Search

Low-cost sensing strategies hold the promise of denser air quality monitoring networks, which could significantly improve our understanding of personal air pollution exposure. Additionally, low-cost air quality sensors could be deployed to areas where limited monitoring exists. However, low-cost sensors are frequently sensitive to environmental conditions and pollutant cross-sensitivities, which have historically been poorly addressed by laboratory calibrations, limiting their utility for monitoring. In this study, we investigated different calibration models for the Real-time Affordable Multi-Pollutant (RAMP) sensor package, which measures CO, NO2, O3, and CO2. We explored three methods: (1) laboratory univariate linear regression, (2) empirical multiple linear regression, and (3) machine-learning-based calibration models using random forests (RF). Calibration models were developed for 16–19 RAMP monitors (varied by pollutant) using training and testing windows spanning August 2016 through February 2017 in Pittsburgh, PA, US. The random forest models matched (CO) or significantly outperformed (NO2, CO2, O3) the other calibration models, and their accuracy and precision were robust over time for testing windows of up to 16 weeks. Following calibration, average mean absolute error on the testing data set from the random forest models was 38 ppb for CO (14 % relative error), 10 ppm for CO2 (2 % relative error), 3.5 ppb for NO2 (29 % relative error), and 3.4 ppb for O3 (15 % relative error), and Pearson r versus the reference monitors exceeded 0.8 for most units. Model performance is explored in detail, including a quantification of model variable importance, accuracy across different concentration ranges, and performance in a range of monitoring contexts including the National Ambient Air Quality Standards (NAAQS) and the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. A key strength of the RF approach is that it accounts for pollutant cross-sensitivities. This highlights the importance of developing multipollutant sensor packages (as opposed to single-pollutant monitors); we determined this is especially critical for NO2 and CO2. The evaluation reveals that only the RF-calibrated sensors meet the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. We also demonstrate that the RF-model-calibrated sensors could detect differences in NO2 concentrations between a near-road site and a suburban site less than 1.5 km away. From this study, we conclude that combining RF models with carefully controlled state-of-the-art multipollutant sensor packages as in the RAMP monitors appears to be a very promising approach to address the poor performance that has plagued low-cost air quality sensors. [ABSTRACT FROM AUTHOR]

Low-cost sensing strategies hold the promise of denser air quality monitoring networks, which could significantly improve our understanding of personal air pollution exposure. Additionally, low-cost air quality sensors could be deployed to areas where limited monitoring exists. However, low-cost sensors are frequently sensitive to environmental conditions and pollutant cross-sensitivities, which have historically been poorly addressed by laboratory calibrations, limiting their utility for monitoring. In this study, we investigated different calibration models for the Real-time Affordable Multi-Pollutant (RAMP) sensor package, which measures CO, NO2, O3, and CO2. We explored three methods: 1) laboratory univariate linear regression, 2) empirical multivariate linear regression and 3) machine-learning based calibration models using random forests (RF). Calibration models were developed for 19 RAMP monitors using training and testing windows spanning August 2016 through February 2017 in Pittsburgh, PA. The random forest models matched (CO) or significantly outperformed (NO2, CO2, O3) the other calibration models, and their accuracy and precision was robust over time for testing windows of up to 16 weeks. Following calibration, average mean absolute error on the testing dataset from the random forest models was 38 ppb for CO (14 % relative error), 10 ppm for CO2 (2 % relative error), 3.5 ppb for NO2 (29 % relative error) and 3.4 ppb for O3 (15 % relative error), and Pearson r versus the reference monitors exceeded 0.8 for most units. Model performance is explored in detail, including a quantification of model variable importance, accuracy across different concentration ranges, and performance in a range of monitoring contexts including the National Ambient Air Quality Standards (NAAQS), and the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. A key strength of the RF approach is that it accounts for pollutant cross sensitivities. This highlights the importance of developing multipollutant sensor packages (as opposed to single pollutant monitors); we determined this is especially critical for NO2 and CO2. The evaluation reveals that only the RF-calibrated sensors meet the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. We also demonstrate that the RF model calibrated sensors could detect differences in NO2 concentrations between a near-road site and a suburban site less than 1.5 km away. From this study, we conclude that combining RF models with the RAMP monitors appears to be a very promising approach to address the poor performance that has plagued low cost air quality sensors. [ABSTRACT FROM AUTHOR]

Air sensors can provide valuable non-regulatory and supplemental data as they can be affordably deployed in large numbers and stationed in remote areas far away from regulatory air monitoring stations. Air sensors have inherent limitations that are critical to understand before collecting and interpreting the data. Many of these limitations are mechanistic in nature, which will require technological advances. However, there are documented quality assurance (QA) methods to promote data quality. These include laboratory and field evaluation to quantitatively assess performance, the application of corrections to improve precision and accuracy, and active management of the condition or state of health of deployed air quality sensors. This paper summarizes perspectives presented at the U.S. Environmental Protection Agency's 2023 Air Sensors Quality Assurance Workshop (https://www.epa.gov/air-sensor-toolbox/quality-assurance-air-sensors#QAworkshop) by stakeholders (e.g., manufacturers, researchers, air agencies) and identifies the most pressing needs. These include QA protocols, streamlined data processing, improved total volatile organic compound (TVOC) data interpretation, development of speciated VOC sensors, and increased documentation of hardware and data handling. Community members using air sensors need training and resources, timely data, accessible QA approaches, and shared responsibility with other stakeholders. In addition to identifying the vital next steps, this work provides a set of common QA and QC actions aimed at improving and homogenizing air sensor QA that will allow stakeholders with varying fields and levels of expertise to effectively leverage air sensor data to protect human health., Competing Interests: The authors declare no competing financial interest.

Previous studies have characterized spatial patterns of pollution with land use regression (LUR) models from distributed passive or filter samplers at low temporal resolution. Large-scale deployment of low-cost sensors (LCS), which typically sample in real time, may enable time-resolved or real-time modeling of concentration surfaces. The aim of this study was to develop spatiotemporal models of PM 2.5 , NO 2 , and CO using an LCS network in Pittsburgh, Pennsylvania. We modeled daily average concentrations in August 2016-December 2017 across 50 sites. Land use variables included 13 time-independent (e.g., elevation) and time-dependent (e.g., temperature) predictors. We examined two models: LUR and a machine-learning-enabled land use model (land use random forest, LURF). The LURF models outperformed LUR models, with increase in the average externally cross-validated R 2 of 0.10-0.19. Using wavelet decomposition to separate short-lived events from the regional background, we also created time-decomposed LUR and LURF models. Compared to the standard model, this resulted in improvement in R 2 of up to 0.14. The time-decomposed models were more influenced by spatial parameters. Mapping our models across Allegheny County, we observed that time-decomposed LURF models created robust PM 2.5 predictions, suggesting that this approach may improve our ability to map air pollutants at high spatiotemporal resolution.