scholarly journals Longer Time Span Air Pollution Prediction: The Attention and Autoencoder Hybrid Learning Model

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Xin-Yu Tu ◽  
Bo Zhang ◽  
Yu-Peng Jin ◽  
Guo-Jian Zou ◽  
Jian-Guo Pan ◽  
...  

Air pollution has become a critical issue in human’s life. Predicting the changing trends of air pollutants would be of great help for public health and natural environments. Current methods focus on the prediction accuracy and retain the forecasting time span within 12 hours. Shorter time span decreases the practicability of these perditions, even with higher accuracy. This study proposes an attention and autoencoder (A&A) hybrid learning approach to obtain a longer period of air pollution changing trends while holding the same high accuracy. Since pollutant concentration forecast highly relates to time changing, quite different from normal prediction problems like autotranslation, we integrate “time decay factor” into the traditional attention mechanism. The time decay factor can alleviate the impact of the value observed from a longer time before while increasing the impact of the value from a closer time point. We also utilize the hidden states in the decoder to build connection between history values and current ones. Thus, the proposed model can extract the changing trend of a longer history time span while coping with abrupt changes within a shorter time span. A set of experiments demonstrate that the A&A learning approach can obtain the changing trend of air pollutants, like PM2.5, during a longer time span of 12, 24, or even 48 hours. The approach is also tested under different pollutant concentrations and different periods and the results validate its robustness and generality.

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Rui Zhang ◽  
Yujie Meng ◽  
Hejia Song ◽  
Ran Niu ◽  
Yu Wang ◽  
...  

Abstract Background Although exposure to air pollution has been linked to many health issues, few studies have quantified the modification effect of temperature on the relationship between air pollutants and daily incidence of influenza in Ningbo, China. Methods The data of daily incidence of influenza and the relevant meteorological data and air pollution data in Ningbo from 2014 to 2017 were retrieved. Low, medium and high temperature layers were stratified by the daily mean temperature with 25th and 75th percentiles. The potential modification effect of temperature on the relationship between air pollutants and daily incidence of influenza in Ningbo was investigated through analyzing the effects of air pollutants stratified by temperature stratum using distributed lag non-linear model (DLNM). Stratified analysis by sex and age were also conducted. Results Overall, a 10 μg/m3 increment of O3, PM2.5, PM10 and NO2 could increase the incidence risk of influenza with the cumulative relative risk of 1.028 (95% CI 1.007, 1.050), 1.061 (95% CI 1.004, 1.122), 1.043 (95% CI 1.003, 1.085), and 1.118 (95% CI 1.028, 1.216), respectively. Male and aged 7–17 years were more sensitive to air pollutants. Through the temperature stratification analysis, we found that temperature could modify the impacts of air pollution on daily incidence of influenza with high temperature exacerbating the impact of air pollutants. At high temperature layer, male and the groups aged 0–6 years and 18–64 years were more sensitive to air pollution. Conclusion Temperature modified the relationship between air pollution and daily incidence of influenza and high temperature would exacerbate the effects of air pollutants in Ningbo.


2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
M E L Brandao ◽  
B A L F Braga ◽  
M L C Martins ◽  
P L A A Pereira

Abstract Santos is a seaboard Brazilian city recognized by its port activity where the road and rail infrastructure along with the large transportation operation, displays an important factor to contribute with all kinds of toxic and air pollutants. Recent studies have suggested associations between air pollution and various birth outcomes. Pollutant gases such as NOx, O3 and particulate matter PM2,5, PM10 have been cited as factors involved in such outcomes. The present study aims to assess the relationship between atmospheric pollutants and perinatal outcomes in the city of Santos from Jan. 2012 to Dec. 2015. Cross-sectional study that analyzed 10.319 singleton births in an area set with 2 km radius of the monitoring stations. Birth weight and information on mother and pregnancy were obtained at the Brazilian “Born Alive National Information System”. Daily records of air pollutants (PM10, PM2.5, NO2 and O3), temperature and relative air humidity, for the study period, were obtained from São Paulo State Environmental Agency (CETESB). Associations between preterm birth and air pollutants mean levels at each gestational trimester were investigated using multiple logistic regression model controlled by the variables: infant sex, type of delivery, maternal education. prenatal care, and number of previous live births, temperature and relative air humidity. NO2 e PM2,5 was not associated with preterm birth. O3 was significantly associated in the first trimester in the fourth quartile (OR = 1,47 CI 95% 1,05; 2,07). PM10 was significantly associated in the first trimester for the fourth quartile (OR = 1,28 CI 95% 1,00; 1,64), second trimester for the second quartile (OR = 1,37 CI 95% 1,07; 1,77). Conclusions the results shows evidence that maternal exposure to air pollution especially during the first trimester of pregnancy may contribute to preterm birth. Further actions are needed towards controlling air pollution are strongly recommended for promoting early-life health. Key messages This is the first research of this kind that was made in Santos. It brings important evidence of the impact in the life of the population, especially those whose is not even born yet. It can be used as a resource to guide public policies in health, especially the guidelines that dictate the concentration of air pollutants and air quality.


