scholarly journals Urban PM2.5 Concentration Prediction via Attention-Based CNN–LSTM

2020 ◽  
Vol 10 (6) ◽  
pp. 1953 ◽  
Author(s):  
Songzhou Li ◽  
Gang Xie ◽  
Jinchang Ren ◽  
Lei Guo ◽  
Yunyun Yang ◽  
...  
Keyword(s):  
Particulate Matter ◽  
Air Quality ◽  
Air Pollutant ◽  
Quality Data ◽  
Coefficient Of Determination ◽  
Series Data ◽  
The Past ◽  
Lstm Network ◽  
Concentration Prediction ◽  
Pm2.5 Concentration

Urban particulate matter forecasting is regarded as an essential issue for early warning and control management of air pollution, especially fine particulate matter (PM2.5). However, existing methods for PM2.5 concentration prediction neglect the effects of featured states at different times in the past on future PM2.5 concentration, and most fail to effectively simulate the temporal and spatial dependencies of PM2.5 concentration at the same time. With this consideration, we propose a deep learning-based method, AC-LSTM, which comprises a one-dimensional convolutional neural network (CNN), long short-term memory (LSTM) network, and attention-based network, for urban PM2.5 concentration prediction. Instead of only using air pollutant concentrations, we also add meteorological data and the PM2.5 concentrations of adjacent air quality monitoring stations as the input to our AC-LSTM. Hence, the spatiotemporal correlation and interdependence of multivariate air quality-related time-series data are learned by the CNN–LSTM network in AC-LSTM. The attention mechanism is applied to capture the importance degrees of the effects of featured states at different times in the past on future PM2.5 concentration. The attention-based layer can automatically weigh the past feature states to improve prediction accuracy. In addition, we predict the PM2.5 concentrations over the next 24 h by using air quality data in Taiyuan city, China, and compare it with six baseline methods. To compare the overall performance of each method, the mean absolute error (MAE), root-mean-square error (RMSE), and coefficient of determination (R2) are applied to the experiments in this paper. The experimental results indicate that our method is capable of dealing with PM2.5 concentration prediction with the highest performance.

scholarly journals An Air Quality Prediction Model Based on a Noise Reduction Self-Coding Deep Network

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jianxian Cai ◽  
Xun Dai ◽  
Li Hong ◽  
Zhitao Gao ◽  
Zhongchao Qiu
Keyword(s):  
Time Series ◽  
Air Quality ◽  
Prediction Model ◽  
Noise Reduction ◽  
Prediction Accuracy ◽  
Air Pollutant ◽  
Monitoring Data ◽  
Series Data ◽  
Deep Network ◽  
Lstm Network

Aiming at remedying the problem of low prediction accuracy of existing air pollutant prediction models, a denoising autoencoder deep network (DAEDN) model that is based on long short-term memory (LSTM) networks was designed. This model created a noise reduction autoencoder with an LSTM network to extract the inherent air quality characteristics of original monitoring data and to implement noise reduction processing on monitoring data to improve the accuracy of air quality predictions. The LSTM network structure in the DAEDN model was designed as bidirectional LSTM (Bi-LSTM) to solve the problem of a lag in the unidirectional LSTM prediction results and thereby to further improve the prediction accuracy of the prediction model. Using air pollutant time series data, the DAEDN model was trained using hourly PM2.5 concentration data collected in Beijing over 5 years. The experimental results show that the DAEDN model can extract more stable features from the noisy input after training was completed. The models were evaluated using RMSE and MAE, and the results show that the indexes are 15.504 and 6.789; compared with unidirectional LSTM, it is reduced by 7.33% and 5.87%, respectively. In addition, the new prediction model essentially considered the time series properties of the prediction of the concentration of spatial pollutants and the fully integrated environmental big data, such as air quality monitoring, meteorological monitoring, and forecasting.

scholarly journals The Diamond League athletic series: does the air quality sparkle?

2021 ◽  
Author(s):  
James R. Hodgson ◽  
Lee Chapman ◽  
Francis D. Pope
Keyword(s):  
Particulate Matter ◽  
Air Quality ◽  
Performance Metrics ◽  
Urban Air Pollution ◽  
Quality Data ◽  
Performance Variation ◽  
Short And Long Term ◽  
Respiratory Conditions ◽  
Race Performance

