scholarly journals Temporal Difference-based Graph Transformer Networks for Air Quality PM2.5 Prediction: A Case Study in China

2022 ◽  
Author(s):  
Zhen Zhang ◽  
Shiqing Zhang ◽  
Xiaoming Zhao ◽  
Linjian Chen ◽  
Jun Yao
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Attention Mechanism ◽  
Quality Prediction ◽  
Temporal Difference ◽  
Short Term ◽  
Air Quality Prediction ◽  
Complex Relationships

Abstract The acceleration of industrialization and urbanization has recently brought about serious air pollution problems, which threaten human health and lives, the environmental safety, and sustainable social development. Air quality prediction is an effective approach for providing early warning of air pollution and supporting cleaner industrial production. However, existing approaches have suffered from a weak ability to capture long-term dependencies and complex relationships from time series PM2.5 data. To address this problem, this paper proposes a new deep learning model called temporal difference-based graph transformer networks (TDGTN) to learn long-term temporal dependencies and complex relationships from time series PM2.5 data for air quality PM2.5 prediction. The proposed TDGTN comprises of encoder and decoder layers associated with the developed graph attention mechanism. In particular, considering the similarity of different time moments and the importance of temporal difference between two adjacent moments for air quality prediction, we first construct graph-structured data from original time series PM2.5 data at different moments without explicit graph structure. Then, based on the constructed graph, we improve the self-attention mechanism with the temporal difference information, and develop a new graph attention mechanism. Finally, the developed graph attention mechanism is embedded into the encoder and decoder layers of the proposed TDGTN to learn long-term temporal dependencies and complex relationships from a graph prospective on air quality PM2.5 prediction tasks. To verify the effectiveness of the proposed method, we conduct air quality prediction experiments on two real-world datasets in China, such as Beijing PM2.5 dataset ranging from 01/01/2010 to 12/31/2014 and Taizhou PM2.5 dataset ranging from 01/01/2017 to 12/31/2019. Compared with other air quality forecasting methods, such as autoregressive moving average (ARMA), support vector regression (SVR), convolutional neural network (CNN), long short-term memory (LSTM), the original Transformer, our experiment results indicate that the proposed method achieves more accurate results on both short-term (1 hour) and long-term (6, 12, 24, 48 hours) air quality prediction tasks.

scholarly journals Prediction of Ambient PM2.5 Concentrations Using a Correlation Filtered Spatial-Temporal Long Short-Term Memory Model

2019 ◽  
Vol 10 (1) ◽  
pp. 14 ◽  
Author(s):  
Yuexiong Ding ◽  
Zheng Li ◽  
Chengdian Zhang ◽  
Jun Ma
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Quality Prediction ◽  
Short Term ◽  
Concentration Data ◽  
Term Memory ◽  
Air Quality Prediction ◽  
Long Short Term Memory

Due to the increasingly serious air pollution problem, air quality prediction has been an important approach for air pollution control and prevention. Many prediction methods have been proposed in recent years to improve the prediction accuracy. However, most of the existing methods either did not consider the spatial relationships between monitoring stations or overlooked the strength of the correlation. Excluding the spatial correlation or including too much weak spatial inputs could influence the modeling and reduce the prediction accuracy. To overcome the limitation, this paper proposes a correlation filtered spatial-temporal long short-term memory (CFST-LSTM) model for air quality prediction. The model is designed based on the original LSTM model and is equipped with a spatial-temporal filter (STF) layer. This layer not only takes into account the spatial influence between stations, but also can extract highly correlated sequential data and drop weaker ones. To evaluate the proposed CFST-LSTM model, hourly PM2.5 concentration data of California are collected and preprocessed. Several experiments are conducted. The experimental results show that the CFST-LSTM model can effectively improve the prediction accuracy and has great generalization.

scholarly journals Air Pollution and Mortality: Timing Is Everything

Atmosphere ◽  
2020 ◽  
Vol 11 (12) ◽  
pp. 1274
Author(s):  
Frederick W. Lipfert
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Indoor Air Pollution ◽  
Health Effect ◽  
Traffic Density ◽  
Long Term Effects ◽  
Short Term ◽  
Long Term Studies

