Prediction of daily mean and one-hour maximum PM2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models.

BACKGROUND: Machine-learning algorithms are becoming popular techniques to predict ambient air PM2.5 concentrations at high spatial resolutions (1 × 1 km) using satellite-based aerosol optical depth (AOD). Most machine-learning models have aimed to predict 24 h-averaged PM2.5 concentrations (mean PM2.5) in high-income regions. Over Mexico, none have been developed to predict subdaily peak levels, such as the maximum daily 1-h concentration (max PM2.5). OBJECTIVE: Our goal was to develop a machine-learning model to predict mean PM2.5 and max PM2.5 concentrations in the Mexico City Metropolitan Area from 2004 through 2019. METHODS: We present a new modeling approach based on extreme gradient boosting (XGBoost) and inverse-distance weighting that uses AOD, meteorology, and land-use variables. We also investigated applications of our mean PM2.5 predictions that can aid local authorities in air-quality management and public-health surveillance, such as the co-occurrence of high PM2.5 and heat, compliance with local air-quality standards, and the relationship of PM2.5 exposure with social marginalization. RESULTS: Our models for mean and max PM2.5 exhibited good performance, with overall cross-validated mean absolute errors (MAE) of 3.68 and 9.20 µg/m3, respectively, compared to mean absolute deviations from the median (MAD) of 8.55 and 15.64 µg/m3. In 2010, everybody in the study region was exposed to unhealthy levels of PM2.5. Hotter days had greater PM2.5 concentrations. Finally, we found similar exposure to PM2.5 across levels of social marginalization. SIGNIFICANCE: Machine learning algorithms can be used to predict highly spatiotemporally resolved PM2.5 concentrations even in regions with sparse monitoring. IMPACT: Our PM2.5 predictions can aid local authorities in air-quality management and public-health surveillance, and they can advance epidemiological research in Central Mexico with state-of-the-art exposure assessment methods.

Observations of lightning in relation to transitions in volcanic activity during the 3 June 2018 Fuego Eruption.

Satellite and ground-based remote sensing are combined to characterize lightning occurrence during the 3 June 2018 Volcán de Fuego eruption in Guatemala. The combination of the space-based Geostationary Lightning Mapper (GLM) and ground-based Earth Networks Total Lightning Network observed two distinct periods of lightning during this eruption totaling 75 unique lightning flash occurrences over five hours (57 in cloud, 18 cloud-to-ground). The first period of lightning coincided with the rapid growth of the ash cloud, while the second maxima occurred near the time of a deadly pyroclastic density current (PDC) and thunderstorm. Ninety-one percent of the lightning during the event was observed by only one of the lightning sensors, thus showing the importance of combining lightning datasets across multiple frequencies to characterize electrical activity in volcanic eruptions. GLM flashes during the event had a median total optical energy and flash length of 16 fJ, and 12 km, respectively. These median GLM flash energies and lengths observed in the volcanic plume are on the lower end of the flash spectrum because flashes observed in surrounding thunderstorms on 3 June had larger median total optical energy values (130 fJ) and longer median flash lengths (20 km). All 18 cloud-to-ground flashes were negative polarity, supportive of net negative charge within the plume. Mechanisms for the generation of the secondary lightning maxima are discussed based on the presence and potential interaction between ash plume, thunderstorm, and PDC transport during this secondary period of observed lightning.