Air Pollution Monitoring Stations Research Articles

Mapping dust risk under heterogenous vulnerability to dust: The combination of spatial modelling and questionnaire survey

Dust storms are natural events that remove and relocate surface soil, damage vegetation crops, and disrupt many other aspects of the earth's terrestrial ecosystem. Despite the importance of the risk assessment of dust hazards, vulnerability modeling of them is very limited. For this reason, this study provides a conceptual model based on Structural Equation Modeling and the Finite Mixture Partial Least Squares (FIMIX-PLS) approach using interviews and questions for vulnerability modeling of dust in Ahvaz County, Khuzestan province, Iran. Key model drivers included Resilience Actions, Natural-Physical effects, Economic Influence, and Social Influence. The Aerosol Optical Depth (AOD) product of MODIS/Terra was used to develop a dust hazard map. MODIS/Terra performance was evaluated using observed PM10 data from Ahvaz County air pollution monitoring stations. Land use mapping was used for spatial detection of agricultural land affected by the intensity of the AOD map in the previous step. The vulnerability model fitting results showed that the model had acceptable validity (SRMR = 0.013). Results showed that approximately 25 % of agricultural lands are at high and very high dust hazard risk. Based on modeling results, natural-physical variables affect about 89 % and 97 % of social and economic drivers, respectively. Conversely, social influences significantly negatively affect dust storm resilience resulting in agricultural vulnerability. Based on results from the integrated model, strengthening farmers' resilience strategies against dust hazards requires additional research and attention.

Road traffic flow and air pollution concentrations: evidence from Japan

AbstractVehicular emissions are a major global health concern. The aim of this study is to examine the short-term relationship between road traffic flows and air pollution concentrations in Japan. Our approach involves matching hourly data from the 2015 Road Traffic Census to data from nearby air pollution monitoring and meteorological stations and estimating a dynamic panel model. We focus on four pollutants designated under the vehicle emission standards of Japan: nitrogen oxides (NOx), carbon monoxide (CO), nonmethane hydrocarbons (NMHC), and fine particulate matter (PM2.5). The standard estimates indicate that short-run pollution concentration-road traffic flow elasticities are 0.04–0.05 for NOx, CO, and NMHC, and insignificant for PM2.5. Long-term effects are also estimated. We apply the estimates to a case study on the link between road traffic flows and meeting the new World Health Organization air quality guidelines.

TEHRAN AIR POLLUTION MODELING USING LONG-SHORT TERM MEMORY ALGORITHM: AN UNCERTAINTY ANALYSIS

Abstract. Air pollution is a major environmental issue in urban areas, and accurate forecasting of particles 10 μm or smaller (PM10) level is essential for smart public health policies and environmental management in Tehran, Iran. In this study, we evaluated the performance and uncertainty of long short-term memory (LSTM) model, along with two spatial interpolation methods including ordinary kriging (OK) and inverse distance weighting (IDW) for mapping the forecasted daily air pollution in Tehran. We used root mean square error (RMSE) and mean square error (MSE) to evaluate the prediction power of the LSTM model. In addition, prediction intervals (PIs), and Mean and standard deviation (STD) were employed to assess the uncertainty of the process. For this research, the air pollution data in 19 Tehran air pollution monitoring stations and temperature, humidity, wind speed and direction as influential factors were taken into account. The results showed that the OK had better RMSE and STD in the test (32.48 ± 9.8 μg/m3) and predicted data (56.6 ± 13.3 μg/m3) compared with those of the IDW in the test (47.7 ± 22.43 μg/m3) and predicted set (62.18 ± 26.1 μg/m3). However, in PIs, IDW ([0, 0.7] μg/m3) compared with the OK ([0, 0.5] μg/m3) had better performance. The LSTM model achieved in the predicted values an RMSE of 8.6 μg/m3 and a standard deviation of 9.8 μg/m3 and PIs between [2.7 ± 4.8, 14.9 ± 15] μg/m3.

