Historical PM2 Research Articles

Stacked ResNet-LSTM and CORAL model for multi-site air quality prediction

As the global economy is booming, and the industrialization and urbanization are being expedited, particulate matter 2.5 (PM2.5) turns out to be a major air pollutant jeopardizing public health. Numerous researchers are committed to employing various methods to address the problem of the nonlinear correlation between PM2.5 concentration and several factors to achieve more effective forecasting. However, a considerable space remains for the improvement of forecasting accuracy, and the problem of missing air pollution data on certain target areas also needs to be solved. Our research work is divided into two parts. First, this study presents a novel stacked ResNet-LSTM model to enhance prediction accuracy for PM2.5 concentration level forecast. As revealed from the experimental results, the proposed model outperforms other models such as boosting algorithms or general recurrent neural networks, and the advantage of feature extraction through residual network (ResNet) combined with a model stacking strategy is shown. Second, to solve the problem of insufficient air quality and meteorological data on some research areas, this study proposes the use of a correlation alignment (CORAL) method to carry out a prediction on the target area by aligning the second-order statistics between source area and target area. As indicated from the results, this model exhibits a considerable accuracy even in the absence of historical PM2.5 data in the target forecast area.

Deep Ensemble Machine Learning Framework for the Estimation of Concentrations.

Background:Accurate estimation of historical (particle matter with an aerodynamic diameter of less than ) is critical and essential for environmental health risk assessment.Objectives:The aim of this study was to develop a multiple-level stacked ensemble machine learning framework for improving the estimation of the daily ground-level concentrations.Methods:An innovative deep ensemble machine learning framework (DEML) was developed to estimate the daily concentrations. The framework has a three-stage structure: At the first stage, four base models [gradient boosting machine (GBM), support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGBoost)] were used to generate a new data set of concentrations for training the next-stage learners. At the second stage, three meta-models [RF, XGBoost, and Generalized Linear Model (GLM)] were used to estimate concentrations using a combination of the original data set and the predictions from the first-stage models. At the third stage, a nonnegative least squares (NNLS) algorithm was employed to obtain the optimal weights for estimation. We took the data from 133 monitoring stations in Italy as an example to implement the DEML to predict daily at each grid cell from 2015 to 2019 across Italy. We evaluated the model performance by performing 10-fold cross-validation (CV) and compared it with five benchmark algorithms [GBM, SVM, RF, XGBoost, and Super Learner (SL)].Results:The results revealed that the prediction performance of DEML [coefficients of determination and root mean square error ] was superior to any benchmark models (with of 0.51, 0.76, 0.83, 0.70, and 0.83 for GBM, SVM, RF, XGBoost, and SL approach, respectively). DEML displayed reliable performance in capturing the spatiotemporal variations of in Italy.Discussion: The proposed DEML framework achieved an outstanding performance in estimation, which could be used as a tool for more accurate environmental exposure assessment. https://doi.org/10.1289/EHP9752

Accurate Multi-Site Daily-Ahead Multi-Step PM2.5 Concentrations Forecasting Using Space-Shared CNN-LSTM

Accurate multi-step PM2.5 (particulate matter with diameters ≤2.5um) concentration prediction is critical for humankinds’ health and air population management because it could provide strong evidence for decision-making. However, it is very challenging due to its randomness and variability. This paper proposed a novel method based on convolutional neural network (CNN) and long-short-term memory (LSTM) with a space-shared mechanism, named space-shared CNN-LSTM (SCNN-LSTM) for multi-site daily-ahead multi-step PM2.5 forecasting with self-historical series. The proposed SCNN-LSTM contains multi-channel inputs, each channel corresponding to one-site historical PM2.5 concentration series. In which, CNN and LSTM are used to extract each site's rich hidden feature representations in a stack mode. Especially, CNN is to extract the hidden short-time gap PM2.5 concentration patterns; LSTM is to mine the hidden features with long-time dependency. Each channel extracted features are merged as the comprehensive features for future multi-step PM2.5 concentration forecasting. Besides, the space-shared mechanism is implemented by multi-loss functions to achieve space information sharing. Therefore, the final features are the fusion of short-time gap, long-time dependency, and space information, which enables forecasting more accurately. To validate the proposed method's effectiveness, the authors designed, trained, and compared it with various leading methods in terms of RMSE, MAE, MAPE, and R2 on four real-word PM2.5 data sets in Seoul, South Korea. The massive experiments proved that the proposed method could accurately forecast multi-site multi-step PM2.5 concentration only using self-historical PM2.5 concentration time series and running once. Specifically, the proposed method obtained averaged RMSE of 8.05, MAE of 5.04, MAPE of 23.96%, and R2 of 0.7 for four-site daily ahead 10-hour PM2.5 concentration forecasting.

