Does polluted air dampen your mood?

Following smoke exposure and poor air quality during the 2023 Canadian wildfires, bird singing and chirping patterns were negatively affected, according to a recent article in Biological Conservation. So if our feathered friends’ behaviors are affected by air quality, how is it affecting us?

University of Michigan-Dearborn faculty in the social sciences and in computer science worked together to explore answers to this question, conducting a study during the fall semester that examined air quality, human wellbeing and the effect poor air quality has on happiness.

“We want people to feel happy. We want people to be productive so they can accomplish their goals and contribute in a way they find to be meaningful. Air quality is extremely important in that,” says Professor of Economics Natalia Czap, who notes that emotional wellbeing influences behavior. Happiness and productivity are linked — human productivity increases 13% when people are happy.

“Air Quality and Human Wellbeing: Assessing Emotional Impact of Lower Air Quality Using Autonomous Artificial Intelligence-Based Distributed Sensing Systems” — a UM-Dearborn study on which Czap is the principal investigator — resulted in two new outcomes: Strengthening the research connection between air quality and mood, while also developing an algorithm that resulted in high participant engagement with self-reporting studies.

The research was funded by a U-M Bold Challenges Boost grant. Applications for the 2026 Boost grant cycle are open now through May 15.

More than 120 participants took part in the air quality and wellbeing study during the fall semester. They used portable Atmotube Pro air quality sensors and tracked their levels of happiness four times a day for three weeks. To get optimal research insight, Natalia Czap and her long-term collaborator Associate Professor of Economics Hans Czap connected with Assistant Professor of Computer and Information Science Zheng Song and Professor of Computer and Information Science Qiang Zhu to develop a data collection system.

“All researchers want to have high-quality data. But it can be challenging to motivate participants because they have other things to focus on in daily life,” Natalia Czap says. “While trying to establish a connection between the air quality and the way participants were feeling using ecological momentary assessment, we expected a response rate of about 75% based on our research of the literature. We far exceeded that.” Ecological momentary assessment is a research method that captures real-time data on behaviors and moods within a participant's natural environment using smartphones or wearable devices.

The average response rate for most participants during the study was above 90%. A high response rate is especially important for this study because the team looked at air quality and its impact at the individual level during the three-week period. Previously published studies measured the impact on an aggregate level — meaning for a city or region — but the research team wanted to look closer. For example: Are two people in the same city, but in different neighborhoods, affected differently? Does it matter how close you are to a factory? Are you in a better situation if your neighborhood has many trees?

Song and Zhu worked with computer science graduate students to customize one of their newly developed explore and exploit, or E&E, algorithms for the project. Czap says it’s important to note that exploit is meant in a scientific machine-learning way and not how the word is used in everyday conversations.

“Think of it like choosing a place to eat. Explore is like trying new restaurants to see which one is best. Exploit means you are going to your favorite restaurant because you see it as the best one,” says graduate student Shashank Chauhan, who is earning a Master of Science in artificial intelligence and plans to pursue a doctoral degree. “Based on participant behavior, the E&E algorithm helps us learn the best time to prompt people to enter their data. That is better for the people who are in the study because it is asking for feedback and more convenient times. It’s also better for research because you have more active participants.”

In the study, each research volunteer received a text message four times a day — morning, early afternoon, late afternoon and evening — through a UM-Dearborn-created smart survey system, a cloud-based meeting ground where surveying and GIS join forces. The survey prompted them to subjectively answer questions related to their wellbeing and how sunny it is outside. Accounting for sunshine is important because it is a powerful determinant of a person’s mood all on its own. The responses to the questions were combined with the objective data collected from the air quality monitors users carried with them.

During the first week, the SMS messages were sent to everyone at similar time intervals with randomly selected times. After that first week, the E&E algorithm began detecting patterns in individual response times and tailored future text prompts to seemingly more opportune times for some of the participants.

“If a morning SMS was sent and it took a user a very long time to respond during that first week, maybe they are not a morning person. The E&E algorithm detects this. We kept learning to find better times for each person from the previous week’s response times,” Song says. “The E&E algorithm helped us have high quality observations from the collection of the user’s objective and subjective data. We are studying the methodology and we are happy that, according to our preliminary data analysis, it works.” The prompts were also tied to air quality numbers on each person’s air quality sensor. For example, if someone was in a very low air quality environment, an SMS would be sent. There’s also a gamification component— an activity leaderboard — to further encourage participation, tested by the team, thanks to a suggestion by Hans Czap.

To review the effectiveness of the E&E algorithm and the gamification leaderboard, not all study participants had the E&E algorithm or gamification applied. Participants were divided into four groups during the study: A control group that continued to get random messages with no gamification, a group that had the algorithm applied and no gamification, a group that had the gamification, and no algorithm and a group that had both. The team published an Institute of Electrical and Electronics Engineers conference paper about their data collection system in 2025. 

The UM-Dearborn researchers began analyzing data in January. The research team noted higher response rates when there were interventions like the algorithm and/or gamification versus the control. Initial results also show a negative correlation between air quality and wellbeing, with lower happiness linked to higher levels of PM2.5, which are small inhalable particles that come from sources like vehicle exhaust, factories and wildfires. 

While the interdisciplinary project’s preliminary results are not a complete surprise, they highlight the importance of addressing air quality to help create change. Natalia Czap says adding their findings to the existing literature showing negative effects on humans provides further evidence for interventions that help improve public health and cognitive performance. “Let’s say there is a high-stakes test and the air quality near you is poor. If you know how you and people around you are likely to be affected, you might wait and do the test on another day,” she says. “Even when something seems obvious because of anecdotal evidence, that isn’t enough. You need data — and high-quality data — to help create policies.” 

The researchers will continue to analyze the data for more insights. But there is something they do know for certain — they appreciated working in an interdisciplinary collaboration, which was encouraged through the U-M Boost grant. 

“We are studying something completely different, but I’ve learned that the underlying science is the same. I’ve been very impressed to learn about the work being done in a field that is completely outside of my own,” says Song, who approaches research from an intelligent systems perspective. “I now better understand how putting people together from different backgrounds creates a dynamic joint effort that expands knowledge. That is what we are here to do — we are all working toward new discoveries.”

Research team members also include Economics and Computation major Ishita Desai and 2024 UM-Dearborn alum Siddhi Baravkar. Baravkar, who developed the first version of the survey system and its algorithm, now works as a software engineer at Mutual of Omaha.

Story by Sarah Tuxbury. Photos by Matthew Stephens