Environmental exposure and sensitization patterns in a Swiss alpine pediatric cohort

BackgroundThe level of environmental exposure throughout life may contribute to the prevalence of allergic sensitization and allergic disease. The alpine climate has been considered a healthy climate with little allergen exposure and pollution. We conducted a cross-sectional study to investigate local environmental exposure and concomitant prevalence of allergic sensitization among local school children born and raised in an alpine environment. MethodsClinical and demographic data were collected with a questionnaire. Allergen content was assessed in residential settled dust samples, lifetime exposure to pollen and air pollution was calculated using data from national pollen and air pollution monitoring stations, and the allergic sensitization profile was determined with component resolved diagnostics (ISAC®). Univariate and multivariate regression models were used to estimate the relation between exposure and sensitization. ResultsIn a cohort of children born and raised in an alpine environment, sensitization to aeroallergens is quite common (38%), especially to grass (33%) and cat (16%). House dust mite allergen was detected in up to 38% of residential dust samples, but sensitization to HDM was low (2.5%). Pollutant levels were low, but an increasing trend was observed in the amount of ozone and PM10. Living close to a busy road was associated with increased odds OR (95% CI) for being sensitized to any allergen 2.7 (1.0–7.2), to outdoor allergens 2.8 (1.1–7.1) and being sensitized plus reporting symptoms of rhinoconjunctivitis 4.4 (1.3–14.8) and asthma 5.5 (1.4–21). Indoor living conditions, including the presence of visible mold, increased the odds of being sensitized to indoor allergens (1.9 (1.1–3.2) and being sensitized plus reporting symptoms of rhinoconjunctivitis 1.9 (1.0–3.6) and asthma 2.1 (1.0–4.1). ConclusionIn a healthy alpine environment, pollution might still be an important factor contributing to allergic sensitization.

Machine learning-based global air quality index development using remote sensing and ground-based stations

Air pollution refers to the presence of hazardous substances in the air that has adverse effects on health, causing millions premature deaths annually. Ground-based stations can provide accurate measurements for monitoring air pollution. However, the spatial coverage of air pollution measurements is limited by the number of measurement instruments available in specific hotspot areas. Satellite remote sensing can reduce spatial uncertainty; however, the measurement results are mostly limited to the upper atmosphere with high measurement sensitivity. To better represent surface conditions, this study aims to model the Air Quality Index for pollutants CO, NO2, SO2, PM2.5, and PM10 in the global region using remotely sensed data. To support this study, 425 data points from air pollution stations distributed globally are combined using Machine Learning Linear Regression methods. Furthermore, socioeconomic and environmental data are combined with air pollution satellite to form Multiple models. According to the results of this study, the Multiple Models are more accurate than the single models, showing that the addition of socioeconomic and environmental data can enhance accuracy. The results of this study are expected to help regions without air pollution monitoring stations to estimate the air quality index using satellite data, in turn, preventing air pollution disasters.

Predicting air quality in smart city using novel transfer learning based framework

Air quality is a matter of concern these days due to its adverse effect on human health. Multiple new air pollution monitoring and prediction stations are being developed in smart cities to tackle the issue. Recent advanced deep learning techniques show excellent performance for air quality predictions but need sufficient training data for model performance. The data insufficiency issue at a new station can be resolved using the proposed novel transfer learning-based framework to predict pollution concentration at the new station. The prediction ability at a new station can be significantly enhanced by this effective technology. The performance of the model is assessed on various stations in Delhi, India.

Assessment of the association between ambient air pollution and stillbirth in the UK: Results from a secondary analysis of the MiNESS case-control study.

