Lyu, P (2025) Assessing the impact of weather conditions on safety in construction environments: Data-driven approaches for learning from accidents. PhD thesis, Arizona State University, USA.
Abstract
The impact of weather conditions on construction worker safety is a critical yet underexplored area of occupational safety and health research. This dissertation investigates the quantitative relationship between various weather conditions, extreme weather events, and construction accident risks. By using historical accident data from the Occupational Safety and Health Administration (OSHA) and meteorological records from OpenWeather and the National Weather Service (NWS), this study employs data-driven methodologies, including Bayesian Network (BN) models, matched-pair analysis, and Multinomial Logit Models (MNL), to assess accident likelihood and severity under different environmental conditions. The findings indicate that high temperature, lower humidity, and cloudy significantly increase accident probabilities, while precipitation and strong wind elevate injury severity. Extreme weather events, including heat, floods, hails, and wildfires, contribute to a heightened risk of construction accidents, particularly fall-related incidents, and heat illnesses. Further, hear-related injuries (HRIs) are found to be disproportionately severe among middle-aged, older, and male workers in high-risk industries such as construction, manufacturing, and agriculture. For example, the probability of experiencing a fatal HRI increases by 7.5% for middle-aged workers and 9.8% for older workers (relative to youth workers), while male workers face a 22.4% higher likelihood of fatal HRIs compared to female workers. A higher heat index (HI), along with incidents involving collapses, heart attacks, and fall accidents, exacerbates HRI severity. Conversely, workers who experience symptoms like dehydration, dizziness, cramps, faintness, and vomiting show a lower likelihood of fatal outcomes. This research underscores the urgent need for integrating real-time weather data with historical accident trends to enhance risk assessment, work schedule optimization, and site-specific safety planning. Additionally, it highlights the importance of targeted safety protocols and training strategies tailored to demographic and industry-specific vulnerabilities. The insights from this research contribute to the advancement of occupational safety frameworks in the face of increasing climate variability, supporting the development of predictive safety interventions and improved resource allocation strategies for construction sites and other high-risk work environments.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Song, S |
| Uncontrolled Keywords: | construction worker; injury; learning; manufacturing; optimization; precipitation; probability; resource allocation; risk assessment; safety; training; weather |
| Index terms: | resource allocation, bayesian network, illness, occupational safety and health, work environment, risk assessment, variability, high temperature, humidity, occupational safety, extreme weather event, heart, dissertation, construction worker, injury, construction site, strategy, face, construction accident, vulnerability, methodology, multinomial, environmental conditions, precipitation, weather |
| Subjects: | climate science, practitioner, research dissemination and communication, environmental science, psychology, financial risk, medical science and clinical practice, research methods, environmental hazards, air quality, resource management, work location, management, thermal systems, statistical analysis, occupational health and safety management, health conditions and diseases, probabilistic model |
| Topics: | Sustainability, Health and Safety, Roles and Professions, Research Practice, Cost Management, Business Strategy, Organizational Design, Site Management, Digital Applications |
| Descriptive scope: | 4 PCTA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here