A causal machine-learning framework for studying policy impact on air pollution: A case-study in COVID-19 lockdowns.

When studying the impact of policy interventions or natural experiments on air pollution, such as new environmental policies and opening or closing an industrial facility, careful statistical analysis is needed to separate causal changes from other confounding factors. Using COVID-19 lockdowns as a case-study, we present a comprehensive framework for estimating and validating causal changes from such perturbations. We propose using flexible machine learning-based comparative interrupted time series (CITS) models for estimating such a causal effect. We outline the assumptions required to identify causal effects, showing that many common methods rely on strong assumptions that are relaxed by machine learning models. For empirical validation, we also propose a simple diagnostic criterion, guarding against false effects in baseline years when there was no intervention. The framework is applied to study the impact of COVID-19 lockdowns on NO2 in the eastern US. The machine learning approaches guard against false effects better than common methods and suggest decreases in NO2 in Boston, New York City, Baltimore, and Washington D.C. The study showcases the importance of our validation framework in selecting a suitable method and the utility of a machine learning based CITS model for studying causal changes in air pollution time series.

Evaluation of Calibration Approaches for Indoor Deployments of PurpleAir Monitors.

Low-cost air quality monitors are growing in popularity among both researchers and community members to understand variability in pollutant concentrations. Several studies have produced calibration approaches for these sensors for ambient air. These calibrations have been shown to depend primarily on relative humidity, particle size distribution, and particle composition, which may be different in indoor environments. However, despite the fact that most people spend the majority of their time indoors, little is known about the accuracy of commonly used devices indoors. This stems from the fact that calibration data for sensors operating in indoor environments are rare. In this study, we sought to evaluate the accuracy of the raw data from PurpleAir fine particulate matter monitors and for published calibration approaches that vary in complexity, ranging from simply applying linear corrections to those requiring co-locating a filter sample for correction with a gravimetric concentration during a baseline visit. Our data includes PurpleAir devices that were co-located in each home with a gravimetric sample for 1-week periods (265 samples from 151 homes). Weekly-averaged gravimetric concentrations ranged between the limit of detection (3 µg/m3) and 330 µg/m3. We found a strong correlation between the PurpleAir monitor and the gravimetric concentration (R>0.91) using internal calibrations provided by the manufacturer. However, the PurpleAir data substantially overestimated indoor concentrations compared to the gravimetric concentration (mean bias error ≥ 23.6 µg/m3 using internal calibrations provided by the manufacturer). Calibrations based on ambient air data maintained high correlations (R ≥ 0.92) and substantially reduced bias (e.g. mean bias error = 10.1 µg/m3 using a US-wide calibration approach). Using a gravimetric sample from a baseline visit to calibrate data for later visits led to an improvement over the internal calibrations, but performed worse than the simpler calibration approaches based on ambient air pollution data. Furthermore, calibrations based on ambient air pollution data performed best when weekly-averaged concentrations did not exceed 30 µg/m3, likely because the majority of the data used to train these models were below this concentration.

Identifying optimal co-location calibration periods for low-cost sensors.

Low-cost sensors are often co-located with reference instruments to assess their performance and establish calibration equations, but limited discussion has focused on whether the duration of this calibration period can be optimized. We placed a multipollutant monitor that contained sensors that measure particulate matter smaller than 2.5 µm (PM2.5), carbon monoxide (CO), nitrogen dioxide (NO2), ozone (O3), and nitric oxide (NO) at a reference field site for one year. We developed calibration equations using randomly selected co-location subsets spanning 1 to 180 consecutive days out of the 1-year period and compared the potential root mean square errors (RMSE) and Pearson correlation coefficients (r). The co-located calibration period required to obtain consistent results varied by sensor type, and several factors increased the co-location duration required for accurate calibration, including the response of a sensor to environmental factors, such as temperature or relative humidity (RH), or cross-sensitivities to other pollutants. Using measurements from Baltimore, MD, where a broad range of environmental conditions may be observed over a given year, we found diminishing improvements in the median RMSE for calibration periods longer than about six weeks for all the sensors. The best performing calibration periods were the ones that contained a range of environmental conditions similar to those encountered during the evaluation period (i.e., all other days of the year not used in the calibration). With optimal, varying conditions it was possible to obtain an accurate calibration in as little as one week for all sensors, suggesting that co-location can be minimized if the period is strategically selected and monitored so that the calibration period is representative of the desired measurement setting.