We examined whether the risk of stillbirth was related to ambient air pollution in a UK population. Prospective case-control study. Forty-one maternity units in the UK. Women who had a stillbirth ≥28 weeks' gestation (n = 238) and women with an ongoing pregnancy at the time of interview (n = 597). Secondary analysis of data from the Midlands and North of England Stillbirth case-control study only including participants domiciled within 20 km of fixed air pollution monitoring stations. Pollution exposure was calculated using pollution climate modelling data for NO2 , NOx and PM2.5 . The association between air pollution exposure and stillbirth risk was assessed using multivariable logistic regression adjusting for household income, maternal body mass index (BMI), maternal smoking, Index of Multiple Deprivation quintile and household smoking and parity. Stillbirth. There was no association with whole pregnancy ambient air pollution exposure and stillbirth risk, but there was an association with preconceptual NO2 exposure (adjusted odds ratio [aOR] 1.06, 95% CI 1.01-1.08 per microg/m3 ). Risk of stillbirth was associated with maternal smoking (aOR 2.54, 95% CI 1.38-4.71), nulliparity (aOR 2.16, 95% CI 1.55-3.00), maternal BMI (aOR 1.05, 95% CI 1.01-1.08) and placental abnormalities (aOR 4.07, 95% CI 2.57-6.43). Levels of ambient air pollution exposure during pregnancy in the UK, all of were beneath recommended thresholds, are not associated with an increased risk of stillbirth. Periconceptual exposure to NO2 may be associated with increased risk but further work is required to investigate this association.

Long-term spatial and temporal evaluation of the PM2.5 and PM10 mass concentrations in Lithuania

Evaluating the spatio-temporal trends of particulate mass concentration is beneficial for appraising the risk to human health and environmental quality. In this study, the long-term observational data of particulate matter mass concentration (PM2.5, PM10), and PM2.5/PM10 ratios' variability of sixteen EPA air pollution monitoring stations in Lithuania over 17 years (2006–2022), were analyzed. A seasonal-trend decomposition procedure using Loess and Mann-Kendall regression with Sen's slope was used to qualify long-term trends and seasonality. The Theil-Sen analysis estimated significant reductions of −2.66, −4.42, and −1.89% per year for PM10, PM2.5, and PM2.5/PM10 ratios after 2013. The possible reasons for these changes are the reduction in liquid fuel consumption, the mitigation of energy sector emissions, as well as Lithuania's positive gross domestic product (GDP) in recent years. The results also revealed a significant increasing trend (+4.48%/year) for PM10 in rural areas, due to increased agricultural emissions. Trend analysis was also applied to different quartiles. The upper and middle values of PM2.5 and the upper values of PM10, responsible for high PM mass concentration, underwent a significant decrease.

Identification of Sources Causing Air Pollution in Indian Cities Using Hierarchical Agglomerative Cluster Analysis

The distressing levels of air pollution in India is becoming health hazard to the inhabitants. It's important to note that due to the nation's continued urbanisation and its heavy reliance on coal for electricity generation, air pollution is expected to get worse in some areas of India over the next few decades. Present study aims to address the issue by identifying the sources causing air pollution using Hierarchical Agglomerative Cluster Analysis [HACA]. Two years daily data (2018 and 2019), downloaded from publicly available source Kaggle.com of sixteen selected air pollution monitoring stations was used for the study. The stations were selected based upon diversified environmental conditions and local sources. HACA was successful in grouping the monitoring stations into four clusters based on their average Air Quality Index (AQI) level. These four clusters are named as Low Pollution, Moderate Pollution, High Pollution and Very High Pollution Region [LPR, MPR, HPR and VHPR] with average AQI 96; 135; 173 and 227 respectively. Discriminant Analysis (DA) confirmed the resulting clusters with 100% accuracy. It was found that stations with similar environmental factors, regional sources, and pollution amounts were clustered together. Despite numerous actions taken by the authorities to reduce air pollution, it was noticed that topographical conditions play an essential role in the rise of pollution. This study helps to implement different strategies by the authorities’ concern based on local sources and topographical conditions.

Prediction of CO pollutant in Mashhad metropolis, Iran: Using multiple linear regression