Maternal Secondhand Smoke Exposure Enhances Macrosomia Risk Among Pregnant Women Exposed to PM2.5: A New Interaction of Two Air Pollutants in a Nationwide Cohort.

Background: Fine particulate matter (PM2.5) is one of the most common outdoor air pollutants, and secondhand smoking (SHS) is an important source of inhalable indoor air pollution. Previous studies were controversial and inconsistent about PM2.5 and SHS air pollutants on neonatal birth weight outcomes, and no studies assessed the potential interactive effects between PM2.5 and SHS on birth weight outcomes.Purpose: To investigate the interaction between gestational PM2.5 and SHS air pollution exposure on the risk of macrosomia among pregnant women and examine the modifying effect of SHS exposure on the association of PM2.5 air pollution and birth weight outcomes during pregnancy.Methods: Research data were derived from the National Free Preconception Health Examination Project (NFPHEP), which lasted 3 years from January 1, 2010, to December 31, 2012. At least 240,000 Chinese women from 220 counties were enrolled in this project. PM2.5 exposure concentration was obtained using a hindcast model specific for historical PM2.5 estimation from satellite-retrieved aerosol optic depth. Different interaction models about air pollution exposure on birth weight outcomes were established, according to the adjustment of different confounding factors and different pregnancy stages. The establishment of interaction models was based on multivariable logistic regression, and the main confounding factors were maternal age at delivery and pre-pregnancy body mass index (BMI) of participants. SHS subgroups analysis was conducted to further confirm the results of interaction models.Results: In total, 197,877 participants were included in our study. In the full-adjusted interaction model, maternal exposure to PM2.5 was associated with an increased risk of macrosomia in whole, the first-, second-, and third trimesters of pregnancy (p < 0.001). The interactive effect was statistically significant between maternal exposure to PM2.5 and SHS on the risk of macrosomia in the whole (interaction p < 0.050) and the first-trimester pregnancy (interaction p < 0.050), not in the second (interaction p > 0.050) or third trimester (interaction p > 0.050) of pregnancy. The higher frequency of SHS exposure prompted the stronger interaction between the two air pollutants in the whole pregnancy and the first-trimester pregnancy.Conclusions: In the whole and first-trimester pregnancy, maternal exposure to SHS during pregnancy enhanced the risk of macrosomia among pregnant women exposed to PM2.5 air pollutants, and the interaction became stronger with the higher frequency of SHS exposure.

Inequality in historical transboundary anthropogenic PM2.5 health impacts

Atmospheric transport of fine particulate matter (PM2.5), the leading environmental risk factor for public health, is estimated to exert substantial transboundary effects at present. During the past several decades, human-produced pollutant emissions have undergone drastic and regionally distinctive changes, yet it remains unclear about the resulting global transboundary health impacts. Here we show that between 1950 and 2014, global anthropogenic PM2.5 has led to 185.7 million premature deaths cumulatively, including about 14% from transboundary pollution. Among four country groups at different affluence levels, on a basis of per capita contribution to transboundary mortality, a richer region tends to exert severer cumulative health externality, with the poorest bearing the worst net externality after contrasting import and export of pollution mortality. The temporal changes in transboundary mortality and cross-regional inequality are substantial. Effort to reduce PM2.5-related transboundary mortality should seek international collaborative strategies that account for historical responsibility and inequality.

