About

Siddharth Bhandari is an assistant research professor in the Department of Civil, Environmental and Architectural Engineering at the University of Colorado Boulder. He is also the associate director of research at the Construction Safety Research Alliance. He earned his BS, MS, and PhD in civil engineering from the University of Colorado Boulder. His research interests include construction safety, experimental psychology, human factors engineering, and workplace mental well-being.

Research topics

• Computer Science
• Artificial Intelligence
• Computer Security
• Engineering
• Psychology
• Political Science
• Business
• Machine Learning
• Risk analysis (engineering)
• Data science
• Actuarial science
• Operations management
• Operations research
• Knowledge management
• Medicine
• Environmental health
• Economics
• Management science

Selected publications

• Enhancing construction safety training through emotion-eliciting virtual reality

  Engineering Construction & Architectural Management · 2026-03-30

  articleSenior author

  Purpose This study explores the potential of virtual reality (VR) to enhance construction safety training by eliciting critical emotional responses, particularly in novices lacking firsthand experience with hazardous scenarios. By targeting emotions like fear and distress, VR aims to improve hazard recognition and foster risk-averse behaviors, addressing gaps in traditional training methods. Design/methodology/approach The study involved 55 construction management students using a VR simulation integrated with haptic feedback to replicate accident scenarios. Emotional responses were measured through galvanic skin response (GSR) metrics, pre- and post-experience self-reported questionnaires and semi-structured interviews. Participants navigated a virtual construction site, identified hazards and experienced a simulated accident to assess emotional and behavioral impacts. Findings The VR simulation significantly increased emotional arousal, with GSR data showing a strong effect size and significant increases in distress, guilt, fear and shame. Participants reported heightened empathy, guilt and responsibility during post-VR interviews. These findings suggest that VR effectively engages users emotionally, bridging the experiential gap in traditional training by replicating hazardous scenarios with high realism and impact. Practical implications The study highlights VR's potential as a scalable, immersive training tool for eliciting emotional and physiological precursors associated with risk-averse decision-making in the construction industry. By evoking anticipatory emotions theorized to influence risk perception, VR may help prepare novices to engage more cautiously with hazardous scenarios, though the link between these precursors and actual safety behavior requires field validation. Originality/value This research provides empirical evidence of VR's capability to elicit emotional responses that influence decision-making in hazardous environments. It offers valuable insights for developing innovative, emotionally engaging safety training programs for the construction sector.

  PublisherDOI

• Breaking ground on mental health: Understanding financial insecurity and job demand in construction

  Journal of Workplace Behavioral Health · 2026-04-21

  articleCorresponding
  PublisherDOI

• Exploring the Impact of Augmented Reality on Work Performance in a Full-Scale MEP Assembly Task: Study of Industry and Novice Populations

  Journal of Construction Engineering and Management · 2025-09-17

  articleSenior author

  Building information modeling (BIM) has revolutionized the construction industry; however, field personnel still rely on traditional methods for design interpretation. Augmented reality (AR) head-mounted display devices (HMDDs) offer a promising alternative for delivering three-dimensional design information, yet their effectiveness must be validated across diverse populations with a significant sample size. This study examines the impact of AR HMDDs on mechanical, electrical, and plumbing (MEP) assembly tasks, evaluating key performance metrics: task completion time, rework rate, and error rate. Both novice and experienced participants completed assembly tasks in industrial and laboratory settings, marking the first comparative analysis of AR models with different levels of detail (LOD 300 and LOD 400) against traditional isometric paper plans. Findings indicate that the AR LOD 400 model significantly improved all performance metrics across both populations, except for the error rate among industry professionals. The AR LOD 300 model notably reduced rework rates, while traditional paper plans were the least effective. Age did not significantly impact performance, whereas higher spatial cognition enhanced novices’ efficiency. Participants acknowledged AR HMDDs, particularly the LOD 400 model, as beneficial for design comprehension; however, some also reported distractions. These insights highlight the need for user-centered AR interface design and tailored training strategies to enhance usability and efficiency. As the first study to investigate the influence of AR model LODs on construction task performance with a robust sample size, the results provide valuable guidance for optimizing AR HMD technology, training protocols, and design information delivery in the construction industry.

  PublisherDOI

• Bringing reality to virtual reality: the role of environmental richness in improving construction practitioners’ VR experience