AbstractGiven the importance of carbon monoxide (CO) in acute health threats, studies have been conducted in different countries and cities (272 cities in China and 337 cities on a global scale) on the relationship between daily mortality and CO while the spatial analysis of factors affecting CO pollutant in cities, especially in developing countries, has rarely been done. Accordingly, this research has measured the effect of five environmental‐social variables (ESVs) on the spatial distribution of CO pollutants in the metropolis of Mashhad, Iran. CO concentration data were collected in 23 air pollutant monitoring stations in an area of 356 km2 in 2019. Then, the relationship between five variables and CO pollutant were measured using linear and multiple regression by Sentinel 2A and 3 satellite images in ArcGIS and TerrSet software. The results show that the mean CO concentration averages at 1.56 ppm in the whole city. But its range varies between 0.171 and 2.907 ppm, which is a low figure compared with presented standards and does not indicate a critical situation. The results of multiple regression indicate that 42% of the variance in CO concentration is explained by independent variables. Among five independent variables, the beta value of the land surface temperature (LST) and digital elevation model (DEM) variables is negative and positive for the other three variables, including population density, normalised difference vegetation index (NDVI) and normalised difference built‐up index (NDBI). It should be noted that the strongest correlating variable is population density. Prediction of the spatial distribution of CO pollutants shows the division of the city into three areas: (1) the south and southwest slopes of the city with a low concentration; (2) central areas with a medium concentration; and (3) northern and northeastern areas of the city with a high concentration where low‐income groups reside and there are more worn‐out vehicles, motorcycles and industrial workshops. Areas with high CO concentration need more attention from urban managers.

Air pollution monitoring and avoidance behavior: Evidence from the health insurance market

Previous studies have often focused on the direct benefits of environmental regulations on health. This paper quantifies the impact of environmental regulations on the cost of prevention for urban residents. The purpose of this study is to examine how environmental regulations affect urban commercial health insurance purchases. Air pollution monitoring stations in China capture exogenous air quality changes to overcome potential endogenous problems. Evidence shows that an increase in the operating days of air pollution monitoring stations will reduce the purchase of commercial health insurance in the city. The mechanism is that the operation of air pollution monitoring stations is conducive to improving local air quality and alleviating residents’ health prevention needs. Heterogeneity analysis shows that the impact of air pollution monitoring station operation on the cost of prevention is less effective in more developed cities. Finally, we demonstrate that the number of claims for commercial health insurance dropped with the operation of air pollution monitoring stations. The results show that the benefits of improved air pollution do not only include the direct benefits of increased health, but also include the potential benefits of reduced prevention costs. Ultimately, the results further indicate the importance of air pollution control.

Air pollution and attention in Polish schoolchildren with and without ADHD

BackgroundDevelopment and functioning of attention—a key component of human cognition—can be affected by environmental factors. We investigated whether long- and short-term exposure to particulate matter with aerodynamic diameter < 10 μm (PM10) and nitrogen dioxide (NO2) are related to attention in 10- to 13-year-old children living in Polish towns recruited in the NeuroSmog case-control study. MethodsWe investigated associations between air pollution and attention separately in children with attention deficit hyperactivity disorder (ADHD, n = 187), a sensitive, at-risk population with impaired attention and in population-based typically developing children (TD, n = 465). Alerting, orienting, and executive aspects of attention were measured using the attention network test (ANT), while inhibitory control was measured with the continuous performance test (CPT). We assessed long-term exposure to NO2 and PM10 using novel hybrid land use regression (LUR) models. Short-term exposures to NO2 and PM10 were assigned to each subject using measurements taken at the air pollution monitoring station nearest to their home address. We tested associations for each exposure-outcome pair using adjusted linear and negative binomial regressions. ResultsWe found that long-term exposures to both NO2 and PM10 were associated with worse visual attention in children with ADHD. Short-term exposure to NO2 was associated with less efficient executive attention in TD children and more errors in children with ADHD. It was also associated with shorter CPT response times in TD children; however, this effect was accompanied by a trend towards more CPT commission errors, suggestive of more impulsive performance in these subjects. Finally, we found that short-term PM10 exposure was associated with fewer omission errors in CPT in TD children. ConclusionsExposure to air pollution, especially short-term exposure to NO2, may have a negative impact on attention in children. In sensitive populations, this impact might be different than in the general population.

Disguised pollution: Industrial activities in the dark

In this study we investigate disguised pollution by industrial firms in China. We find that sulfur dioxide (SO2) readings increase by 10.8% in air pollution monitoring stations four hours after sunset in high factory density areas, controlling for station-year, date, and city-hour fixed effects. Physical inspections by the Ministry of Environmental Protection may only temporarily reduce disguised pollution, suggesting that reliance on physical inspections to enforce regulations is ineffective if firms can shift production activities to non-daylight hours. We show that direct monitoring, as is done with some large polluters in China, can prevent this and should be cost-effective to extend to all industrial polluters.