2020 ◽  
Vol 5 (4) ◽  
pp. 230-234
Author(s):  
I. I. Berezin ◽  
Yu. Yu. Eliseev ◽  
A. K. Sergeev

Objectives to reveal cause-and-effect relationships in the system "air pollution morbidity of the population" in a large industrial city. Material and methods.The dynamics of the pollutants concentration, such as formaldehyde and benzopyrene, through the period of 20152017 was analyzed in relation to the indicators of the morbidity of the respiratory system in the population of Samara. In particular, the study focused on the ratio of allergic rhinitis and asthma cases and the concentration of the formaldehyde and benzopyrene. Results.The incidence of respiratory diseases and the general morbidity increased both among children (by 46.7%) and adults (by 11.4%). There was the causal correlation between the effect of benzopyrene on the development of allergic rhinitis and bronchial asthma in children(r = 0.57 and r = 0.76) and in adults (r = 0.45 and r = 0.51) in Samara. The significant differences between the level of the pollutants and the frequency of the respiratory system diseases were registered in children and adults in different areas of Samara. Discussion.As a result of the increase of the maximum allowable concentration (MAC) of formaldehyde in atmospheric air, this pollutant has now ceased to be a priority. The revealed negative correlations point to the absence of an adverse effect of formaldehyde on the development of allergic rhinitis and bronchial asthma in both children and adults in Samara. Conclusion.According to the results of the study, the preventive measures aimed at reducing the impact of main air pollutants on the health of children and adults in Samara were suggested. Their implementation is possible by the immediate informing of the executive authorities to ensure they can make timely management decisions to improve the quality of the environment.


2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jonathan Spiteri ◽  
Philip von Brockdorff

PurposeThe aim of this paper is to quantify the impact of transboundary air pollutants, particularly those related to urban traffic, on health outcomes. The importance of focusing on the health implications of transboundary pollution is due to the fact that these emissions originate from another jurisdiction, thus constituting international negative externalities. Thus, by isolating and quantifying the impact of these transboundary air pollutants on domestic health outcomes, the authors can understand more clearly the extent of these externalities, identify their ramifications for health and emphasise the importance of cross-country cooperation in the fight against air pollution.Design/methodology/approachThe authors employ panel data regression analysis to look at the relationship between emissions of transboundary air pollution and mortality rates from various respiratory diseases among a sample of 40 European countries, over the period 2003–2014. In turn, the authors use annual data on transboundary emissions of sulphur oxides (SOx), nitrogen oxides (NOx) and fine particulate matter (PM2.5), together with detailed data on the per capita incidence of various respiratory diseases, including lung cancer, asthma and chronic obstructive pulmonary disease (COPD). The authors consider a number of different regression equation specifications and control for potential confounders like the quality of healthcare and economic prosperity within each country.FindingsThe results show that transboundary emissions of PM2.5 are positively and significantly related to mortality rates from asthma in our sample of countries. Quantitatively, a 10% increase in PM2.5 transboundary emissions per capita from neighbouring countries is associated with a 1.4% increase in the asthma mortality rate within the recipient country or roughly 200 deaths by asthma per year across our sample.Originality/valueThese findings have important policy implications for cross-country cooperation and regulation in the field of pollution abatement and control, particularly since all the countries under consideration form a part of the UN's Convention on Long-Range Transboundary Air Pollution (CLRTAP), a transnational cooperative agreement aimed at curtailing such pollutants on an international level.


2021 ◽  
Author(s):  
Michał Zacharko ◽  
Robert Cichowicz ◽  
Marcin Andrzejewski ◽  
Paweł Chmura ◽  
Edward Kowalczuk ◽  
...  

Abstract The aim of the study was to determine the impact of air quality – analyzed on the basis of the model of integrating three types of air pollutants (ozone – O3, particulate matter - PM, nitrogen dioxide – NO2) – on the physical activity of soccer players. Study material consisted of 8927 individual match observations of 461 players competing in the German Bundesliga during the 2017/2018 and 2018/2019 domestic seasons. The measured indices included players’ physical activities: total distance (TD) and high intensity effort (HIE). Statistical analysis showed that with increasing levels of air pollution, both TD (F = 13.900(3); p = 0.001) and HIE (F = 8.060(3); p = 0.001) decrease significantly. The worsening of just one parameter of air pollution results in a significant reduction in performance. This is important information as air pollution is currently a considerable problem for many countries. Improving air quality during training sessions and sports competitions will result in better well-being and sporting performance of athletes, and will also help protect athletes from negative health effects caused by air pollution.


