Southern Region Director of the USDOT Build America Center, leading innovative research on financing, funding, and project delivery solutions for infrastructure projects.

Research topics

• Engineering
• Machine Learning
• Computer Science
• Business
• Geography
• Mathematics
• Medicine
• Environmental science
• Architectural engineering
• Civil engineering
• Operations research
• Risk analysis (engineering)
• Economics
• Operations management
• Econometrics
• Environmental health
• Transport engineering

Selected publications

• Explainable AI-driven expert system for impact profiling of contract modifications in construction projects

  Expert Systems with Applications · 2026-03-12

  articleOpen accessSenior author

  Change orders, defined as formal contract modifications, frequently disrupt project performance, yet predictive approaches to assess their impacts are still limited and insufficiently explainable for practical use in construction. This study introduces an explainable artificial intelligence (XAI)-based framework to profile the impact of change order-related disruptions, aiming to provide both accurate predictions and interpretable insights into associated risks. Utilizing a comprehensive dataset from highway construction projects, including project-specific variables, change order characteristics, and a macroeconomic indicator, the study develops four predictive models: two classification models to determine whether a change order causes delays or cost overruns, and two regression models to estimate the severity of these impacts. An XAI technique is then applied to identify key contributing factors and construct an interpretable impact profiling framework. Three principal findings emerge from this study. First, tree-based ensemble learning models delivered strong predictive capabilities in classifying and quantifying the impacts of change orders on schedule and cost. Second, XAI interpretation identified critical factors influencing change order-related disruptions and uncovered their value-dependent impact patterns, including monotonic and non-monotonic forms. Third, the proposed impact profiling framework, presented through a visual representation, offers dual-perspective insights by capturing both the overall importance of each feature and the value-dependent effects of features on disruption outcomes, while jointly presenting schedule- and cost-related impacts in an integrated, interpretable view. By combining predictive performance with interpretability, the proposed framework advances expert systems for intelligent and transparent decision support in construction, helping stakeholders manage change order risks and ensure resilient project delivery.

  PublisherDOI

• Data integration and machine learning applications for improved text classification and performance benchmarking in small buildings

  Journal of Facilities Management · 2026-03-20

  article

  Purpose This study aims to enhance facility management (FM) in small buildings by integrating diverse computerized maintenance management system (CMMS) data sets and applying machine learning (ML) to improve text classification for maintenance work orders, while benchmarking single-building performance. Design/methodology/approach Two maintenance data sets, one from a single office building (2,596 work orders) and another from public campus facilities (117,173 work orders), were integrated using feature engineering, natural language processing (NLP) and a support vector machine (SVM) classifier to categorize mechanical, electrical and plumbing (MEP) issues. Model performance was validated through cross-validation and benchmark analysis of facility conditions. Findings Integrating the campus data set with the office data set improved prediction performance, achieving 85% accuracy and an 85% F1 score, with a 19% higher accuracy and 20% higher F1 score for plumbing classifications. Benchmark analysis against campus facilities enabled diagnosing performance gaps in the office building, supporting data-driven decisions. Practical implications The framework enables facility managers to automate data management, prioritize maintenance tasks and make cost-effective retrofitting decisions, enhancing efficiency in small buildings. Originality/value Prior research has overlooked small data sets from single or small-to-medium-sized buildings due to data scarcity. This study offers a novel framework for integrating large, open-source CMMS data sets with small data sets, advancing automated FM in resource-constrained settings.

  PublisherDOI

• Exploring Dispute Resolution Mechanisms in Large-Scale Design-Build Transportation Infrastructure Projects in the U.S.

  2025-07-31

  articleOpen accessSenior author
  PublisherOA PDFDOI

• Preliminary Cost Estimation of Pavement Maintenance Projects through Machine Learning: Emphasis on Trees Algorithms

  Journal of Management in Engineering · 2025-05-13 · 3 citations

  articleSenior author

  Accurate cost estimation is crucial for developing cost-effective pavement maintenance plans, but it remains challenging, particularly during the preliminary stage due to limited project information. The objective of this research is to create a cost forecasting model specifically for pavement maintenance projects at the initial stage. The study employed data preprocessing and feature selection methods to apply trees-based algorithms, including extreme gradient boosting random forest, and extra trees. Data from the Georgia DOT (GDOT) from 2017 to 2021, encompassing variables related to bidding, assets, and projects, were processed and fed into the chosen machine learning algorithms. Model performances were assessed and compared using key metrics to identify the optimal combination of predictive model and feature selection method that achieves a reliable preliminary cost estimation at the initial stages of the plan development process. The extra trees regression with SelectFromModel feature selection demonstrated superior performance, achieving a mean absolute percentage error of 13.60% and a coefficient of determination of 91.68%. The results underscore the applicability of the extra trees algorithm in cost forecasting through the following aspects: (1) the model is suitable for the preliminary stage when only limited features are available; (2) the model provides consistent prediction results despite the lack of extensive or high-quality data; and (3) the model is tailored for maintenance projects by integrating the asset characteristics into the model. The findings contribute to the body of knowledge through (1) identifying the significant features for determining preliminary cost estimates of pavement maintenance projects; and (2) developing a reasonably accurate model for cost estimating in the initial stages of plan development process. It is anticipated that the outcome of this research will provide transportation agencies with a practical approach of integrating machine learning into their current practices of preliminary cost estimation, ultimately utilizing the public fund more efficiently.

