In this study, we present a nationwide machine learning model for hourly PM2.5 estimation for the continental United States (US) using high temporal resolution Geostationary Operational Environmental Satellites (GOES-16) Aerosol Optical Depth (AOD) data, meteorological variables from the European Center for Medium Range Weather Forecasting (ECMWF) and ancillary data collected between May 2017 and December 2020. A model sensitivity analysis was conducted on predictor variables to determine the optimal model. It turns out that GOES16 AOD, variables from ECMWF, and ancillary data are effective variables in PM2.5 estimation and historical reconstruction, which achieves an average mean absolute error (MAE) of 3.0 μg/m3, and a root mean square error (RMSE) of 5.8 μg/m3. This study also found that the model performance as well as the site measured PM2.5 concentrations demonstrate strong spatial and temporal patterns. Specifically, in the temporal scale, the model performed best between 8:00 p.m. and 11:00 p.m. (UTC TIME) and had the highest coefficient of determination (R2) in Autumn and the lowest MAE and RMSE in Spring. In the spatial scale, the analysis results based on ancillary data show that the R2 scores correlate positively with the mean measured PM2.5 concentration at monitoring sites. Mean measured PM2.5 concentrations are positively correlated with population density and negatively correlated with elevation. Water, forests, and wetlands are associated with low PM2.5 concentrations, whereas developed, cultivated crops, shrubs, and grass are associated with high PM2.5 concentrations. In addition, the reconstructed PM2.5 surfaces serve as an important data source for pollution event tracking and PM2.5 analysis. For this purpose, from May 2017 to December 2020, hourly PM2.5 estimates were made for 10 km by 10 km and the PM2.5 estimates from August through November 2020 during the period of California Santa Clara Unite (SCU) Lightning Complex fires are presented. Based on the quantitative and visualization results, this study reveals that a number of large wildfires in California had a profound impact on the value and spatial-temporal distributions of PM2.5 concentrations.
more »
« less
Community-Based Measurements Reveal Unseen Differences during Air Pollution Episodes
Short-term exposure to fine particulate matter (PM2.5) pollution is linked to numerous adverse health effects. Pollution episodes, such as wildfires, can lead to substantial increases in PM2.5 levels. However, sparse regulatory measurements provide an incomplete understanding of pollution gradients. Here, we demonstrate an infrastructure that integrates community-based measurements from a network of low-cost PM2.5 sensors with rigorous calibration and a Gaussian process model to understand neighborhood-scale PM2.5 concentrations during three pollution episodes (July 4, 2018, fireworks; July 5 and 6, 2018, wildfire; Jan 3−7, 2019, persistent cold air pool, PCAP). The firework/wildfire events included 118 sensors in 84 locations, while the PCAP event included 218 sensors in 138 locations. The model results accurately predict reference measurements during the fireworks (n: 16, hourly root-mean-square error, RMSE, 12.3−21.5 μg/m3, n(normalized)-RMSE: 9−24%), the wildfire (n: 46, RMSE: 2.6−4.0 μg/m3; nRMSE: 13.1−22.9%), and the PCAP (n: 96, RMSE: 4.9−5.7 μg/m3; nRMSE: 20.2−21.3%). They also revealed dramatic geospatial differences in PM2.5 concentrations that are not apparent when only considering government measurements or viewing the US Environmental Protection Agency’s AirNow’s visualizations. Complementing the PM2.5 estimates and visualizations are highly resolved uncertainty maps. Together, these results illustrate the potential for low-cost sensor networks that combined with a data-fusion algorithm and appropriate calibration and training can dynamically and with improved accuracy estimate PM2.5 concentrations during pollution episodes. These highly resolved uncertainty estimates can provide a much-needed strategy to communicate uncertainty to end users.
