Search for: All records

Despite decades of progress in reducing nitrogen oxide (NO_x) emissions, ammonium nitrate (AN) remains the primary inorganic component of particulate matter (PM) in Los Angeles (LA). Using aerosol mass spectrometry over multiple years in LA illustrates the controlling dynamics of AN and their evolution over the past decades. These data suggest that much of the nitric acid (HNO₃) production required to produce AN in LA occurs during the nighttime via heterogeneous hydrolysis of N₂O₅. Further, we show that US Environmental Protection Agency–codified techniques for measuring total PM_2.5fail to quantify the AN component, while low-cost optical sensors demonstrate good agreement. While previous studies suggest that declining NO_xhas reduced AN, we show that HNO₃formation is still substantial and leads to the formation of many tens of micrograms per cubic meter of AN aerosol. Continued focus on reductions in NO_xwill help meet the PM_2.5standards in the LA basin and many other regions. 

Accurate air pollution monitoring is critical to understand and mitigate the impacts of air pollution on human health and ecosystems. Due to the limited number and geographical coverage of advanced, highly accurate sensors monitoring air pollutants, many low-cost and low-accuracy sensors have been deployed. Calibrating low-cost sensors is essential to fill the geographical gap in sensor coverage. We systematically examined how different machine learning (ML) models and open-source packages could help improve the accuracy of particulate matter (PM) 2.5 data collected by Purple Air sensors. Eleven ML models and five packages were examined. This systematic study found that both models and packages impacted accuracy, while the random training/testing split ratio (e.g., 80/20 vs. 70/30) had minimal impact (0.745% difference for R2). Long Short-Term Memory (LSTM) models trained in RStudio and TensorFlow excelled, with high R2 scores of 0.856 and 0.857 and low Root Mean Squared Errors (RMSEs) of 4.25 µg/m3 and 4.26 µg/m3, respectively. However, LSTM models may be too slow (1.5 h) or computation-intensive for applications with fast response requirements. Tree-boosted models including XGBoost (0.7612, 5.377 µg/m3) in RStudio and Random Forest (RF) (0.7632, 5.366 µg/m3) in TensorFlow offered good performance with shorter training times (<1 min) and may be suitable for such applications. These findings suggest that AI/ML models, particularly LSTM models, can effectively calibrate low-cost sensors to produce precise, localized air quality data. This research is among the most comprehensive studies on AI/ML for air pollutant calibration. We also discussed limitations, applicability to other sensors, and the explanations for good model performances. This research can be adapted to enhance air quality monitoring for public health risk assessments, support broader environmental health initiatives, and inform policy decisions.