  PublisherDOI

• Price Adjustment Clauses in Highway Construction: State of the Practice

  Journal of Legal Affairs and Dispute Resolution in Engineering and Construction · 2025-12-31

  articleSenior author

  Material price volatility creates uncertainty for highway construction projects. This uncertainty complicates bid preparation because suppliers may be unable to guarantee fixed material prices for the project duration. In response, contractors often include risk premiums, leading to price speculation and inflated bid prices. These embedded contingencies may cause transportation agencies to overpay under fixed-price contracts. To address these risks, state DOTs implement material price adjustment clauses (PACs) in certain highway construction contracts. While PACs are commonly applied to construction materials such as fuel, asphalt, steel, and cement, their implementation varies across several decision factors—including eligible bid items, trigger thresholds, opt-in/opt-out provisions, caps, and more. The growing interest in PACs, along with these variations, underscores the need for a review of current practices to identify the key elements shaping their use. This study reviews PAC implementation across 50 state DOTs, focusing on variations in PAC eligibility requirements, contractual conditions, triggering events, and calculation process. Data were collected from publicly available specifications, verified through direct communication with state DOT construction-related representatives, and analyzed using content analysis. Results show that 96% of state DOTs implement at least one type of material price adjustment (including pilot implementation), with fuel (84%) and asphalt (80%) being the most common, followed by steel (36%) and cement (6%). Most PACs require a 5% trigger value to activate price adjustment and use an indexed material usage per unit method for calculation. These findings offer a national reference point for evaluating the current practices and considering potential improvements to PAC implementation strategies.

  PublisherDOI

• Framework for Building Energy Management: Seasonal Benchmarks for Optimizing Thermal Comfort

  CIB Conferences · 2025-06-19

  articleOpen accessSenior author

  Given the critical role of indoor thermal comfort in occupants’ well-being and productivity, this study conducted preliminary research to develop a framework for energy management strategies that emphasize thermal comfort and seasonal variations in energy consumption from heating, ventilation, and air conditioning (HVAC) systems. Using a kindergarten facility in South Korea as a case study, the research collected real-time data on indoor thermal conditions and energy usage over one year through an IoT-based sensor network. K-Means clustering was employed to identify distinct energy consumption patterns. The main findings are as follows: First, the cluster analysis identified three significant patterns corresponding to seasonal variations—Cluster 1 representing summer, Cluster 2 representing winter, and Cluster 3 representing the transitional periods of spring and fall. Second, tailored energy benchmark values were established for each cluster, ensuring alignment with seasonal demand while maintaining optimal thermal comfort for occupants. The analysis also revealed the gap between benchmark values and current energy usage, highlighting the significant potential for energy savings. This study demonstrates the feasibility of achieving energy savings in HVAC systems without compromising occupants’ thermal comfort. By offering a scalable framework adaptable to various building types, this research lays the foundation for efficient energy management practices that can enhance occupants’ thermal comfort and reduce energy consumption.

  PublisherOA PDFDOI

• Empirical Assessment of Variability in Project Effectiveness and Change Orders across Project Delivery Methods

  Journal of Construction Engineering and Management · 2025-08-26 · 1 citations

  articleSenior author

  This study presents an empirical evaluation of variability in project outcomes and change orders, segmented by reason types and project delivery methods—design-build procured by best-value (D-B/BV), design-build procured by lowest bid (D-B/LB), and design-bid-build procured by lowest bid (D-B-B/LB). Data from 67 completed highway construction projects, encompassing 1,155 change orders, were analyzed using statistical tests and metrics assessing project effectiveness and change orders. Key findings include: (1) D-B/BV and D-B/LB outperformed the traditional D-B-B approach, with lower schedule and cost growth, higher intensity, and statistically lower award growth and estimate-to-final cost growth. D-B projects also exhibited a statistically significant reduction in change order frequency per project, pointing to better efficiency; (2) a breakdown of change order reasons showed that Modification by construction personnel was a common issue across all delivery methods. D-B-B/LB projects were particularly prone to frequent issues such as Design oversight, while D-B projects faced persistent challenges like Deleting/adding items. Notably, frequency did not always align with average impact. One example is Modification by construction personnel, which occurred less often in D-B/LB but led to the highest average schedule and cost effects, followed by D-B/BV and D-B-B/LB, reversing the frequency patterns; and (3) total impact analysis confirmed that certain reason types such as Modification by construction personnel were major contributors to overall project schedule and cost growth. These findings contribute to project management in transportation construction by highlighting performance patterns and key risks across delivery methods, helping decision-makers improve planning, control, and overall project efficiency. Future research can build on this work using multistate data sets and broader comparisons to explore regional and contractual influences and uncover causal links between delivery methods and outcome variability.