more »
« less
- NSF-PAR ID:
- 10207574
- Date Published:
- Journal Name:
- Environmental Science & Technology
- ISSN:
- 0013-936X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract. As the changing climate expands the extent of arid andsemi-arid lands, the number of, severity of, and health effects associated with dust events are likely to increase. However, regulatory measurements capable of capturing dust (PM10, particulate matter smaller than10 µm in diameter) are sparse, sparser than measurements of PM2.5 (PM smaller than 2.5 µm in diameter). Although low-cost sensors couldsupplement regulatory monitors, as numerous studies have shown forPM2.5 concentrations, most of these sensors are not effective atmeasuring PM10 despite claims by sensor manufacturers. This studyfocuses on the Salt Lake Valley, adjacent to the Great Salt Lake, whichrecently reached historic lows exposing 1865 km2 of dry lake bed. Itevaluated the field performance of the Plantower PMS5003, a common low-costPM sensor, and the Alphasense OPC-N3, a promising candidate for low-costmeasurement of PM10, against a federal equivalent method (FEM, betaattenuation) and research measurements (GRIMM aerosol spectrometer model1.109) at three different locations. During a month-long field study thatincluded five dust events in the Salt Lake Valley with PM10 concentrations reaching 311 µg m−3, the OPC-N3 exhibited strong correlation with FEM PM10 measurements (R2 = 0.865, RMSE = 12.4 µg m−3) and GRIMM (R2 = 0.937, RMSE = 17.7 µg m−3). The PMS exhibited poor to moderate correlations(R2 < 0.49, RMSE = 33–45 µg m−3) withreference or research monitors and severely underestimated the PM10concentrations (slope < 0.099) for PM10. We also evaluated aPM-ratio-based correction method to improve the estimated PM10concentration from PMSs. After applying this method, PMS PM10concentrations correlated reasonably well with FEM measurements (R2 > 0.63) and GRIMM measurements (R2 > 0.76), andthe RMSE decreased to 15–25 µg m−3. Our results suggest that itmay be possible to obtain better resolved spatial estimates of PM10concentration using a combination of PMSs (often publicly availablein communities) and measurements of PM2.5 and PM10, such as thoseprovided by FEMs, research-grade instrumentation, or the OPC-N3.more » « less
-
The impacts of wildfires along the wildland urban interface (WUI) on atmospheric particulate concentrations and composition are an understudied source of air pollution exposure. To assess the residual impacts of the 2021 Marshall Fire (Colorado), a wildfire that predominantly burned homes and other human-made materials, on homes within the fire perimeter that escaped the fire, we performed a combination of fine particulate matter (PM2.5) filter sampling and chemical analysis, indoor dust collection and chemical analysis, community scale PurpleAir PM2.5 analysis, and indoor particle number concentration measurements. Following the fire, the chemical speciation of dust collected in smoke-affected homes in the burned zone showed elevated concentrations of the biomass burning marker levoglucosan (medianlevo = 4147 ng g−1), EPA priority toxic polycyclic aromatic hydrocarbons (median Σ16PAH = 1859.3 ng g−1), and metals (median Σ20Metals = 34.6 mg g−1) when compared to samples collected in homes outside of the burn zone 6 months after the fire. As indoor dust particles are often resuspended and can become airborne, the enhanced concentration of hazardous metals and organics within dust samples may pose a threat to human health. Indoor airborne particulate organic carbon (median = 1.91 μg m−3), particulate elemental carbon (median = .02 μg m−3), and quantified semi-volatile organic species in PM2.5 were found in concentrations comparable to ambient air in urban areas across the USA. Particle number and size distribution analysis at a heavily instrumented supersite home located immediately next to the burned area showed indoor particulates in low concentrations (below 10 μg m−3) across various sizes of PM (12 nm–20 μm), but were elevated by resuspension from human activity, including cleaning.more » « less
-
Low-cost sensors enable finer-scale spatiotemporal measurements within the existing methane (CH 4 ) monitoring infrastructure and could help cities mitigate CH 4 emissions to meet their climate goals. While initial studies of low-cost CH 4 sensors have shown potential for effective CH 4 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 CH 4 instrument. In the laboratory, the sensor was sensitive to CH 4 concentrations below ambient background concentrations. Different sensor units responded similarly to changing CH 4 , 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 CH 4 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 CH 4 concentrations. The results highlight the utility of sensor deployment in more variable ambient CH 4 conditions and demonstrate the importance of accounting for temperature and humidity dependencies as well as co-located CO concentrations with low-cost CH 4 measurements. We show this can be addressed via Multiple Linear Regression (MLR) models accounting for key covariates to enable urban measurements in areas with CH 4 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 CH 4 hotspots.more » « less
-
Abstract. Low-cost sensors are often co-located with reference instruments to assess their performance and establish calibration equations, but limiteddiscussion has focused on whether the duration of this calibration period can be optimized. We placed a multipollutant monitor that containedsensors that measured particulate matter smaller than 2.5 µm (PM2.5), carbon monoxide (CO), nitrogendioxide (NO2), ozone (O3), and nitric oxide (NO) at a reference field site for 1 year. We developed calibration equationsusing randomly selected co-location subsets spanning 1 to 180 consecutive days out of the 1-year period and compared the potential root-mean-square error (RMSE) and Pearson correlation coefficient (r) values. The co-located calibration period required to obtain consistent results varied bysensor type, and several factors increased the co-location duration required for accurate calibration, including the response of a sensor toenvironmental factors, such as temperature or relative humidity (RH), or cross-sensitivities to other pollutants. Using measurements fromBaltimore, MD, where a broad range of environmental conditions may be observed over a given year, we found diminishing improvements in the medianRMSE for calibration periods longer than about 6 weeks for all the sensors. The best performing calibration periods were the ones that contained arange of environmental conditions similar to those encountered during the evaluation period (i.e., all other days of the year not used in thecalibration). With optimal, varying conditions it was possible to obtain an accurate calibration in as little as 1 week for all sensors, suggestingthat co-location can be minimized if the period is strategically selected and monitored so that the calibration period is representative of thedesired measurement setting.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1021/acs.est.0c02341
