Fast prediction of infection risk using computational fluid dynamics and machine learning
Open Access
- Author:
- Lee, Hyeonjun
- Graduate Program:
- Architectural Engineering (MS)
- Degree:
- Master of Science
- Document Type:
- Master Thesis
- Date of Defense:
- November 15, 2023
- Committee Members:
- Donghyun Rim, Thesis Advisor/Co-Advisor
Wangda Zuo, Committee Member
James Freihaut, Program Head/Chair
William P Bahnfleth, Committee Member - Keywords:
- Infection risk
Computational Fluid Dynamics
Machine learning - Abstract:
- This study offers an exclusive analysis of airborne transmission risks in classroom environments, employing Computational Fluid Dynamics (CFD) simulations to explore critical factors such as ventilation strategies, air change rates, occupant arrangements, source locations, and particle sizes. Through 224 generated simulation cases, this research also incorporates data-driven supervised learning methods—specifically, Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN)—for rapid airborne infection risk prediction. Key findings reveal that displacement ventilation decreases infection risk by 49%-77% in comparison to mixing ventilation. Moreover, the conventional Wells-Riley model was identified as lacking in its ability to accurately predict spatial infection risks. The study further challenges the universally beneficial role of higher air change rates, revealing an increased risk of up to 103% for occupants seated in the back rows of a classroom when air change rates were elevated. The research also suggests that relying solely on physical distancing is insufficient in specific settings and emphasizes the need to consider other factors like airflow patterns. Lastly, while CNN-based spatial models showed limitations in accurately depicting particle distribution and infection risk, the introduction of a temporal dimension in a Semi-Temporospatial model demonstrated improved performance, indicating avenues for future research. The results of this study can be used to inform HVAC system design and operation strategies to reduce the risk of infection transmission in indoor environments.