INFLUENCE OF POINT SOURCES OF POLLUTION ON AIR QUALITY IN MAOPOLSKA FIRST TESTS OF A NEW VERSION OF FORECASTING OF AIR POLLUTION PROPAGATION SYSTEM

Polluted air is dangerous to human life and health. Particulate matter, among others PM10, isone of the most harmful substances. In Maopolska and its capital Krakw, the concentrations ofharmful substances often exceed the standards set by the World Health Organization. Krakw,thanks to the ban on residential heating with solid fuels, has significantly reduced emissions ofpollution, but they remain high in the remaining part of the region, affecting air quality in thecapital as well. With the frequent occurrence of high concentrations of pollutants, in addition tothe necessary measures aimed at reducing emissions, forecasting of air pollutant concentrations isneeded to inform the population if normative concentrations are likely to be exceeded. The FAPPS(Forecasting of Air Pollution Propagation System), based on the AROME/MM5/CALMET/CALPUFF model ensemble, has been operating in Maopolska since 2014 and has been used tocreate pollution concentration forecasts for Krakw and Maopolska. In this study, the influence ofemissions from point sources on air quality in Maopolska was investigated based on the results ofmodellingwith this system. Modelling results indicate that this influence is negligible. The qualityof PM10 forecasts for four versions of the FAPPS system, differing in the meteorological modelused MM5 (Fifth-Generation Penn State/NCAR Mesoscale Model) or WRF (Weather Researchand Forecasting) and the emission input (2015 emissions from the Maopolska Marshals Office,updated with data from the City of Krakw for 2018, or the 2020 emission inventory from theCentral Emission Database) was tested. The quality of forecasts was assessed based on the resultsof measurements at the 22 air pollution monitoring stations for three smog episodes that occurredon 1117.11.2021, 1115.12.2021 and 1318.03.2022. The best results for Krakw were obtainedusing an approach based on the WRF model and the emission inventory from the Central EmissionDatabase, for which an RMSE (Root Mean Square Error) value of 30.02 g/m3 was obtained forselected episodes. In the case of Maopolska, the lowest RMSE value (33.58 g/m3) was obtainedfor the system using the emission inventory obtained from the Marshals Office and the WRF model. First tests indicate that changing the meteorological model from MM5 to WRF can lead toimproved modelling results, but, further research is needed to confirm it.

Understanding the Interplay between Air Pollution, Biological Variables, and Major Depressive Disorder: Rationale and Study Protocol of the DeprAir Study

Major depressive disorder (MDD) is a serious and disabling condition, whose etiological mechanisms are not fully understood. The aim of the DeprAir study is to verify the hypothesis that air pollution exposure may exacerbate neuroinflammation with consequent alterations in DNA methylation of genes involved in circadian rhythms and hormonal dysregulation, resulting in the worsening of depressive symptoms. The study population consists of 420 depressed patients accessing the psychiatry unit of the Policlinico Hospital (Milan, Italy), from September 2020 to December 2022. Data collection is still ongoing for about 100 subjects. For each participant demographic and lifestyle information, depression history and characteristics, as well as blood samples, were collected. MDD severity was assessed through five rating scales commonly used in clinical practice to assess the severity of affective symptoms. Exposure to particulate and gaseous air pollutants is assigned to each subject using both air pollution monitoring station measurements and estimates derived from a chemical transport model. DeprAir is the first study investigating in a comprehensive picture whether air pollution exposure could be an important modifiable environmental factor associated with MDD severity and which biological mechanisms mediate the negative effect of air pollution on mental health. Its results will represent an opportunity for preventive strategies, thus entailing a tremendous impact on public health.

