RESUMEN

Air pollution is a serious challenge to humankind as it poses many health threats. It can be measured using the air quality index (AQI). Air pollution is the result of contamination of both outdoor and indoor environments. The AQI is being monitored by various institutions globally. The measured air quality data are kept mostly for public use. Using the previously calculated AQI values, the future values of AQI can be predicted, or the class/category value of the numeric value can be obtained. This forecast can be performed with more accuracy using supervised machine learning methods. In this study, multiple machine-learning approaches were used to classify PM2.5 values. The values for the pollutant PM2.5 were classified into different groups using machine learning algorithms such as logistic regression, support vector machines, random forest, extreme gradient boosting, and their grid search equivalents, along with the deep learning method multilayer perceptron. After performing multiclass classification using these algorithms, the parameters accuracy and per-class accuracy were used to compare the methods. As the dataset used was imbalanced, a SMOTE-based approach for balancing the dataset was used. Compared to all other classifiers that use the original dataset, the accuracy of the random forest multiclass classifier with SMOTE-based dataset balancing was found to provide better accuracy.

RESUMEN

Reliable long-horizon PM2.5 forecasts are crucial and beneficial for health protection through early warning against air pollution. However, the dynamic nature of air quality makes PM2.5 forecasts at long horizons very challenging. This study proposed a novel machine learning-based model (MCNN-BP) that fused multiple convolutional neural networks (MCNN) with a back-propagation neural network (BPNN) for making spatiotemporal PM2.5 forecasts for the next 72 h at 74 stations covering the whole Taiwan simultaneously. Model configuration involved an ensemble of massive hourly air quality and meteorological monitoring datasets and the existing publicly-available PM2.5 simulated (forecasted) datasets from an atmospheric chemical transport (ACT) model. The proposed methodology collaboratively constructed two CNNs to mine the observed data (the past) and the forecasted data from ACT (the future) separately. The results showed that the MCNN-BP model could significantly improve the accuracy of spatiotemporal PM2.5 forecasts and substantially reduce the forecast biases of the ACT model. We demonstrated that the proposed MCNN-BP model with effective feature extraction and good denoising ability could overcome the curse of dimensionality and offer satisfactory regional long-horizon PM2.5 forecasts. Moreover, the MCNN-BP model has considerably shorter computational time (5 min) and lower computational load than the compute-intensive ACT model. The proposed approach hits a milestone in multi-site and multi-horizon forecasting, which significantly contributes to early warning against regional air pollution.

Asunto(s)

RESUMEN

Accurate air quality forecasts can provide data-driven supports for governmental departments to control air pollution and further protect the health of residents. However, existing air quality forecasting models mainly focus on site-specific time series forecasts at a local level, and rarely consider the spatiotemporal relationships among regional monitoring stations. As a novelty, we construct a diffusion convolutional recurrent neural network (DCRNN) model that fully considers the influence of geographic distance and dominant wind direction on the regional variations in air quality through different combinations of directed and undirected graphs. The hourly fine particulate matter (PM2.5) and ozone data from 123 air quality monitoring stations in the Yangtze River Delta, China are used to evaluate the performance of the DCRNN model in the regional prediction of PM2.5 and ozone concentrations. Results show that the proposed DCRNN model outperforms the baseline models in prediction accuracy. Compared with the undirected graph model, the directed graph model considering the effects of wind direction performs better in 24 h predictions of pollutant concentrations. In addition, more accurate forecasts of both PM2.5 and ozone are found at a regional level where monitoring stations are distributed densely rather than sparsely. Therefore, the proposed model can assist environmental researchers to further improve the technologies of air quality forecasts and could also serve as tools for environmental policymakers to implement pollution control measures.

