Intense economic and industrial development in China has been accompanied by severe local air pollution, as well as in other downwind countries in East Asia. This study analyzes satellite observational data of sulfur dioxide (SO₂), nitrogen dioxide (NO₂), and aerosol optical depth (AOD) to explore the spatial distribution, long-term temporal variation, and correlation to meteorological conditions over this region over the period 2005–2015. SO₂ and NO₂ data are retrieved from the ozone monitoring instrument (OMI) onboard the National Aeronautics and Space Administration (NASA) Aura satellite, while AOD data are from the moderate-resolution imaging spectroradiometer (MODIS) onboard the NASA Aqua satellite. Spatial distributions of SO₂, NO₂, and AOD show the highest levels in the North China Plain (NCP), with hotspots also in Southeastern China (SC) and the Sichuan Basin (SB). Biomass burning also contributes to a high level of AOD in Southeast Asia in spring and in Equatorial Asia in fall. Considering the correlation of pollutant levels to meteorological conditions, monitoring data show that higher temperature and higher relative humidity (RH) favor the conversion of SO₂ and NO₂ to sulfate and nitrate aerosol, respectively. The impact of stronger lower tropospheric stability facilitates the accumulation of SO₂ and NO₂ in NCP and SC. Transport of SO₂ and NO₂ from intense source regions to relatively clean regions is highly influential over East Asia; such transport from the NCP leads to a considerable increase of pollutants in SC, SB, Taiwan Island (TW), and Taiwan Strait (TWS), particularly in winter. Aerosols generated by biomass burning in Southeast Asia and anthropogenic aerosol in SC are transported to TW and TWS and lead to the increase of AOD, with the highest levels of AOD in SC, TW, and TWS occurring in spring. Precipitation results in the removal of pollutants, especially in highly polluted regions, the effect of which is most significant in winter and spring.

In New York State (NYS), episodic high fine particulate matter (PM_2.5) concentrations associated with aerosols originated from the Midwest, Mid-Atlantic, and Pacific Northwest states have been reported. In this study, machine learning techniques, including multiple linear regression (MLR) and artificial neural network (ANN), were used to estimate surface PM_2.5 mass concentrations at air quality monitoring sites in NYS during the summers of 2016–2019. Various predictors were considered, including meteorological, aerosol, and geographic predictors. Vertical predictors, designed as the indicators of vertical mixing and aloft aerosols, were also applied. Overall, the ANN models performed better than the MLR models, and the application of vertical predictors generally improved the accuracy of PM_2.5 estimation of the ANN models. The leave-one-out cross-validation results showed significant cross-site variations and were able to present the different predictor-PM_2.5 correlations at the sites with different PM_2.5 characteristics. In addition, a joint analysis of regression coefficients from the MLR model and variable importance from the ANN model provided insights into the contributions of selected predictors to PM_2.5 concentrations. The improvements in model performance due to aloft aerosols were relatively minor, probably due to the limited cases of aloft aerosols in current datasets.

We aim to resolve the difficulties of action recognition arising from the large intra-class variations. These unfavorable variations make it infeasible to represent one action instance by other ones of the same action. We hence propose to extract both instance-specific and class-consistent features to facilitate action recognition. Specifically, the instance-specific features explore the self-similarities among frames of each video instance, while class-consistent features summarize within-class similarities. We introduce a generative formulation to combine the two diverse types of features. The experimental results demonstrate the effectiveness of our approach.

An increasing trend of wildfire activity over North America over the past decades has been observed. Elevated surface fine mode particulate matter (PM2.5) concentration and reduction of solar radiation during the smoke episodes have been widely reported. Given that the intensity and frequency of wildfires are expected to increase under changing climate, the impact of smoke aerosols on air quality and solar energy could become more significant. This study aims to characterize the transport of smoke aerosols and quantify their impact on local air quality and solar energy over New York (NY) and California (CA) States. A multi-year analysis of smoke cases during the summer of 2017-2022, case studies of smoke events in September of 2017 and June of 2023 over NY, and numerical experiments of the 2020 wildfire over CA were conducted. Various analyses were conducted, including 1) identification of smoke plumes using satellite measurements, ground-based observations, and aerosol reanalysis products, 2) quantification of the contribution of smoke aerosols to local air quality and solar radiation, and 3) characterization of the transport process and vertical mixing of smoke events. Results of multi-year analysis showed that transported smoke aerosols introduced an increase of daily PM2.5 of 3-4 ?g m-3 on average over NYS. Besides, 30.0% - 40.0% of the polluted days were associated with transported smoke aerosols. The record-breaking smoke event in June 2023 led to an increase of PM2.5 by 15-fold - 60-fold while annually occurred less extreme smoke events caused an enhancement of PM2.5 by 3-fold. Analysis of case studies reveals that synoptic subsidence, entrainment process, and turbulent mixing collectively contributed to the downward transport of smoke aerosols and the enhancement of surface PM2.5 concentrations. During the summer of 2020 over CA, results of model simulation show that wildfire activity leads to an increase of monthly aerosol optical depth by 0.2-0.7 and reduction of clear-sky global horizontal irradiance by 3-10%. Future studies considering a range of variability in wildfire activities (e.g. geographic location, size, and time of year) and the key factors which determine air quality and solar energy impacts of the transported smoke aerosols, such as plume rise, large-scale circulation, aerosol physical/chemical processes, and PBL evolution, are recommended.