This paper considers timing issues in health-effect exposure and response studies. Short-term studies must consider delayed and cumulative responses; prior exposures, disease latency, and cumulative impacts are required for long-term studies. Lacking individual data, long-term air quality describes locations, as do greenspaces and traffic density, rather than exposures of residents. Indoor air pollution can bias long-term exposures and effect estimates but short-term effects also respond to infiltrated outdoor air. Daily air quality fluctuations may affect the frail elderly and are necessarily included in long-term averages; any true long-term effects must be given by differences between annual and daily effects. I found such differences to be negligible after adjusting for insufficient lag effects in time-series studies and neglect of prior exposures in long-term studies. Aging of subjects under study implies cumulative exposures, but based on age-specific mortality, I found relative risks decreasing with age, precluding cumulative effects. A new type of time-series study found daily mortality of previously frail subjects to be associated with various pollutants without exposure thresholds, but the role of air pollution in the onset of frailty remains an unexplored issue. The importance of short-term fluctuations has been underestimated and putative effects of long-term exposures have been overestimated.

scholarly journals Air Quality Prediction in Smart Cities Using Machine Learning Technologies based on Sensor Data: A Review

2020 ◽  
Vol 10 (7) ◽  
pp. 2401 ◽  
Author(s):  
Ditsuhi Iskandaryan ◽  
Francisco Ramos ◽  
Sergio Trilles
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Air Quality ◽  
Smart Cities ◽  
Learning Technologies ◽  
Sensor Data ◽  
Quality Prediction ◽  
Air Quality Prediction ◽  
Air Pollution Prediction ◽  
Pollution Prediction

The influence of machine learning technologies is rapidly increasing and penetrating almost in every field, and air pollution prediction is not being excluded from those fields. This paper covers the revision of the studies related to air pollution prediction using machine learning algorithms based on sensor data in the context of smart cities. Using the most popular databases and executing the corresponding filtration, the most relevant papers were selected. After thorough reviewing those papers, the main features were extracted, which served as a base to link and compare them to each other. As a result, we can conclude that: (1) instead of using simple machine learning techniques, currently, the authors apply advanced and sophisticated techniques, (2) China was the leading country in terms of a case study, (3) Particulate matter with diameter equal to 2.5 micrometers was the main prediction target, (4) in 41% of the publications the authors carried out the prediction for the next day, (5) 66% of the studies used data had an hourly rate, (6) 49% of the papers used open data and since 2016 it had a tendency to increase, and (7) for efficient air quality prediction it is important to consider the external factors such as weather conditions, spatial characteristics, and temporal features.

scholarly journals Effects of meteorology and emissions on urban air quality: a quantitative statistical approach to long-term records (1999–2016) in Seoul, South Korea

2018 ◽  
Vol 18 (21) ◽  
pp. 16121-16137 ◽  
Author(s):  
Jihoon Seo ◽  
Doo-Sun R. Park ◽  
Jin Young Kim ◽  
Daeok Youn ◽  
Yong Bin Lim ◽  
...  
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
South Korea ◽  
Meteorological Conditions ◽  
Meteorological Variables ◽  
Urban Air ◽  
Short Term ◽  
Long Term Trends ◽  
Local Emissions

Abstract. Together with emissions of air pollutants and precursors, meteorological conditions play important roles in local air quality through accumulation or ventilation, regional transport, and atmospheric chemistry. In this study, we extensively investigated multi-timescale meteorological effects on the urban air pollution using the long-term measurements data of PM10, SO2, NO2, CO, and O3 and meteorological variables over the period of 1999–2016 in Seoul, South Korea. The long-term air quality data were decomposed into trend-free short-term components and long-term trends by the Kolmogorov–Zurbenko filter, and the effects of meteorology and emissions were quantitatively isolated using a multiple linear regression with meteorological variables. In terms of short-term variability, intercorrelations among the pollutants and meteorological variables and composite analysis of synoptic meteorological fields exhibited that the warm and stagnant conditions in the migratory high-pressure system are related to the high PM10 and primary pollutant, while the strong irradiance and low NO2 by high winds at the rear of a cyclone are related to the high O3. In terms of long-term trends, decrease in PM10 (−1.75 µg m−3 yr−1) and increase in O3 (+0.88 ppb yr−1) in Seoul were largely contributed by the meteorology-related trends (−0.94 µg m−3 yr−1 for PM10 and +0.47 ppb yr−1 for O3), which were attributable to the subregional-scale wind speed increase. Comparisons with estimated local emissions and socioeconomic indices like gross domestic product (GDP) growth and fuel consumptions indicate probable influences of the 2008 global economic recession as well as the enforced regulations from the mid-2000s on the emission-related trends of PM10 and other primary pollutants. Change rates of local emissions and the transport term of long-term components calculated by the tracer continuity equation revealed a decrease in contributions of local emissions to the primary pollutants including PM10 and an increase in contributions of local secondary productions to O3. The present results not only reveal an important role of synoptic meteorological conditions on the episodic air pollution events but also give insights into the practical effects of environmental policies and regulations on the long-term air pollution trends. As a complementary approach to the chemical transport modeling, this study will provide a scientific background for developing and improving effective air quality management strategy in Seoul and its metropolitan area.