  Construction Innovation · 2025-11-18 · 2 citations

  articleOpen access

  Purpose This study aims to investigate how environmental richness in virtual construction environments influences construction practitioners’ behavior and presence. It aims to identify elements within these environments that significantly contribute to an enhanced sense of presence, addressing the gap in understanding the relationship between environmental richness and ecological validity in virtual safety training. Design/methodology/approach A mixed-methods study involving 28 full-time construction practitioners was conducted. Participants navigated two virtual environments – a “rich” version with nonhazardous, realistic details and a “bare” version with minimal environmental richness. Data were collected through eye-tracking, positional analysis, presence questionnaires and semistructured interviews. The study used exploratory, confirmatory and explanatory analyses to evaluate behavioral impacts, statistical differences in presence scores and thematic insights into participants’ experiences. Findings Environmental richness significantly impacted participants’ sense of presence, with the rich version producing higher presence scores (p = 0.018). Qualitative data highlighted that nonhazardous elements, such as terrain details, climatic conditions and virtual co-workers, enhanced realism and immersion. Heatmaps revealed wider visual attention and movement patterns in the rich environment, indicating greater engagement. Practical implications The findings suggest that investing in nonhazardous elements, often overlooked in virtual reality (VR) development due to resource constraints, can enhance presence and realism in virtual construction environments. This can lead to more ecologically valid training experiences that better replicate real-world scenarios, ultimately improving hazard recognition and decision-making skills. Originality/value Prior VR-based safety training has often lacked ecological validity, i.e. missing realistic site context or social dynamics, which may limit behavioral realism. This study addresses that gap by comparing a richly detailed virtual construction site against a bare version, to examine how added realism impacts users’ sense of presence and safety behaviors. By providing empirical evidence on the role of environmental richness in virtual construction environments, it emphasizes the importance of nonhazardous elements in enhancing presence, offering actionable insights for designing more effective VR-based safety training solutions.

  PublisherDOI

• Comparing training delivery methods: Impact on learning outcomes and engagement among construction workers

  Safety Science · 2025-04-08 · 4 citations

  articleOpen access

  • This study compares five safety training methods using a multi-arm field experiment on construction sites. • Training methods were evaluated for their effect on both learning outcomes and worker engagement levels. • Data were collected from 591 workers using pre- and post-training surveys on safety knowledge and engagement. • Pre-recorded video improved learning at low cost; hands-on interactive lectures boosted both learning and engagement. • Teaching an energy-based hazard definition led to a 26% improvement in workers’ hazard recognition scores. Effective safety training is crucial for enhancing workers’ safety awareness and promoting safer behaviors, yet delivering such training within time and budget constraints remains a challenge. This study assessed the effectiveness of five safety training delivery methods—pre-recorded video, lecture, interactive lecture, flipped lecture (pre-recorded video followed by a hands-on activity after two weeks), and interactive lecture with hands-on activity—on engagement levels and short-term learning outcomes, namely hazard recognition skill, high-energy hazard recognition skill (hazards with the potential to cause serious injuries or fatalities), perception of high-energy hazards, and risk tolerance. A multi-arm parallel-group field experiment was conducted, with data collected through pre- and post-training surveys. The results revealed that while engagement levels increased linearly as the learner-centeredness of the training increased, improvements in hazard recognition skills followed a parabolic trend. Additionally, trainees in all groups except the interactive lecture group perceived high-energy hazards as riskier after the training but risk tolerance did not decrease in any training groups. These findings provide specific guidance on selecting optimal safety training delivery method as it relates to training objectives and resource constraints. These results may help practitioners to select the most appropriate method of safety training delivery based on their specific aims and available resources.

  PublisherDOI

• Exploring the Potential for Safety Training in VR to Generate Emotional Engagement and Situational Interest among Construction Workers

  Journal of Construction Engineering and Management · 2025-12-24

  articleOpen access

  To improve its traditional safety training methods, the construction industry has started to adopt virtual reality (VR) to enhance workers’ safety practices. Although preliminary research has shown promising results for the adoption of VR in safety training, there is a dearth of research on whether VR supports engagement [emotions and situational interest (SI)] among construction workers. Additionally, it is unclear if the potential improvements in engagement translate to learning achievements. This study sought to address this existing knowledge gap by assessing the impact of VR-based safety training (when adopted with traditional passive training and used as a tool to provide situated learning) on the conditions affecting learning—in this study, emotions and situational interest. The study used a quantitative quasi-experimental approach not only to evaluate how incorporating VR (and VR paired with haptic feedback) to a traditional passive training session affects these key conditions, but also to evaluate the effect of emotions and situational interest on the learning outcomes obtained from the experience. The study gathered data from 221 participants representing various sectors of the construction industry across the United States, including both on-site workers and construction managers. Parametric tests showed that VR-based safety training, as tested in this experiment, increased negative emotions and decreased positive emotions of participants, aligning with results from past studies. Findings indicated that the experience was effective at eliciting emotional arousal among participants. Results indicated a statistically significant increase in situational interest, including interest in the use of VR technology for construction safety trainings but did not have a statistically significant effect on maintained value-based situational interest (which is related to the perceived long-term value of the experience). Finally, results also showed that emotions and situational interest do not influence the learning outcome obtained from the experience. These results underscore the potential of VR-based safety training to significantly enhance situational interest and emotional responses; however, they also challenge the assumption that emotional engagement and situational interest directly enhance learning outcomes from a VR-based safety training module, as tested in this experiment. This research underscores VR’s potential in safety training while highlighting the need for further exploration into how these technologies influence learning efficacy.