Laboratory and field evaluation of a low-cost methane sensor and key environmental factors for sensor calibration.

Low-cost sensors enable finer-scale spatiotemporal measurements within the existing methane (CH4) monitoring infrastructure and could help cities mitigate CH4 emissions to meet their climate goals. While initial studies of low-cost CH4 sensors have shown potential for effective CH4 measurement at ambient concentrations, sensor deployment remains limited due to questions about interferences and calibration across environments and seasons. This study evaluates sensor performance across seasons with specific attention paid to the sensor's understudied carbon monoxide (CO) interferences and environmental dependencies through long-term ambient co-location in an urban environment. The sensor was first evaluated in a laboratory using chamber calibration and co-location experiments, and then in the field through two 8 week co-locations with a reference CH4 instrument. In the laboratory, the sensor was sensitive to CH4 concentrations below ambient background concentrations. Different sensor units responded similarly to changing CH4, CO, temperature, and humidity conditions but required individual calibrations to account for differences in sensor response factors. When deployed in-field, co-located with a reference instrument near Baltimore, MD, the sensor captured diurnal trends in hourly CH4 concentration after corrections for temperature, absolute humidity, CO concentration, and hour of day. Variable performance was observed across seasons with the sensor performing well (R 2 = 0.65; percent bias 3.12%; RMSE 0.10 ppm) in the winter validation period and less accurately (R 2 = 0.12; percent bias 3.01%; RMSE 0.08 ppm) in the summer validation period where there was less dynamic range in CH4 concentrations. The results highlight the utility of sensor deployment in more variable ambient CH4 conditions and demonstrate the importance of accounting for temperature and humidity dependencies as well as co-located CO concentrations with low-cost CH4 measurements. We show this can be addressed via Multiple Linear Regression (MLR) models accounting for key covariates to enable urban measurements in areas with CH4 enhancement. Together with individualized calibration prior to deployment, the sensor shows promise for use in low-cost sensor networks and represents a valuable supplement to existing monitoring strategies to identify CH4 hotspots.

Non-linear probabilistic calibration of low-cost environmental air pollution sensor networks for neighborhood level spatiotemporal exposure assessment.

BACKGROUND: Low-cost sensor networks for monitoring air pollution are an effective tool for expanding spatial resolution beyond the capabilities of existing state and federal reference monitoring stations. However, low-cost sensor data commonly exhibit non-linear biases with respect to environmental conditions that cannot be captured by linear models, therefore requiring extensive lab calibration. Further, these calibration models traditionally produce point estimates or uniform variance predictions which limits their downstream in exposure assessment. OBJECTIVE: Build direct field-calibration models using probabilistic gradient boosted decision trees (GBDT) that eliminate the need for resource-intensive lab calibration and that can be used to conduct probabilistic exposure assessments on the neighborhood level. METHODS: Using data from Plantower A003 particulate matter (PM) sensors deployed in Baltimore, MD from November 2018 through November 2019, a fully probabilistic NGBoost GBDT was trained on raw data from sensors co-located with a federal reference monitoring station and compared against linear regression trained on lab calibrated sensor data. The NGBoost predictions were then used in a Monte Carlo interpolation process to generate high spatial resolution probabilistic exposure gradients across Baltimore. RESULTS: We demonstrate that direct field-calibration of the raw PM2.5 sensor data using a probabilistic GBDT has improved point and distribution accuracies compared to the linear model, particularly at reference measurements exceeding 25 µg/m3, and also on monitors not included in the training set. SIGNIFICANCE: We provide a framework for utilizing the GBDT to conduct probabilistic spatial assessments of human exposure with inverse distance weighting that predicts the probability of a given location exceeding an exposure threshold and provides percentiles of exposure. These probabilistic spatial exposure assessments can be scaled by time and space with minimal modifications. Here, we used the probabilistic exposure assessment methodology to create high quality spatial-temporal PM2.5 maps on the neighborhood-scale in Baltimore, MD. IMPACT STATEMENT: We demonstrate how the use of open-source probabilistic machine learning models for in-place sensor calibration outperforms traditional linear models and does not require an initial laboratory calibration step. Further, these probabilistic models can create uniquely probabilistic spatial exposure assessments following a Monte Carlo interpolation process.