2020 ◽  
Vol 5 (4) ◽  
pp. 137-140
Author(s):  
Hina Islam ◽  
Irfan Sharif Shakoori ◽  
Fauzia Aslam ◽  
Gohar Ashraf ◽  
Hammad Akram

AbstractAir pollution is a result of natural phenomena or human activities that can cause the release of harmful substances in the environment, leading to adverse health outcomes among living beings. Pollution is associated with adverse health impacts on multiple organ systems among humans. While the respiratory and cardiovascular systems are mainly affected, there are other health issues related to the eyes, skin, brain, blood, immunity, behavioral/mental well-being, and reproduction among exposed individuals. Air pollutants can especially have higher health impacts on people at the extremes of their ages (children and elderly) and on those suffering from underlying respiratory and heart issues. Pollutants such as ozone, sulfur dioxide, particulate matter, and nitrogen dioxide have respiratory effects among children and adults and are associated with increased respiratory diseases, asthma exacerbations, and related hospitalizations. Carbon monoxide interferes with transporting oxygen by forming carboxyhemoglobin leading to cardiovascular, neurological, and respiratory problems. Particulate matter is a heterogeneous mixture of tiny particles of varying compositions found in the atmosphere and has a wide variety of severe health effects. Particulate matter emits from combustion, diesel engines, power generation, and wood-burning, and certain industrial activities. Lead is considered neurotoxic and has more severe consequences among children. Here we summarize characteristics of six criteria air pollutants and associated air quality risk assessment parameters known as the Pollutant Standard Index (PSI). The present manuscript also examines the impact of air pollution on human behavior, mental well-being, and neurological health consequences, as air pollution has been associated with cognitive decline, hyperactivity, dementia, anxiety, depression, aggression, and Alzheimer’s disease-related changes. Lastly, we also attempt to look into any relationship between air pollutants and Coronavirus disease (COVID-19) and examine its possible association with a higher COVID-19 incidence, complications, and mortality.


2021 ◽  
Author(s):  
Ilaria D'Elia ◽  
Gino Briganti ◽  
Lina Vitali ◽  
Antonio Piersanti ◽  
Gaia Righini ◽  
...  

Abstract. Air pollution harms human health and the environment. Several regulatory efforts and different actions have been taken in the last decades by authorities. Air quality trend analysis represents a valid tool in assessing the impact of these actions taken both at national and local levels. This paper presents for the first time the capability of the Italian national chemical transport model, AMS-MINNI, in capturing the observed concentration trends of three air pollutants, NO2, inhalable particles having diameter less than 10 micrometres (PM10) and O3, in Italy over the period 2003–2010. We firstly analyse the model performance finding it in line with the state of the art of regional models applications. The modelled trends result in a general significant downward trend for the three pollutants and, in comparison with observations, the values of the simulated slopes show the same magnitude for NO2 (in the range −3.0 ÷ −0.5 ug m−3 yr−1), while a smaller variability is detected for PM10 (−1.5 ÷ −0.5 ug m−3 yr−1) and O3-maximum daily 8-hour average concentration (−2.0 ÷ −0.5 ug m−3 yr−1). As a general result, we find a good agreement between modelled and observed trends; moreover, the model allowed to extend both the spatial coverage and the statistical significance of pollutants' concentrations trends with respect to observations, in particular for NO2. We also conduct a qualitative attempt to correlate the temporal concentration trends to meteorological and emission variability. Since no clear tendency in yearly meteorological anomalies (temperature, precipitation, geopotential height) was observed for the period investigated, we focus the discussion of concentrations trends on emissions variations. We point out that, due to the complex links between precursors emissions and air pollutants concentrations, emission reductions do not always result in a corresponding decrease in atmospheric concentrations, especially for those pollutants that are formed in the atmosphere such as O3 and the major fraction of PM10. These complex phenomena are still uncertain and their understanding is of the utmost importance in planning future policies for reducing air pollution and its impacts on health and ecosystems.