Hybrid interpretable predictive machine learning model for air pollution prediction

Air pollution prediction is a burning issue, as pollutants can harm human health. Traditional machine learning models usually aim to improve the overall prediction accuracy but neglect the accuracy for peak values. Moreover, these models are not interpretable. They fail to explain the interactions between various determining factors and their impacts on air pollution. In this paper, we propose a new Hybrid Interpretable Predictive Machine Learning model for the Particulate Matter 2.5 prediction, which carries two novelties. First, a hybrid model structure is constructed with deep neural network and Nonlinear Auto Regressive Moving Average with Exogenous Input model. Second, automatic feature generation and feature selection procedures are integrated into this hybrid model. The experimental results demonstrate the superiority of our model over other models in prediction accuracy for peak values and model interpretability. The proposed model reveals how PM2.5 prediction is estimated by historical PM2.5, weather, and season. The accuracies (measured by correlation coefficients) of 1, 3 and 6-hour-ahead prediction are 0.9870, 0.9332 and 0.8587, respectively. More importantly, the proposed approach presents a new interpretable machine learning framework for time series data, enabling to explain complex dependence of multimode inputs, and to build reliable predictive models.

A satellite-derived, ground-measurement-independent monthly PM2.5 mass concentration dataset over China during 2000 - 2015

ABSTRACT Following the accelerated development of urbanization and industrialization, atmospheric particulate matter has become a significant threat to public health globally. Environmental health studies usually use the mass concentration of fine particles (PM2.5) as a base data to predict the health risks of particulate exposure. However, PM2.5 data from ground monitoring stations in China has not been provided until January 2013 by the Ministry of Environmental Protection of China. Hence, an alternative dataset of PM2.5 spatiotemporal distributions extending to years earlier than 2013 is urgently needed, which is of great significance to atmospheric environment assessment and pollution prevention and control. Atmospheric aerosol products by the moderate-resolution imaging spectroradiometer (MODIS) have been released since 2000, which provides the possibility to reconstruct historical PM2.5. However, most current methods do not have the ability to estimate PM2.5 mass concentration independently of ground observations. The PM2.5 mass concentration data set produced by PM2.5 remote sensing (PMRS) model based on physical processes does not depend on the ground observations, and also is not affected by the uncertainty of model emission sources or the completeness of chemical reaction mechanism. These ensure that the point-by-point validation for PM2.5 mass concentration data is more convincing, and the dataset can also be further used for model assimilation and artificial intelligence training to improve their predictions. In this study, we calculate the monthly PM2.5 mass concentration near the ground over land of China using aerosol inversion products (aerosol optical depth and fine-mode fraction) of MODIS and meteorological data (boundary layer height & relative humidity) provided by the Modern-Era Retrospective Analysis for Research and Applications Version 2 (MERRA-2) data set. The results show that, in China, 6 pollution centers mainly concentrated in the central and eastern regions. The highest PM2.5 mass concentration occurred in winter, whereas the pollution range was larger in summer. There are 63.4% of validation sites with biases within ±20 μg m−3, and the expected error is as ±(15 μg m−3 + 30%) enveloped by the monthly mean PM2.5 mass concentrations. The monthly PM2.5 is stored as NETCDF format, with a spatial resolution of 1°×1°. The published data is available in http://www.dx.doi.org/10.11922/sciencedb.j00076.00061.

