Correction and Accuracy of PurpleAir PM2.5 Measurements for Extreme Wildfire Smoke

Abstract

PurpleAir particulate matter (PM) sensors are increasingly used in the United States and other countries for real-time air quality information, particularly during wildfire smoke episodes. Uncorrected PurpleAir data can be biased and may exhibit a nonlinear response at extreme smoke concentrations (>300 µg/m3). This bias and nonlinearity result in a disagreement with the traditional ambient monitoring network, leading to the public’s confusion during smoke episodes. These sensors must be evaluated during smoke-impacted times and then corrected for bias, to ensure that accurate data are reported. The nearby public PurpleAir sensor and monitor pairs were identified during the summer of 2020 and were used to supplement the data from collocated pairs to develop an extended U.S.-wide correction for high concentrations. We evaluated several correction schemes to identify an optimal correction, using the previously developed U.S.-wide correction, up to 300 µg/m3, transitioning to a quadradic fit above 400 µg/m3. The correction reduces the bias at each air quality index (AQI) breakpoint; most ambient collocations that were studied met the Environmental Protection Agency’s (EPA) performance targets (twelve of the thirteen ambient sensors met the EPA’s targets) and some smoke-impacted sites (5 out of 15 met the EPA’s performance targets in terms of the 1-h averages). This correction can also be used to improve the comparability of PurpleAir sensor data with regulatory-grade monitors when they are collectively analyzed or shown together on public information websites; the methods developed in this paper can also be used to correct future air-sensor types. The PurpleAir network is already filling in spatial and temporal gaps in the regulatory monitoring network and providing valuable air-quality information during smoke episodes.

Keywords: PM2.5; PurpleAir; air quality index (AQI); air sensor; correction; evaluation; wildfire smoke.

Figure 1

Nonlinearity in hourly PurpleAir PM_2.5, uncorrected [cf = 1], versus the monitor PM_2.5 values, colored by the relative humidity, as measured by the PurpleAir.

Figure 2

Summary of the distribution of RH and PM_2.5 for each sensor (withholding groups). The Atascadero sensor experienced both typical ambient and smoke−impacted periods.

Figure 3

Percentage of the time that the PurpleAir NowCast AQI is the same as or different by 1 or 2 NowCast AQI categories. This is binned by the reference NowCast AQI category. It includes data using both withholding methods.

Figure 4

Example time series from the Forks of Salmon, CA, showing the data that were corrected based on different corrections on the PurpleAir map (Woodsmoke, AQandU, LRAPA, ALT cf = 3) and in the literature (Nilson cf_atm and cf_1).

Figure 5

Disagreement between Nilson cf_atm (actually used in Nilson’s paper based on their corrigendum) and the extended US-wide correction, plotted over the range of RH used in each correction, shown at low concentrations (A) and over the full range (B) with gray vertical lines showing the transition zone from the US-wide correction to the quadradic fit.