Evaluating the Performance of Using Low-Cost Sensors to Calibrate for Cross-Sensitivities in a Multipollutant Network.

As part of our low-cost sensor network, we colocated multipollutant monitors containing sensors for particulate matter, carbon monoxide, ozone, nitrogen dioxide, and nitrogen monoxide at a reference field site in Baltimore, MD, for 1 year. The first 6 months were used for training multiple regression models, and the second 6 months were used to evaluate the models. The models produced accurate hourly concentrations for all sensors except ozone, which likely requires nonlinear methods to capture peak summer concentrations. The models for all five pollutants produced high Pearson correlation coefficients (r > 0.85), and the hourly averaged calibrated sensor and reference concentrations from the evaluation period were within 3-12%. Each sensor required a distinct set of predictors to achieve the lowest possible root-mean-square error (RMSE). All five sensors responded to environmental factors, and three sensors exhibited cross-sensitives to another air pollutant. We compared the RMSE from models (NO2, O3, and NO) that used colocated regulatory instruments and colocated sensors as predictors to address the cross-sensitivities to another gas, and the corresponding model RMSEs for the three gas models were all within 0.5 ppb. This indicates that low-cost sensor networks can yield useable data if the monitoring package is designed to comeasure key predictors. This is key for the utilization of low-cost sensors by diverse audiences since this does not require continual access to regulatory grade instruments.

Development and Performance Evaluation of a Low-Cost Portable PM2.5 Monitor for Mobile Deployment.

The concentration of fine particulate matter (PM2.5) is known to vary spatially across a city landscape. Current networks of regulatory air quality monitoring are too sparse to capture these intra-city variations. In this study, we developed a low-cost (60 USD) portable PM2.5 monitor called Smart-P, for use on bicycles, with the goal of mapping street-level variations in PM2.5 concentration. The Smart-P is compact in size (85 × 85 × 42 mm) and light in weight (147 g). Data communication and geolocation are achieved with the cyclist's smartphone with the help of a user-friendly app. Good agreement was observed between the Smart-P monitors and a regulatory-grade monitor (mean bias error: −3.0 to 1.5 µg m−3 for the four monitors tested) in ambient conditions with relative humidity ranging from 38 to 100%. Monitor performance decreased in humidity > 70% condition. The measurement precision, represented as coefficient of variation, was 6 to 9% in stationary mode and 6% in biking mode across the four tested monitors. Street tests in a city with low background PM2.5 concentrations (8 to 9 µg m−3) and in two cities with high background concentrations (41 to 74 µg m−3) showed that the Smart-P was capable of observing local emission hotspots and that its measurement was not sensitive to bicycle speed. The low-cost and user-friendly nature are two features that make the Smart-P a good choice for empowering citizen scientists to participate in local air quality monitoring.

The climate and health benefits from intensive building energy efficiency improvements.

Intensive building energy efficiency improvements can reduce emissions from energy use, improving outdoor air quality and human health, but may also affect ventilation and indoor air quality. This study examines the effects of highly ambitious, yet feasible, building energy efficiency upgrades in the United States. Our energy efficiency scenarios, derived from the literature, lead to a 6 to 11% reduction in carbon dioxide emissions and 18 to 25% reductions in particulate matter (PM2.5) emissions in 2050. These reductions are complementary with a carbon pricing policy on electricity. However, our results also point to the importance of mitigating indoor PM2.5 emissions, improving PM2.5 filtration, and evaluating ventilation-related policies. Even with no further ventilation improvements, we estimate that intensive energy efficiency scenarios could prevent 1800 to 3600 premature deaths per year across the United States in 2050. With further investments in indoor air quality, this can rise to 2900 to 5100.

Stationary and portable multipollutant monitors for high-spatiotemporal-resolution air quality studies including online calibration.

