Tuesday, September 24, 2024
Media Contact: Tanner Holubar | Communications Specialist | 405-744-2065 | tanner.holubar@okstate.edu
Traditional heating, ventilation and air conditioning systems regulate the environment in buildings, but do little to stop the spread of airborne pollutants that can cause great harm, especially to more vulnerable people such as children.
Researchers from the School of Engineering, Architecture and Technology are embarking on a three-year interdisciplinary project funded by the National Science Foundation, titled “AI-Enhanced Risk Assessment for Mitigating Indoor Viral Transmission in Public Schools.”
Yu Feng, PhD, associate professor in the Department of Chemical Engineering, is conducting the research in collaboration with Chenang Liu, PhD, assistant professor in the School of Industrial Engineering and Management.
Their research combines computational models that capture how airflow affects viral transport with generative artificial intelligence models that are trained using data from simulations of computational fluid dynamics and host cell dynamics in the lab to improve the design and real-time control of air treatment technologies.
“This research may help reduce infection risk by optimizing HVAC systems to reduce the spread of airborne pathogens, especially in schools, hospitals and other crowded indoor spaces,” Feng said. “Especially with the support of OUHSC’s Dr. Changjie Cai, director of the Children’s Environmental Health Center of the Southern Great Plains, this project will have a significant impact on improving public health to protect children from airborne diseases.”
Using state-of-the-art, reliable simulations, it is possible to maintain high air quality and improve energy efficiency while reducing costs. Knowledge gained from this research can help improve public health policies and building design standards.
Dr. Yu Feng
For an HVAC system to have the capacity to mitigate airborne contaminants, it requires high-efficiency filtration, increased fresh air ventilation, an increase in the proportion of outdoor air in the system, and optimized spatial distribution of air velocity, pressure, temperature, and humidity.
A well-designed ventilation system will have “smart” controls that optimize airflow in each room to efficiently remove contaminants and not recirculate air in harmful ways. Real-time monitoring, such as sensors that continuously measure air quality and pathogen levels, can also help mitigate the spread of viruses through airborne contaminants.
Artificial intelligence is essential to improving HVAC design and real-time data: AI models can leverage large amounts of data to suggest optimal HVAC configurations and operating conditions based on room layout, air quality, and infection risk.
AI can also use sensors placed throughout the ventilation system to provide real-time information about airflow within the HVAC, allowing airflow, ventilation rates, and filtration settings to be dynamically adjusted based on the most up-to-date data.
Generating an infection risk index
How airborne virus-laden droplets move through indoor environments can be simulated by combining computational fluid dynamics and host cell dynamics. CFD models predict airflow patterns, droplet transmission, and droplet deposition within indoor spaces and the human respiratory system.
It also monitors air velocity, humidity, and temperature and their effects on airborne contaminants. The HCD model predicts how a person will react to inhaling the virus, including viral replication, immune response activation, and infection progression.
“The output from the CFD-HCD simulation is a key metric for calculating an infection risk index,” says Feng. “Specifically, by assessing factors such as viral load, lung deposition and host immune response, the derived IRI can be used to evaluate the safety of different HVAC designs and classroom layouts.”
Generative AI models leverage generative adversarial networks and diffusion models to optimize HVAC designs, analyzing CFD-HCD simulations and suggesting specific configurations that minimize infection risk while remaining energy efficient.
Inspiring the next generation
There are plans to engage K-12 students through research activities including workshops and hands-on activities.One of the established outreach programs that is part of Grandparents University is called “Lungevity.”
K-12 students will learn about lung health, viral transmission and air quality and will have interactive experiences including building lung models and using virtual reality to see how lungs function and how virus-laden droplets are transported.
“To maximise the potential impact of our outreach efforts, recorded lectures and resources will be made available online to students and teachers,” Feng said.
As part of the project, graduate and undergraduate students will run simulations, develop AI models and analyze data, as well as help mentor and engage K-12 students and collaborate on educational outreach.
Truly an interdisciplinary effort
This research project is a testament to the strong collaboration between experts from OSU and OUHSC, leveraging cutting-edge AI, CFD and public health expertise to address a global challenge.
The scope of this project extends beyond schools, as it can improve sanitation anywhere there are traditional HVAC systems, contributing to the broader vision of healthier, more resilient communities.
Feng said he was grateful to have worked with Liu from IEM and Tsai from OUHSC.
“I believe there are still many ways to improve the lung health of Oklahomans, especially in rural areas,” Fenn said. “This can involve both research and education efforts, and I look forward to forging new collaborations with researchers to advance these efforts.”
You can learn more about Feng and his research here.