scholarly journals Estimating Short- and Long-Term Associations Between Air Quality Index and COVID-19 Transmission: Evidence From 257 Chinese Cities

2021 ◽  
Vol 66 ◽  
Author(s):  
Ru Cao ◽  
Yuxin Wang ◽  
Xiaochuan Pan ◽  
Xiaobin Jin ◽  
Jing Huang ◽  
...  
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Quality Index ◽  
Air Quality Index ◽  
Pollution Level ◽  
Short Term ◽  
Migration Index ◽  
Long Run ◽  
Long Term Impact

Objectives: To evaluate the long- and short-term effects of air pollution on COVID-19 transmission simultaneously, especially in high air pollution level countries.Methods: Quasi-Poisson regression was applied to estimate the association between exposure to air pollution and daily new confirmed cases of COVID-19, with mutual adjustment for long- and short-term air quality index (AQI). The independent effects were also estimated and compared. We further assessed the modification effect of within-city migration (WM) index to the associations.Results: We found a significant 1.61% (95%CI: 0.51%, 2.72%) and 0.35% (95%CI: 0.24%, 0.46%) increase in daily confirmed cases per 1 unit increase in long- and short-term AQI. Higher estimates were observed for long-term impact. The stratifying result showed that the association was significant when the within-city migration index was low. A 1.25% (95%CI: 0.0.04%, 2.47%) and 0.41% (95%CI: 0.30%, 0.52%) increase for long- and short-term effect respectively in low within-city migration index was observed.Conclusions: There existed positive associations between long- and short-term AQI and COVID-19 transmission, and within-city migration index modified the association. Our findings will be of strategic significance for long-run COVID-19 control.

scholarly journals A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization

2017 ◽  
Author(s):  
Dixian Zhu ◽  
Changjie Cai ◽  
Tianbao Yang ◽  
Xun Zhou
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Air Quality ◽  
Regression Models ◽  
Small Scale ◽  
Quality Prediction ◽  
Pollution Concentration ◽  
Task Learning ◽  
Air Quality Prediction ◽  
Standard Regression

In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., Ozone, PM2.5 and Sulfur Dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exists some works applying machine learning to air quality prediction, most of the prior studies are restricted to small scale data and simply train standard regression models (linear or non-linear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration based on meteorological data of previous days by formulating the prediction of 24 hours as a multi-task learning problem. It enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other, and compare with several typical regularizations for multi-task learning including standard Frobenius norm regularization, nuclear norm regularization, ℓ2,1 norm regularization. Our experiments show the proposed formulations and regularization achieve better performance than existing standard regression models and existing regularizations.

scholarly journals Air pollution, SARS-CoV-2 transmission, and COVID-19 outcomes: A state-of-the-science review of a rapidly evolving research area

2020 ◽  
Author(s):  
Anushka Bhaskar ◽  
Jay Chandra ◽  
Danielle Braun ◽  
Jacqueline Cellini ◽  
Francesca Dominici
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Health Outcomes ◽  
Study Design ◽  
Air Pollutant ◽  
Short Term ◽  
Cross Sectional ◽  
Short And Long Term ◽  
Long Term Studies

Background: As the coronavirus pandemic rages on, 692,000 (August 7, 2020) human lives and counting have been lost worldwide to COVID-19. Understanding the relationship between short- and long-term exposure to air pollution and adverse COVID-19 health outcomes is crucial for developing solutions to this global crisis. Objectives: To conduct a scoping review of epidemiologic research on the link between short- and long-term exposure to air pollution and COVID-19 health outcomes. Method: We searched PubMed, Web of Science, Embase, Cochrane, MedRxiv, and BioRxiv for preliminary epidemiological studies of the association between air pollution and COVID-19 health outcomes. 28 papers were finally selected after applying our inclusion/exclusion criteria; we categorized these studies as long-term studies, short-term time-series studies, or short-term cross-sectional studies. One study included both short-term time-series and a cross-sectional study design. Results: 27 studies of the 28 reported evidence of statistically significant positive associations between air pollutant exposure and adverse COVID-19 health outcomes; 11 of 12 long-term studies and all 16 short-term studies reported statistically significant positive associations. The 28 identified studies included various confounders, spatial and temporal resolutions of pollution concentrations, and COVID-19 health outcomes. Discussion: We discuss methodological challenges and highlight additional research areas based on our findings. Challenges include data quality issues, ecological study design limitations, improved adjustment for confounders, exposure errors related to spatial resolution, geographic variability in testing, mitigation measures and pandemic stage, clustering of health outcomes, and a lack of publicly available data and code.

Sign in / Sign up

Export Citation Format

Share Document