Strategy Design of PM2.5 Controlling for Northern Thailand

The emission of fine particulate matter (PM2.5) in dry season from the open biomass burning has caused a long-term negative impact on residents’ health in Northern Thailand. This study takes Chiang Mai and Chiang Rai provinces in Northern Thailand as the study areas to identify pollution episodes, analyze PM2.5 source trajectories, and finally propose pollution control strategies accordingly. PM2.5 levels during 2019–2021 of three representative air pollution monitoring stations (i.e., Chaing Mai-35T, Chiang Rai-57T, and Mae Sai-73T) in these two provinces were collected and analyzed. The Air Quality Index (AQI) defined by PM2.5 level higher than 91 µg m-3 causing serious adverse health effects was adopted to define periods having pollution levels, and the days of the air pollution episodes were identified. Based on these episodes, we applied the backward trajectory model to identify the sources of pollutants. Results showed that PM2.5 levels were significantly higher between February to April compared with other months during 2019–2021 at all three monitoring stations, indicating the severity of PM2.5 episode during the dry season. The backward trajectory demonstrated that air mass transported through the Northern Thailand or nearby mountain areas (categorized as long- or short-transport-distance) contributed up to 21.6% and 75.9% of the total air mass, respectively. Although residents in these mountainous areas are accustomed to the biomass burning, we suggested that there should be urgent needs for the improvement of the long-term air quality in these two provinces. Therefore, this study proposes some control strategies including improvement of prevention knowledge, increase of the risk perception, cultivation of the protection behavior, and intensification of the social influence. In addition to reducing biomass burning pollution, this improvement plan also has a co-benefit of achieving resources recycling concomitantly. Providing effective management strategies may reduce the adverse health effects to Thai residents.

Effect of COVID-19 pandemic restrictions on air pollution at a local scale in urban areas affected by high-intensity vehicle traffic in Poland

The lockdown in 2020 implemented due to the SARS-CoV-2 pandemic has resulted in a significant improvement in air quality at a global scale. Nationwide lockdown also considerably improved air quality at a local scale, especially in cities which were almost completely shut down during the first coronavirus wave, with nearly no activity. We tested the hypothesis that a reduction in the intensity of vehicle traffic causes a drastic decrease in urban air pollution at a local scale. We focused on two urban agglomerations, Warsaw and Cracow, in Poland. Data of the concentrations of traffic-related sources, namely NOx, PM10, and PM2.5, obtained from two air pollution monitoring stations were analyzed for the years 2020 and 2021, during which lockdown and pandemic restrictions were in effect, and for 2019, as a reference. In the years 2020–2021, the average annual concentration of NOx was decreased by ~ 19%, PM2.5 by ~ 19%, and PM10 by ~ 18% in Warsaw, while in Cracow the average annual concentration of NOx was decreased by ~ 16%, PM2.5 by ~ 22%, and PM10 by ~ 2%, compared to 2019. The contribution from traffic-related sources to the overall level of air pollution was estimated. The results indicated that ~ 30 µg/m3 of PM10, ~ 15 µg/m3 of PM2.5, and ~ 120 µg/m3 of NOx in Cracow, and ~ 20 µg/m3 of PM2.5 in Warsaw originate from moving vehicles. The nationwide lockdown allowed us to conduct this study to understand how a reduction in local traffic emissions can decrease ambient air pollution levels.

Associations of environmental factors with total cholesterol level of middle-aged and elderly people in China

BackgroundDyslipidemia is a key factor causing cardio cerebrovascular diseases, and the total cholesterol (TC) is an important lipid indicator among them. Studies have shown that environmental factors have a strong association with TC levels. Previous studies only focused on the seasonal variation of TC level and the short-term effects of some environmental factors on TC level over time, and few studies explored the geographical distribution of TC level and quantified the impact of environmental factors in space.MethodsBased on blood test data which was from China Health and Retirement Longitudinal Study (Charls) database, this study selected the TC level test data of middle-aged and elderly people in China in 2011 and 2015, and collected data from 665 meteorological stations and 1496 air pollutant monitoring stations in China. After pretreatment, the spatial distribution map of TC level was prepared and the regional statistics were made. GeoDetector and geographically weighted regression (GWR) were used to measure the relationship between environmental factors and TC level.ResultsThe TC level of middle-aged and elderly in China was higher in females than in males, and higher in urban areas than in rural areas, showing a clustered distribution. The high values were mainly in South China, Southwest China and North China. Temperature, humidity, PM10 and PM2.5 were significant environmental factors affecting TC level of middle-aged and elderly people. The impact of pollutants was more severe in northern China, and TC level in southern China was mainly affected by meteorological factors.ConclusionsThere were gender and urban-rural differences in TC levels among the middle-aged and elderly population in China, showing aggregation in geographical distribution. Meteorological factors and air pollutants may be very important control factors, and their influencing mechanism needs further study.