The distribution and dynamics of atmospheric pollutants are spatiotemporally heterogeneous due to variability in emissions, transport, chemistry, and deposition. To understand these processes at high spatiotemporal resolution and their implications for air quality and personal exposure, we present custom, low-cost air quality monitors that measure concentrations of contaminants relevant to human health and climate, including gases (e.g., O3, NO, NO2, CO, CO2, CH4, and SO2) and size-resolved (0.3-10 µm) particulate matter. The devices transmit sensor data and location via cellular communications and are capable of providing concentration data down to second-level temporal resolution. We produce two models: one designed for stationary (or mobile platform) operation and a wearable, portable model for directly measuring personal exposure in the breathing zone. To address persistent problems with sensor drift and environmental sensitivities (e.g., relative humidity and temperature), we present the first online calibration system designed specifically for low-cost air quality sensors to calibrate zero and span concentrations at hourly to weekly intervals. Monitors are tested and validated in a number of environments across multiple outdoor and indoor sites in New Haven, CT; Baltimore, MD; and New York City. The evaluated pollutants (O3, NO2, NO, CO, CO2, and PM2.5) performed well against reference instrumentation (e.g., r = 0.66-0.98) in urban field evaluations with fast e-folding response times (≤1 min), making them suitable for both large-scale network deployments and smaller-scale targeted experiments at a wide range of temporal resolutions. We also provide a discussion of best practices on monitor design, construction, systematic testing, and deployment.

An accessible method for screening aerosol filtration identifies poor-performing commercial masks and respirators.

BACKGROUND: The COVID-19 pandemic has presented an acute shortage of regulation-tested masks. Many of the alternatives available to hospitals have not been certified, leaving uncertainty about their ability to properly protect healthcare workers from SARS-CoV-2 transmission. OBJECTIVE: For situations where regulatory methods are not accessible, we present experimental methods to evaluate mask filtration and breathability quickly via cost-effective approaches (e.g., ~$2000 USD) that could be replicated in communities of need without extensive infrastructure. We demonstrate the need for screening by evaluating an existing diverse inventory of masks/respirators from a local hospital. METHODS: Two experimental approaches are presented to examine both aerosol filtration and flow impedance (i.e., breathability). For one of the approaches ("quick assessment"), screening for appropriate filtration could be performed under 10 min per mask, on average. Mask fit tests were conducted in tandem but are not the focus of this study. RESULTS: Tests conducted of 47 nonregulation masks reveal variable performance. A number of commercially available masks in hospital inventories perform similarly to N95 masks for aerosol filtration of 0.2 µm and above, but there is a range of masks with relatively lower filtration efficiencies (e.g., <90%) and a subset with poorer filtration (e.g., <70%). All masks functioned acceptably for breathability, and impedance was not correlated with filtration efficiency. SIGNIFICANCE: With simplified tests, organizations with mask/respirator shortages and uncertain inventories can make informed decisions about use and procurement.

Statistical field calibration of a low-cost PM2.5 monitoring network in Baltimore.

Low-cost air pollution monitors are increasingly being deployed to enrich knowledge about ambient air-pollution at high spatial and temporal resolutions. However, unlike regulatory-grade (FEM or FRM) instruments, universal quality standards for low-cost sensors are yet to be established and their data quality varies widely. This mandates thorough evaluation and calibration before any responsible use of such data. This study presents evaluation and field-calibration of the PM2.5 data from a network of low-cost monitors currently operating in Baltimore, MD, which has only one regulatory PM2.5 monitoring site within city limits. Co-location analysis at this regulatory site in Oldtown, Baltimore revealed high variability and significant overestimation of PM2.5 levels by the raw data from these monitors. Universal laboratory corrections reduced the bias in the data, but only partially mitigated the high variability. Eight months of field co-location data at Oldtown were used to develop a gain-offset calibration model, recast as a multiple linear regression. The statistical model offered substantial improvement in prediction quality over the raw or lab-corrected data. The results were robust to the choice of the low-cost monitor used for field-calibration, as well as to different seasonal choices of training period. The raw, lab-corrected and statistically-calibrated data were evaluated for a period of two months following the training period. The statistical model had the highest agreement with the reference data, producing a 24-hour average root-mean-square-error (RMSE) of around 2 µg m -3. To assess transferability of the calibration equations to other monitors in the network, a cross-site evaluation was conducted at a second co-location site in suburban Essex, MD. The statistically calibrated data once again produced the lowest RMSE. The calibrated PM2.5 readings from the monitors in the low-cost network provided insights into the intra-urban spatiotemporal variations of PM2.5 in Baltimore.