2020 ◽  
Author(s):  
hazem al-najjar ◽  
Nadia Al-Rousan ◽  
Ismail A. Elhaty

Abstract Air pollution depends on seasons, wind speed, temperature, wind direction and air pressure. The effect of different seasons on air pollution is not fully addressed in the reported works. The current study investigated the impact of season on air pollutants including SO2, PM10, NO, NOX, and O3 using NARX method. In the applied methodology, a feature selection was used with each pollutant to find the most important season(s). Afterward, six models are designed based on the feature selection to show the impact of seasons in finding the concentration of pollutants. A case study is conducted on Esenyurt which is one of the most populated and industrialized places in Istanbul to validate the proposed framework. The performance of using all of the designed models with different pollutants showed that using season effect led to improving the performance of predictor and generating high R2 and low error functions.


2020 ◽  
Author(s):  
Yichen Chen ◽  
Xiaopan Li ◽  
Hanyi Chen ◽  
Lianghong Sun ◽  
Tao Lin ◽  
...  

Abstract Background: Air pollution is a severe and dangerous public health problem. However, the effect of ambient gaseous air pollution exposure on years of life lost (YLL) attributable to chronic obstructive pulmonary disease (COPD) mortality has not been quantitatively verified.Methods: We collected the data of 12,781 COPD deaths and ambient gaseous air pollutants, including sulfur dioxide (SO2), nitrogen dioxide (NO2), Carbon monoxide (CO), and ozone (O3), during the years 2013-2019 in the Shanghai Pudong New Area (PNA). Then we performed a time-stratified case-crossover study combined with a distributed lag nonlinear model (DLNM) to estimate the impact of those air pollutants on daily COPD deaths counts and YLL. The confounders including long-term trend and meteorological factors have been controlled for, and effects of age and educational attainment as effect modifiers have also been evaluated.Results: During the 2013-2019 time frame, increases of 10μg/m3 in SO2 and NO2 were associated with a 4.93% (95% CI: 1.47%, 8.50%) and 1.47% (95% CI: 0.14%, 2.82%) in daily COPD death counts at lag0-1day, respectively, a 2.52 (95% CI: 0.31, 4.72) YLL increase and 0.85 (95% CI: 0.01, 1.68) YLL increase at lag0-1day, respectively. A 1mg/m3 increase in CO was associated with a 9.46% (95% CI: 0.40%, 19.35%) at lag0 increase in daily COPD death counts. No significant impact from O3 on both daily COPD deaths counts and YLL (P>0.05). The impact of gaseous air pollutants on the daily COPD death count and YLL were significant in populations of older adults and the lower educated population, while an insignificant effect was observed in the younger population and higher educated population. The YLL due to COPD related to SO2 and CO for the lower educated population was significantly higher than those for the higher educated population.Conclusion: Reducing specific gaseous air pollutants will help to control COPD deaths and improve the population’s life expectancy.


2022 ◽  
Vol 21 (1) ◽  
Author(s):  
Luca Boniardi ◽  
Federica Nobile ◽  
Massimo Stafoggia ◽  
Paola Michelozzi ◽  
Carla Ancona

Abstract Background Air pollution is one of the main concerns for the health of European citizens, and cities are currently striving to accomplish EU air pollution regulation. The 2020 COVID-19 lockdown measures can be seen as an unintended but effective experiment to assess the impact of traffic restriction policies on air pollution. Our objective was to estimate the impact of the lockdown measures on NO2 concentrations and health in the two largest Italian cities. Methods NO2 concentration datasets were built using data deriving from a 1-month citizen science monitoring campaign that took place in Milan and Rome just before the Italian lockdown period. Annual mean NO2 concentrations were estimated for a lockdown scenario (Scenario 1) and a scenario without lockdown (Scenario 2), by applying city-specific annual adjustment factors to the 1-month data. The latter were estimated deriving data from Air Quality Network stations and by applying a machine learning approach. NO2 spatial distribution was estimated at a neighbourhood scale by applying Land Use Random Forest models for the two scenarios. Finally, the impact of lockdown on health was estimated by subtracting attributable deaths for Scenario 1 and those for Scenario 2, both estimated by applying literature-based dose–response function on the counterfactual concentrations of 10 μg/m3. Results The Land Use Random Forest models were able to capture 41–42% of the total NO2 variability. Passing from Scenario 2 (annual NO2 without lockdown) to Scenario 1 (annual NO2 with lockdown), the population-weighted exposure to NO2 for Milan and Rome decreased by 15.1% and 15.3% on an annual basis. Considering the 10 μg/m3 counterfactual, prevented deaths were respectively 213 and 604. Conclusions Our results show that the lockdown had a beneficial impact on air quality and human health. However, compliance with the current EU legal limit is not enough to avoid a high number of NO2 attributable deaths. This contribution reaffirms the potentiality of the citizen science approach and calls for more ambitious traffic calming policies and a re-evaluation of the legal annual limit value for NO2 for the protection of human health.


Sign in / Sign up

Export Citation Format

Share Document