Asunto(s)

RESUMEN

In this work, we use observations and experimental emissions in a version of NOAA's National Air Quality Forecasting Capability to show that the COVID-19 economic slowdown led to disproportionate impacts on near-surface ozone concentrations across the contiguous U.S. (CONUS). The data-fusion methodology used here includes both U.S. EPA Air Quality System ground and the NASA Aura satellite Ozone Monitoring Instrument (OMI) NO2 observations to infer the representative emissions changes due to the COVID-19 economic slowdown in the U.S. Results show that there were widespread decreases in anthropogenic (e.g., NOx) emissions in the U.S. during March-June 2020, which led to widespread decreases in ozone concentrations in the rural regions that are NOx-limited, but also some localized increases near urban centers that are VOC-limited. Later in June-September, there were smaller decreases, and potentially some relative increases in NOx emissions for many areas of the U.S. (e.g., south-southeast) that led to more extensive increases in ozone concentrations that are partly in agreement with observations. The widespread NOx emissions changes also alters the O3 photochemical formation regimes, most notably the NOx emissions decreases in March-April, which can enhance (mitigate) the NOx-limited (VOC-limited) regimes in different regions of CONUS. The average of all AirNow hourly O3 changes for 2020-2019 range from about +1 to -4 ppb during March-September, and are associated with predominantly urban monitoring sites that demonstrate considerable spatiotemporal variability for the 2020 ozone changes compared to the previous five years individually (2015-2019). The simulated maximum values of the average O3 changes for March-September range from about +8 to -4 ppb (or +40 to -10%). Results of this work have implications for the use of widespread controls of anthropogenic emissions, particularly those from mobile sources, used to curb ozone pollution under the current meteorological and climate conditions in the U.S.

RESUMEN

Statistical methods such as multiple linear regression (MLR) and classification and regression tree (CART) analysis were used to build prediction models for the levels of pollutant concentrations in Macao using meteorological and air quality historical data to three periods: (i) from 2013 to 2016, (ii) from 2015 to 2018, and (iii) from 2013 to 2018. The variables retained by the models were identical for nitrogen dioxide (NO2), particulate matter (PM10), PM2.5, but not for ozone (O3) Air pollution data from 2019 was used for validation purposes. The model for the 2013 to 2018 period was the one that performed best in prediction of the next-day concentrations levels in 2019, with high coefficient of determination (R2), between predicted and observed daily average concentrations (between 0.78 and 0.89 for all pollutants), and low root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). To understand if the prediction model was robust to extreme variations in pollutants concentration, a test was performed under the circumstances of a high pollution episode for PM2.5 and O3 during 2019, and the low pollution episode during the period of implementation of the preventive measures for COVID-19 pandemic. Regarding the high pollution episode, the period of the Chinese National Holiday of 2019 was selected, in which high concentration levels were identified for PM2.5 and O3, with peaks of daily concentration exceeding 55 µg/m3 and 400 µg/m3, respectively. The 2013 to 2018 model successfully predicted this high pollution episode with high coefficients of determination (of 0.92 for PM2.5 and 0.82 for O3). The low pollution episode for PM2.5 and O3 was identified during the 2020 COVID-19 pandemic period, with a low record of daily concentration for PM2.5 levels at 2 µg/m3 and O3 levels at 50 µg/m3, respectively. The 2013 to 2018 model successfully predicted the low pollution episode for PM2.5 and O3 with a high coefficient of determination (0.86 and 0.84, respectively). Overall, the results demonstrate that the statistical forecast model is robust and able to correctly reproduce extreme air pollution events of both high and low concentration levels.

Asunto(s)

RESUMEN

The new-generation geostationary satellites feature higher radiometric, spectral, and spatial resolutions, thereby making richer data available for the improvement of PM2.5 predictions. Various aerosol optical depth (AOD) data assimilation methods have been developed, but the accurate representation of the AOD-PM2.5 relationship remains challenging. Empirical statistical methods are effective in retrieving ground-level PM2.5, but few have been evaluated in terms of whether and to what extent they can help improve PM2.5 predictions. Therefore, an empirical and statistics-based scheme was developed for optimizing the estimation of the initial conditions (ICs) of aerosol in WRF-Chem (Weather Research and Forecasting/Chemistry) and for improving the PM2.5 predictions by integrating Himawari-8 data and ground observations. The proposed method was evaluated via two one-year experiments that were conducted in parallel over eastern China. The contribution of the satellite data to the model performance was evaluated via a 2-week control experiment. The results demonstrate that the proposed method improved the PM2.5 predictions throughout the year and mitigated the underestimation during pollution episodes. Spatially, the performance was highly correlated with the amount of valid data.