Sixteen years analysis of PM2.5 and mortality in Kuwait

BACKGROUND AND AIM: Middle Eastern desert countries like Kuwait are notoriously known for dramatic dust storms and enormous petrochemical industries affecting ambient air pollution. However, local health authorities have not been able to assess health impacts of air pollution due to limited monitoring networks and lack of historical exposure data. We aimed to estimate the relationship between estimated historical fine particulate matter (PM2.5) and mortality in Kuwait stratified by cause, gender and age. METHODS: We developed a novel approach using machine learning and remote sensing to estimate spatially and temporally resolved daily urban PM2.5 exposures from 2001 to 2016 in the country. We then used over-dispersed generalized additive models to investigate the association with cause-specific, gender- and age-stratified mortality timeseries. RESULTS:There was a total of 70,321 deaths during the study period of 16 years. The average urban PM2.5 was estimated to be 46.2±19.8 µg/m3. A 10 µg/m3 increase in a 5-day moving average of urban PM2.5 was associated with 1.31% (95% CI: 0.56 to 2.07%) increase in all-cause mortality and a 1.15% (0.13 to 2.18%) increase in daily cardiovascular deaths. The corresponding associations among males and females were 1.23% (0.29 to 2.17%) and 1.44% (0.33 to 2.56%), respectively. For the elderly (above 65 years) there was a 1.23% (0.15 to 2.31%) increase in all-cause mortality. The associations were unchanged after adjusting for dust storm days. CONCLUSIONS:We leveraged available pollution, weather and remote sensing data to predict historical PM2.5 with high temporal and spatial resolution. Urban PM2.5 concentrations were above the international regulatory limits. Our findings suggest that, PM2.5 is associated with increased mortality across different strata of the Kuwaiti population. The approach we used can be implemented in other countries that lack historical pollution data or those with insufficient monitoring networks. KEYWORDS: Desert, Dust storm, Kuwait, Middle East, Air Pollution, Machine Learning

Estimations of ambient fine particle and ozone level at a suburban site of Beijing in winter

Estimates of PM2.5 and O3 in suburban areas are of importance for assessing exposure risk and epidemiological studies of air pollution where large scale and long-term measurements network are absent. To fulfill this goal, our study develops a flexible approach to predict levels of PM2.5 and O3 at a suburban site of Beijing using multilayer perceptron (MLP) neural network analysis with the inputs of gaseous air pollutants (CO, SO2, NO, and NO2) and meteorological parameters (wind direction, wind speed, temperature, pressure and humidity). Daily ambient data of PM2.5, O3, PM10, CO, SO2, NO, and NO2 were estimated using hourly data collected from January 20 to March 10 in the years from 2016–2020 at a suburban site of Beijing, respectively. Ambient measured levels of PM2.5 and O3 were compared with the output estimates of PM2.5 and O3 through MLP neural network analysis with limited input variables. Overall, MLP neural network analysis could explain 97% of measured PM2.5 mass and 82% of measured O3 level with R2 values of 0.983 and 0.905, respectively. This approach could be helpful for reconstruct historical PM2.5 and O3 levels in suburban areas.

Integration of complete ensemble empirical mode decomposition with deep long short-term memory model for particulate matter concentration prediction.

The atmospheric particulate matter (PM) with a diameter of 2.5 μm or less (PM2.5) is one of the key indicators of air pollutants. Accurate prediction of PM2.5 concentration is very important for air pollution monitoring and public health management. However, the presence of noise in PM2.5 data series is a major challenge of its accurate prediction. A novel hybrid PM2.5 concentration prediction model is proposed in this study by combining complete ensemble empirical mode decomposition (CEEMD) method, Pearson's correlation analysis, and a deep long short-term memory (LSTM) method. CEEMD was employed to decompose historical PM2.5 concentration data to different frequencies in order to enhance the timing characteristics of data. Pearson's correlation was used to screen the different frequency intrinsic-mode functions of decomposed data. Finally, the filtered enhancement data were inputted to a deep LSTM network with multiple hidden layers for training and prediction. The results evidenced the potential of the CEEMD-LSTM hybrid model with a prediction accuracy of approximately 80% and model convergence after 700 training epochs. The secondary screening of Pearson's correlation test improved the model (CEEMD-Pearson) accuracy up to 87% but model convergence after 800 epochs. The hybrid model combining CEEMD-Pearson with the deep LSTM neural network showed a prediction accuracy of nearly 90% and model convergence after 650 interactions. The results provide a clear indication of higher prediction accuracy of PM2.5 with less computation time through hybridization of CEEMD-Pearson with deep LSTM models and its potential to be employed for air pollution monitoring.

