Contribution of low-cost sensor measurements to the prediction of PM2.5 levels: A case study in Imperial County, California, USA

Abstract

Regulatory monitoring networks are often too sparse to support community-scale PM 2.5 exposure assessment while emerging low-cost sensors have the potential to fill in the gaps. To date, limited studies, if any, have been conducted to utilize low-cost sensor measurements to improve PM 2.5 prediction with high spatiotemporal resolutions based on statistical models. Imperial County in California is an exemplary region with sparse Air Quality System (AQS) monitors and a community-operated low-cost network entitled Identifying Violations Affecting Neighborhoods (IVAN). This study aims to evaluate the contribution of IVAN measurements to the quality of PM 2.5 prediction. We adopted the Random Forest algorithm to estimate daily PM 2.5 concentrations at 1-km spatial resolution using three different PM 2.5 datasets (AQS-only, IVAN-only, and AQS/ IVAN combined). The results showed that the integration of low-cost sensor measurements is an effective way to significantly improve the quality of PM 2.5 prediction with an increase of crossvalidation (CV) R 2 by ~0.2. The IVAN measurements also contributed to the increased importance *

A Validation Approach Considering the Uneven Distribution of Ground Stations for Satellite-Based PM2.5 Estimation

“…Due to the high cost of PM 2.5 ground stations, the station network exhibits a sparse and uneven spatial distribution, which brings challenges to the validation of the satellite-based PM 2.5 estimation models. With the development of PM 2.5 monitors, the intensive observation network [6], [34], [45], [46] may provide new solutions for the validation of PM 2.5 estimation models. First, portable low-cost devices and observation vehicles are likely to offer more validation approaches for PM 2.5 estimation models.…”

Performance of a Low-Cost Sensor Community Air Monitoring Network in Imperial County, CA

“…Thus, more spatially refined air quality information can be used to help pinpoint pollution episodes important for adverse, acute exposures to particulate matter, individual exposure reduction, and reduce exposure misclassification. In addition, the Network data has been used for spatial and temporal modeling [33] and to model PM 2.5 concentrations [34,35].…”

Validating and Comparing Highly Resolved Commercial “Off the Shelf” PM Monitoring Sensors with Satellite Based Hybrid Models, for Improved Environmental Exposure Assessment

“…They have shown that a smaller, local scale for the satellite (0.1 × 0.1 km) has greater promise in utilization with ground monitors, while exhibiting difficulties in correlating them when the scale was larger. However, even at a 1 × 1 km scale, studies have shown that assimilating ground measurements in satellite based models using COTS could improve correlation value by ~0.2 [ 61 ]. Additional research is required in order to utilize 1 × 1 km models more effectively in exposure assessment, while taking into consideration different areas and pollution levels.…”