Asunto(s)

RESUMEN

In the era of big data, a variety of factors (particularly meteorological factors) have been applied to PM2.5 concentration prediction, revealing a clear discrepancy in timescale. To capture the complicated multi-scale relationship with PM2.5-related factors, a novel multi-factor & multi-scale method is proposed for PM2.5 forecasting. Three major steps are taken: (1) multi-factor analysis, to select predictive factors via statistical tests; (2) multi-scale analysis, to extract scale-aligned components via multivariate empirical mode decomposition; and (3) PM2.5 prediction, including individual prediction at each timescale and ensemble prediction across different timescales. The empirical study focuses on the PM2.5 of Cangzhou, which is one of the most air-polluted cities in China, and indicates that the proposed multi-factor & multi-scale learning paradigms statistically outperform their corresponding original techniques (without multi-factor and multi-scale analysis), semi-improved variants (with either multi-factor or multi-scale analysis), and similar counterparts (with other multi-scale analyses) in terms of prediction accuracy.

Asunto(s)

RESUMEN

Air pollution is a global problem and can be perceived as a modern-day curse. One way of dealing with it is by finding economical ways to monitor and forecast air quality. Accurately monitoring and forecasting fine particulate matter (PM2.5) concentrations is a challenging prediction task but Internet of Things (IoT) can help in developing economical and agile ways to design such systems. In this paper, we use a historical data-based approach to perform PM2.5 forecasting. A forecasting method is developed which uses exponential smoothing with drift. Experiments and evaluation were performed using the real-time PM2.5 data obtained from large scale deployment of IoT devices in Taichung region in Taiwan. We used the data from 132 monitoring stations to evaluate our model's performance. A comparison of prediction accuracy and computation time between the proposed model and three widely used forecasting models was done. The results suggest that our method can perform PM2.5 forecast for 132 monitoring stations with error as low as 0.16 µ g/ m 3 and also with an acceptable computation time of 30 s. Further evaluation was done by forecasting PM2.5 for next 3 h. The results show that 90 % of the monitoring stations have error under 1.5 µ g/ m 3 which is significantly low.

RESUMEN

A stacked ensemble model is developed for forecasting and analyzing the daily average concentrations of fine particulate matter (PM2.5) in Beijing, China. Special feature extraction procedures, including those of simplification, polynomial, transformation and combination, are conducted before modeling to identify potentially significant features based on an exploratory data analysis. Stability feature selection and tree-based feature selection methods are applied to select important variables and evaluate the degrees of feature importance. Single models including LASSO, Adaboost, XGBoost and multi-layer perceptron optimized by the genetic algorithm (GA-MLP) are established in the level 0 space and are then integrated by support vector regression (SVR) in the level 1 space via stacked generalization. A feature importance analysis reveals that nitrogen dioxide (NO2) and carbon monoxide (CO) concentrations measured from the city of Zhangjiakou are taken as the most important elements of pollution factors for forecasting PM2.5 concentrations. Local extreme wind speeds and maximal wind speeds are considered to extend the most effects of meteorological factors to the cross-regional transportation of contaminants. Pollutants found in the cities of Zhangjiakou and Chengde have a stronger impact on air quality in Beijing than other surrounding factors. Our model evaluation shows that the ensemble model generally performs better than a single nonlinear forecasting model when applied to new data with a coefficient of determination (R2) of 0.90 and a root mean squared error (RMSE) of 23.69µg/m3. For single pollutant grade recognition, the proposed model performs better when applied to days characterized by good air quality than when applied to days registering high levels of pollution. The overall classification accuracy level is 73.93%, with most misclassifications made among adjacent categories. The results demonstrate the interpretability and generalizability of the stacked ensemble model.

Asunto(s)

RESUMEN

Many regions in China experience air pollution episodes because of the rapid urbanization and industrialization over the past decades. Here we analyzed the effect of emission controls implemented during the G-20 2016 Hangzhou summit on air quality. Emission controls included a forced closure of highly polluting industries, and limiting traffic and construction emissions in the cities and surroundings. Particles with aerodynamic diameter lower than 2.5 µm (PM2.5) and ozone (O3) were measured. We also simulated air quality using a forecast system consisting of the two-way coupled Weather Research and Forecast and Community Multi-scale Air Quality (WRF-CMAQ) model. Results show PM2.5 and ozone levels in Hangzhou during the G-20 Summit were considerably lower than previous to the G-20 Summit. The predicted concentrations of ozone were reduced by 25.4%, whereas the predicted concentrations of PM2.5 were reduced by 56%.