  PublisherOA PDFDOI

• Toward Resilient Construction Supply Chains: Addressing the Truck Driver Shortage Through Strategic Interventions

  Buildings · 2025-10-31

  articleOpen access

  The construction industry is critically reliant on efficient supply chains to ensure better project management, success, and profitability. This research examined the critical and ongoing challenges within the construction supply chain, with a particular emphasis on the persistent shortage of truck drivers and its far-reaching implications for construction logistics. Utilizing a structured multi-phase approach, the research integrated a comprehensive literature review, bibliometric analysis, and an empirical case study involving commercial motor vehicle (CMV) drivers. The literature review established the current state of knowledge on transportation labor shortages. At the same time, the bibliometric analysis revealed four key thematic clusters that collectively define the primary areas influencing construction supply chain performance. The case study reinforced these findings by highlighting key factors contributing to driver shortages, including demographic shifts, challenging working conditions, regulatory barriers, and geopolitical disruptions. The paper concludes with practical implications for industry practitioners, policymakers, and supply chain managers, emphasizing the necessity of integrative operational and strategic responses to build resilient and sustainable construction supply chains and logistics systems, with a specific focus on truck driver shortages. By examining both academic literature and field-based perspectives, this research provides a comprehensive understanding of how labor shortages, particularly in transportation, can destabilize construction supply chains and identifies the most effective measures to support their foundations.

  PublisherOA PDFDOI

• Out-of-distribution detection in text using statistical techniques

  Discover Data · 2025-11-26

  articleOpen access

  Abstract Out-of-distribution data points diverge from the general profile of the data, typically defined by the specific task for which the machine learning model is being constructed. Machine learning models are more reliable when out-of-distribution detection is part of the pipeline. Out-of-domain detection models are employed not just to sieve input into a model, but also to scrutinise output from a generative model, a process known as selective generation [1]. In literature, Mahalanobis distance is widely used in anomaly detection. In this work, we leverage the relation of Mahalanobis distance to Hotelling’s T-squared and Chi-squared distribution, which is further adapted for the inference on out-of-domain detection task. Data is usually categorised into three types: a) in-domain, b) out-of-domain, and c) background data. We explore approaches: a) constructed solely with in-domain data, and b) constructed using both in-domain and background data. Our proposed approaches are background free and efficient, and shows promising results compared to existing work in the literature which employ background data. We show that Hotelling’s T-square approach improves upon the Chi-square approach.

  PublisherOA PDFDOI

• Impact of Energy-Based Safety Training on Quality of Prejob Safety Meetings and Control of Hazardous Energy in Construction: Multiple Baseline Experiment

  Journal of Construction Engineering and Management · 2025-05-12 · 1 citations

  articleOpen access

  Serious injuries and fatalities (SIFs) continue to plague the construction industry. The preponderance of evidence suggests that preventing SIFs requires the identification, assessment, and control of hazardous energy. In this study, we isolated and measured the impact of energy-based safety training on the quality of prejob safety briefs and the presence of direct controls during subsequent work. We conducted a standardized training intervention in both English and Spanish and tested it via a multiple baseline experiment on 10 construction crews working in the US and Canada. Dependent variables were measured using a prejob safety brief quality scoring rubric and the High-Energy Control Assessment (HECA) protocol. The training caused immediate and significant improvements in the quality of prejob safety briefs and a measurable but smaller effect on the HECA score. Whereas prejob safety meeting scores and effect sizes were consistent, HECA was highly variable across the work crews both before and after the training. This suggests that, although short-term impacts on the quality of safety planning may occur over a short time frame, the impacts on the control of hazardous energy may require comparatively more time and data to achieve conclusive results. Methodologically, this study demonstrates an experimental protocol for isolating and attributing the impact of a safety intervention over short periods. Such a protocol may be used in practice to draw casual inferences, and is a step toward the ability to objectively measure the return on safety investment.

  PublisherOA PDFDOI

• How does augmented reality head-mounted display impact the ability to detect safety hazards while performing piping assembly?

  International Journal of Industrial Ergonomics · 2025-05-01 · 2 citations

  article
  PublisherDOI

Frequent coauthors

• Paolo Madeddu

  NIHR Bristol Cardiovascular Biomedical Research Unit

  168 shared

• Costanza Emanueli

  Imperial College London

  140 shared

• Rajesh Katare

  University of Otago

  112 shared

• M. Meloni

  University of Sassari

  96 shared

• Claude Delcayre

  Hôpital Lariboisière

  84 shared

• Lucie Carrier

  Universität Hamburg

  84 shared

• David M. Poitz

  TU Dresden

  84 shared

• Jolanda van der Velden

  Vrije Universiteit Amsterdam

  72 shared

Education

• Ph.D., Civil Engineering

  University of Colorado Boulder

• M.S., Civil Engineering

  University of Colorado Boulder

• B.S., Civil Engineering

  University of Colorado Boulder

Awards & honors

• National Safety Council’s Rising Stars of Safety Award 2021
• ELECTRI International’s Early Career Award 2019
• Best Paper Award at the 2015 5th International/11th Construc…