Activity-determined Steps on the Attenuation of Atmospheric PM2.5 Concentration Environmental Kuznets Curve (EKC) at the Country Level: Empirical Evidence in Taiwan

Finding ways to minimize the atmospheric concentration of PM2.5 is an emergency issue throughout the world. This research has found a method to calculate historical PM2.5 data and to define the PM2.5 environmental Kuznets curve (EKC) pattern in Taiwan. From the analysis of the Taiwan Environmental Protection Agency’s public emission data, results showed that the continuous decay of PM2.5 is mostly contributed by the energy policy, while several short-term regular stepwise fluctuations in PM2.5 concentrations are caused by natural activity. Our study also proved that the linear decay with stepwise fluctuations also exhibits an EKC pattern.&#x0D; The results herein mean that the continuous decay of PM2.5 is caused by the energy policy, while the regular fluctuation of PM2.5 concentrations is caused by natural activity, like the La Nino phenomena. Based on the viewpoint of this paper, the oil consumption percentage for electricity generation should be first reduced to zero. However, oil-based power plants are an important emergency source of electricity supply. If Taiwan wants to continue the reduction of PM2.5 in the future, then a big capacity electric storage facility should be built as an emergency source of electricity supply. The energy policy in Taiwan at 2025 will be 50% natural gas, 30% coal, and 20% green energy. As oil fuel will reach 0%, PM2.5 will be affected by the energy intensity contributed from coal and natural gas, meaning that PM2.5 will maintain a long-term attenuation trend until 2035.

A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction

Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks.

A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings

Due to the severe outdoor PM2.5 pollution in China, many people have installed air-cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2h and the prediction horizon is 30min, the median prediction error is 8.3µg/m3 for the whole test set. For times with indoor PM2.5 concentrations between (20,50]µg/m3 and (50,100]µg/m3 , the median prediction error is 8.3 and 9.2µg/m3 , respectively. The low prediction error between the ground-truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance.

Robust prediction of hourly PM2.5 from meteorological data using LightGBM.

Retrieving historical fine particulate matter (PM2.5) data is key for evaluating the long-term impacts of PM2.5 on the environment, human health and climate change. Satellite-based aerosol optical depth has been used to estimate PM2.5, but estimations have largely been undermined by massive missing values, low sampling frequency and weak predictive capability. Here, using a novel feature engineering approach to incorporate spatial effects from meteorological data, we developed a robust LightGBM model that predicts PM2.5 at an unprecedented predictive capacity on hourly (R2 = 0.75), daily (R2 = 0.84), monthly (R2 = 0.88) and annual (R2 = 0.87) timescales. By taking advantage of spatial features, our model can also construct hourly gridded networks of PM2.5. This capability would be further enhanced if meteorological observations from regional stations were incorporated. Our results show that this model has great potential in reconstructing historical PM2.5 datasets and real-time gridded networks at high spatial-temporal resolutions. The resulting datasets can be assimilated into models to produce long-term re-analysis that incorporates interactions between aerosols and physical processes.

Constructing a spatiotemporally coherent long-term PM2.5 concentration dataset over China during 1980–2019 using a machine learning approach

The lack of long-term observations and satellite retrievals of health-damaging fine particulate matter in China has demanded the estimates of historical PM2.5 (particulate matter less than 2.5 μm in diameter) concentrations. This study constructs a gridded near-surface PM2.5 concentration dataset across China covering 1980–2019 using the space-time random forest model with atmospheric visibility observations and other auxiliary data. The modeled daily PM2.5 concentrations are in excellent agreement with ground measurements, with a coefficient of determination of 0.95 and mean relative error of 12%. Besides the atmospheric visibility which explains 30% of total importance of variables in the model, emissions and meteorological conditions are also key factors affecting PM2.5 predictions. From 1980 to 2014, the model-predicted PM2.5 concentrations increased constantly with the maximum growth rate of 5–10 μg/m3/decade over eastern China. Due to the clean air actions, PM2.5 concentrations have decreased effectively at a rate over 50 μg/m3/decade in the North China Plain and 20–50 μg/m3/decade over many regions of China during 2014–2019. The newly generated dataset of 1-degree gridded PM2.5 concentrations for the past 40 years across China provides a useful means for investigating interannual and decadal environmental and climate impacts related to aerosols.