  PublisherDOI

• Machine Learning–Enhanced Recurrent Event Modeling for Change Order Recurrence in Highway Construction

  Journal of Management in Engineering · 2025-05-29 · 4 citations

  articleSenior author

  Change orders are a persistent challenge in construction projects, often resulting in substantial schedule delays and budget overruns. This study examined the recurrence of change orders by analyzing 1,182 change orders across 68 highway construction projects. The objectives of the research were threefold: (1) to identify key factors influencing change order recurrence; (2) to assess how recurrence patterns evolve throughout the project lifecycle; and (3) to evaluate their impact on project outcomes at different stages. A hybrid analytical approach integrating recurrent event modeling and machine learning (ML), along with statistical tests, was utilized to achieve these goals. The findings highlight significant predictors of change order recurrence, including time-dependent factors (e.g., original contract amount), time-independent factors (e.g., change in contract duration), and an ML-derived risk score. This study finds that larger-scale projects, the low-bid-procured design-bid-build delivery method, higher contingency levels, minor contract duration extensions, and Fall-season change orders are linked to increased recurrence, particularly in the early stage of a project. In contrast, as the project progresses, the effects of recurrent change orders on schedules and costs become more pronounced. Based on these insights, this study proposed phase-specific and cross-phase strategies to mitigate the risks associated with recurrent change orders. Through advanced analytical techniques, this research contributes to the body of knowledge in risk management and project planning, offering a robust framework for understanding change order recurrence.

  PublisherDOI

• TOWARD A DEEPER UNDERSTANDING OF CHANGE ORDERS IN HIGHWAY CONSTRUCTION: A DATA-DRIVEN EMPIRICAL APPROACH

  Computing in construction · 2025-07-14

  articleOpen accessSenior author
  PublisherOA PDFDOI

• Using Shapley Additive Explanations to Explore Features Affecting Expenditure Cash Flow Patterns

  2025-07-31

  articleOpen accessSenior author

  State highway agencies face critical challenges in maintaining accurate expenditure curves for highway projects due to the complex interaction of various factors at both the project and program levels, including political, economic, and project-specific conditions.Inaccurate expenditure curves often lead to cost overruns and project delays, resulting in budget constraints and inappropriate resource allocation for other projects.Thus, understanding the expenditure patterns of highway projects is crucial for effectively managing and forecasting expenditures, meeting funding obligations, reducing financial burdens, and streamlining the delivery of highway construction projects.Therefore, this study aims to reveal and analyze the patterns of expenditure curves in highway projects, identifying key factors that influence these patterns.To achieve this goal, advanced machine learning algorithms, K-means Clustering, Random Forest classification and feature importance, and SHapley Additive exPlanations (SHAP), are utilized to categorize the cash flow patterns of construction projects, to enhance the accruacy of cash flow forecasting, and to illustrate the impact of individual features on the predictions.This study examined 554 finished projects in Georgia, spanning from 2012 to 2018.The findings of this research suggest that project length, owner estimate, contract bid amount, total value of projects managed by prime contractors, bid price of pavement, bases and subbases, and incidental pay items, and number of bid items are significant features shaping expenditure pattern of transportation projects.Moreover, effects of significant feature are identified by evaluating SHAP values.This research contributes to producing more precise cash flow expenditure estimates for transportation projects, enhancing financial management strategies.

  PublisherOA PDFDOI

Recent grants

• Valuation of Investments in Building Energy Improvements under Uncertainties

  NSF · $250k · 2013–2017

• RAPID/Collaborative Research: An Empirical Investigation of Risk Preferences of Transportation Construction Workforce Managers under COVID-19 Pandemic Uncertainties

  NSF · $61k · 2020–2023

Frequent coauthors

• Minsoo Baek

  Kennesaw State University

  40 shared

• Mohsen Shahandashti

  The University of Texas at Arlington

  35 shared

• Mingshu Li

  23 shared

• Yunping Liang

  University of Nebraska–Lincoln

  20 shared

• Frederick Chung

  Georgia Institute of Technology

  19 shared

• Jeongyoon Oh

  18 shared

• Ali Touran

  Georgia Institute of Technology

  18 shared

• Tyler Clark

  Northeastern University

  16 shared

Labs

• Smart Built Environment Eco-System (Smart Bees) LabPI

Awards & honors

• Thomas Fitch Rowland paper award (ASCE)
• AASHTO High Value Research “Sweet Sixteen” Award
• Design-Build Institute of America (DBIA) Distinguished Leade…