Attention enhanced hybrid model for spatiotemporal short-term forecasting of particulate matter concentrations

With ever-increasing global air pollution levels, researchers are exploring ways to forecast air pollutant concentrations to prevent the adverse effects of air pollution on humans. Powered by the data obtained from air pollution monitoring stations, we now have a chance to build sophisticated models to estimate the future concentration of various air pollutants. Previous researches show that deep learning models perform a better task of capturing the complex spatiotemporal dynamics from the data as compared to traditional statistical models. In this paper, a hybrid deep learning framework - AGCTCN (Attention based Graph Convolution and Temporal Convolution Network), based on spatial attention, graph convolution and temporal convolution is presented for short-term forecasting of particulate matter (PM) levels. Specifically, quarter-hourly PM10 and PM2.5 data aggregated from 27 ground air pollution monitoring stations in Delhi, India is used for training the AGCTCN model and our model forecasts the concentrations of these pollutants at these stations for a particular horizon in the future. The forecasts generated by our model are compared and contrasted to those generated by other state-of-the-art models like GC-LSTM and ConvLSTM with respect to four widely used evaluation metrics namely RMSE (root mean squared error), MAE (mean absolute error), correlation coefficient, and R2 (coefficient of determination). Our model shows more than 80% improvement over the GC-LSTM model in terms of the R2 metric, performs the best task of estimating the peak PM concentrations and shows variability and correlation close to that of the observed data. A carefully conducted ablation study shows the effectiveness of the individual components of our architecture. The graph convolution layer improves the model accuracy by approximately 34% on average on the PM datasets. Compared to other models, the AGCTCN framework shows the best performance in short-term forecasting of particulate matter concentrations.

Are dense networks of low-cost nodes really useful for monitoring air pollution? A case study in Staffordshire

Abstract. Air pollution exhibits hyper-local variation, especially near emissions sources. In addition to people's time-activity patterns, this variation is the most critical element determining exposure. Pollution exposure is time-activity- and path-dependent, with specific behaviours such as mode of commuting and time spent near a roadway or in a park playing a decisive role. Compared to conventional air pollution monitoring stations, nodes containing low-cost air pollution sensors can be deployed with very high density. In this study, a network of 18 nodes using low-cost air pollution sensors was deployed in Newcastle-under-Lyme, Staffordshire, UK, in June 2020. Each node measured a range of species including nitrogen dioxide (NO2), ozone (O3), and particulate matter (PM2.5 and PM10); this study focuses on NO2 and PM2.5 over a 1-year period from 1 August 2020 to 1 October 2021. A simple and effective temperature, scale, and offset correction was able to overcome data quality issues associated with temperature bias in the NO2 readings. In its recent update, the World Health Organization (WHO) dramatically reduced annual exposure limit values from 40 to 10 µg m−3 for NO2 and from 10 to 5 µg m−3 for PM2.5. We found that the average annual mean NO2 concentration for the network was 17.5 µg m−3 and 8.1 µg m−3 for PM2.5. While in exceedance of the WHO guideline levels, these average concentrations do not exceed legally binding UK/EU standards. The network average NO2 concentration was 12.5 µg m−3 higher than values reported by a nearby regional air quality monitoring station, showing the critical importance of monitoring close to sources before pollution is diluted. We demonstrate how data from a low-cost air pollution sensor network can reveal insights into patterns of air pollution and help determine whether sources are local or non-local. With spectral analysis, we investigate the variation of the pollution levels and identify typical periodicities. Both NO2 and PM2.5 have contributions from high-frequency sources; however, the low-frequency sources are significantly different. Using spectral analysis, we determine that at least 54.3±4.3 % of NO2 is from local sources, whereas, in contrast, only 37.9±3.5 % of PM2.5 is local.