Estimating PM2.5 concentrations in Northeastern China with full spatiotemporal coverage, 2005–2016

Predicting long-term spatiotemporal characteristics of fine particulate matter (PM2.5) is important in China to understand historical levels of PM2.5, to support health effects research of both long-term and short-term exposures to PM2.5, and to evaluate the efficacy of air pollution control policies. Satellite-retrieved aerosol optical depth (AOD) provides a unique opportunity to characterize the long-term trends of ground-level PM2.5 at high spatial resolution. However, the missing rate of AOD in Northeastern China (NEC) is very high, especially in winter, and challenges the accuracy of long-term predictions of PM2.5 if left unresolved. Using random forest algorithms, this study developed a gap-filling approach combing satellite AOD, meteorological data, land use parameters, population and visibility in the NEC during 2005–2016. The model, including all predictors, combined with a model without AOD was able to fill the gap of PM2.5 predictions caused by missing AOD at 1-km resolution. The R2 (RMSE) of the full-coverage predictions was 0.81 (18.5 μg/m3) at the daily level. Gap-filled PM2.5 predictions on days with missing AOD reduced the relative prediction error from 28% to 2.5% in winter. The leave-one-year-out-cross-validation R2 (RMSE) of the full-coverage predictions was 0.65 (16.3 μg/m3) at the monthly level, indicating relatively high accuracy of predicted historical PM2.5 concentrations. Our results suggested that AOD helped increase the reliability of historical PM2.5 prediction when ground PM2.5 measurements were unavailable, even though predictions from the AOD model only accounted for approximate 37% of the whole dataset. Predicted PM2.5 level in NEC have increased since 2005, reached its peak during 2013–2015, then saw a major decline in 2016. Our high-resolution predictions also showed a south to north gradient and many pollution hot spots in the city clusters surrounding provincial capitals, as well as within large cities. Overall, by combining predictions from the AOD model with higher accuracy and predictions from the non-AOD model to achieve full coverage, our modeling approach could produce long-term, full-coverage historical PM2.5 levels in high-latitude areas in China, despite the widespread and persistent AOD missingness.

An improved deep learning model for predicting daily PM2.5 concentration.

Over the past few decades, air pollution has caused serious damage to public health. Therefore, making accurate predictions of PM2.5 is a crucial task. Due to the transportation of air pollutants among areas, the PM2.5 concentration is strongly spatiotemporal correlated. However, the distribution of air pollution monitoring sites is not even making the spatiotemporal correlation between the central site and surrounding sites vary with different density of sites, and this was neglected by previous methods. To this end, this study proposes a weighted long short-term memory neural network extended model (WLSTME), which addressed the issue that how to consider the effect of the density of sites and wind conditions on the spatiotemporal correlation of air pollution concentration. First, a number of nearest surrounding sites were chosen as the neighbor sites to the central site, and their distance, as well as their air pollution concentration and wind condition, were input to multilayer perception (MLP) to generate weighted historical PM2.5 time series data. Second, historical PM2.5 concentration of the central site and weighted PM2.5 series data of neighbor sites were input into a long short-term memory (LSTM) to address spatiotemporal dependency simultaneously and extract spatiotemporal features. Finally, another MLP was utilized to integrate spatiotemporal features extracted above with the meteorological data of the central site to generate the forecasts future PM2.5 concentration of the central site. Daily PM2.5 concentration and meteorological data on Beijing–Tianjin–Hebei from 2015 to 2017 were collected to train models and to evaluate its performance. Experimental results with three existing methods showed that the proposed WLSTME model has the lowest RMSE (40.67) and MAE (26.10) and the highest p (0.59). Further experiments showed that in all seasons and regions, WLSTME performed the best. This finding confirms that WLSTME can significantly improve PM2.5 prediction accuracy.

