Evaluation of Long-Term Performance of Six PM2.5 Sensor Types

From July 2019 to January 2021, six models of PM2.5 air sensors were operated at seven air quality monitoring sites across the U.S. in Arizona, Colorado, Delaware, Georgia, North Carolina, Oklahoma, and Wisconsin. Common PM sensor data issues were identified, including repeat zero measurements, false high outliers, baseline shift, varied relationships between the sensor and monitor, and relative humidity (RH) influences. While these issues are often easy to identify during colocation, they are more challenging to identify or correct during deployment since it is hard to differentiate between real pollution events and sensor malfunctions. Air sensors may exhibit wildly different performances even if they have the same or similar internal components. Commonly used RH corrections may still have variable bias by hour of the day and seasonally. Most sensors show promise in achieving the U.S. Environmental Protection Agency (EPA) performance targets, and the findings here can be used to improve their performance and reliability further. This evaluation generated a robust dataset of colocated air sensor and monitor data, and by making it publicly available along with the results presented in this paper, we hope the dataset will be an asset to the air sensor community in understanding sensor performance and validating new methods.