Air pollution and COVID-19 mortality in the United States: Strengths and limitations of an ecological regression analysis.

Assessing whether long-term exposure to air pollution increases the severity of COVID-19 health outcomes, including death, is an important public health objective. Limitations in COVID-19 data availability and quality remain obstacles to conducting conclusive studies on this topic. At present, publicly available COVID-19 outcome data for representative populations are available only as area-level counts. Therefore, studies of long-term exposure to air pollution and COVID-19 outcomes using these data must use an ecological regression analysis, which precludes controlling for individual-level COVID-19 risk factors. We describe these challenges in the context of one of the first preliminary investigations of this question in the United States, where we found that higher historical PM2.5 exposures are positively associated with higher county-level COVID-19 mortality rates after accounting for many area-level confounders. Motivated by this study, we lay the groundwork for future research on this important topic, describe the challenges, and outline promising directions and opportunities.

Investigating a Potential Map of PM2.5 Air Pollution and Risk for Tourist Attractions in Hsinchu County, Taiwan.

In the past few years, human health risks caused by fine particulate matters (PM2.5) and other air pollutants have gradually received attention. According to the Disaster Prevention and Protection Act of Taiwan’s Government enforced in 2017, “suspended particulate matter” has officially been acknowledged as a disaster-causing hazard. The long-term exposure to high concentrations of air pollutants negatively affects the health of citizens. Therefore, the precise determination of the spatial long-term distribution of hazardous high-level air pollutants can help protect the health and safety of residents. The analysis of spatial information of disaster potentials is an important measure for assessing the risks of possible hazards. However, the spatial disaster-potential characteristics of air pollution have not been comprehensively studied. In addition, the development of air pollution potential maps of various regions would provide valuable information. In this study, Hsinchu County was chosen as an example. In the spatial data analysis, historical PM2.5 concentration data from the Taiwan Environmental Protection Administration (TWEPA) were used to analyze and estimate spatially the air pollution risk potential of PM2.5 in Hsinchu based on a geographic information system (GIS)-based radial basis function (RBF) spatial interpolation method. The probability that PM2.5 concentrations exceed a standard value was analyzed with the exceedance probability method; in addition, the air pollution risk levels of tourist attractions in Hsinchu County were determined. The results show that the air pollution risk levels of the different seasons are quite different. The most severe air pollution levels usually occur in spring and winter, whereas summer exhibits the best air quality. Xinfeng and Hukou Townships have the highest potential for air pollution episodes in Hsinchu County (approximately 18%). Hukou Old Street, which is one of the most important tourist attractions, has a relatively high air pollution risk. The analysis results of this study can be directly applied to other countries worldwide to provide references for tourists, tourism resource management, and air quality management; in addition, the results provide important information on the long-term health risks for local residents in the study area.

A hybrid deep learning model with multi-source data for PM2.5 concentration forecast

Air quality forecast is an important technical means to ensure timely and proper response to heavy pollution weather. In this study, a hybrid deep air quality predictor (HDAQP) model consisting of one-dimensional convolutional neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN) is proposed to forecast air quality indicators (mainly PM2.5 concentrations). The proposed model can overcome the limitations of the single model and meanwhile make the best of each. CNN model is used to convolve the historical PM2.5 concentration data along with meteorological data to extract shallow features, while LSTM model is used to extract the deep temporal features. Finally, the DNN model is adopted to transfer these deep features into the final forecast results. Compared with the mainstream deep learning models (e.g., RNN, LSTM, and CNN-LSTM models), the HDAQP model exhibits a better performance in short-term PM2.5 concentration forecast. With the increase of prediction time, the long-term prediction performance of the HDAQP model will be degraded, but it is still better than the mainstream deep learning models. Moreover, considering other meteorological factors, with the multi-source data, the HDAQP model can forecast PM2.5 concentrations more accurately.