AbstractUrban air pollution can have negative short- and long-term impacts on health, including cardiovascular, neurological, immune system and developmental damage. The irritant qualities of pollutants such as ozone (O3), nitrogen dioxide (NO2) and particulate matter (PM) can cause respiratory and cardiovascular distress, which can be heightened during physical activity and particularly so for those with respiratory conditions such as asthma. Previously, research has only examined marathon run outcomes or running under laboratory settings. This study focuses on elite 5-km athletes performing in international events at nine locations. Local meteorological and air quality data are used in conjunction with race performance metrics from the Diamond League Athletics series to determine the extent to which elite competitors are influenced during maximal sustained efforts in real-world conditions. The findings from this study suggest that local meteorological variables (temperature, wind speed and relative humidity) and air quality (ozone and particulate matter) have an impact on athletic performance. Variation between finishing times at different race locations can also be explained by the local meteorology and air quality conditions seen during races.

scholarly journals Effectiveness of SOx, NOx, and Primary Particulate Matter Control Strategies in the Improvement of Ambient PM Concentration in Taiwan

Atmosphere ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 460
Author(s):  
Jiun-Horng Tsai ◽  
Ming-Ye Lee ◽  
Hung-Lung Chiang
Keyword(s):  
Particulate Matter ◽  
Air Quality ◽  
Model Simulation ◽  
Control Strategies ◽  
Ambient Air ◽  
Clean Air Act ◽  
Control Measures ◽  
Control Plan ◽  
Clean Air ◽  
Pm2.5 Concentration

The Community Multiscale Air Quality (CMAQ) measurement was employed for evaluating the effectiveness of fine particulate matter control strategies in Taiwan. There are three scenarios as follows: (I) the 2014 baseline year emission, (II) 2020 emissions reduced via the Clean Air Act (CAA), and (III) other emissions reduced stringently via the Clean Air Act. Based on the Taiwan Emission Data System (TEDs) 8.1, established in 2014, the emission of particulate matter 2.5 (PM2.5) was 73.5 thousand tons y−1, that of SOx was 121.3 thousand tons y−1, and that of NOx was 404.4 thousand tons y−1 in Taiwan. The CMAQ model simulation indicated that the PM2.5 concentration was 21.9 μg m−3. This could be underestimated by 24% in comparison with data from the ambient air quality monitoring stations of the Taiwan Environmental Protection Administration (TEPA). The results of the simulation of the PM2.5 concentration showed high PM2.5 concentrations in central and southwestern Taiwan, especially in Taichung and Kaohsiung. Compared to scenario I, the average annual concentrations of PM2.5 for scenario II and scenario III showed reductions of 20.1% and 28.8%, respectively. From the results derived from the simulation, it can be seen that control of NOx emissions may improve daily airborne PM2.5 concentrations in Taiwan significantly and control of directly emitted PM2.5 emissions may improve airborne PM2.5 concentrations each month. Nevertheless, the results reveal that the preliminary control plan could not achievethe air quality standard. Therefore, the efficacy and effectiveness of the control measures must be considered to better reduce emissions in the future.

scholarly journals Regional Energy, CO2, and Economic and Air Quality Index Performances in China: A Meta-Frontier Approach

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 2119 ◽  
Author(s):  
Ying Li ◽  
Yung-Ho Chiu ◽  
Liang Lu
Keyword(s):  
Particulate Matter ◽  
Energy Consumption ◽  
Air Quality ◽  
Quality Index ◽  
Air Pollutant ◽  
Air Quality Index ◽  
Significant Difference ◽  
Desirable Output ◽  
Reduce Emissions ◽  
Carbon Dioxide Co2

Rapid economic development has resulted in a significant increase in energy consumption and pollution such as carbon dioxide (CO2), particulate matter (PM2.5), particulate matter 10 (PM10), SO2, and NO2 emissions, which can cause cardiovascular and respiratory diseases. Therefore, to ensure a sustainable future, it is essential to improve economic efficiency and reduce emissions. Using a Meta-frontier Non-radial Directional Distance Function model, this study took energy consumption, the labor force, and fixed asset investments as the inputs, Gross domestic product (GDP) as the desirable output, and CO2 and the Air Quality Index (AQI) scores as the undesirable outputs to assess energy efficiency and air pollutant index efficiency scores in China from 2013–2016 and to identify the areas in which improvements was necessary. It was found that there was a large gap between the western and eastern cities in China. A comparison of the CO2 and AQI in 31 Chinese cities showed a significant difference in the CO2 emissions and AQI efficiency scores, with the lower scoring cities being mainly concentrated in China’s western region. It was therefore concluded that China needs to pay greater attention to the differences in the economic levels, stages of social development, and energy structures in the western cities when developing appropriately focused improvement plans.

Research Insights: What will People Pay for SMS Air Quality Alerts and Will They Avoid Air Pollution in Response?

2021 ◽  
Author(s):  
Rema Hanna ◽  
Bridget Hoffmann ◽  
Paulina Oliva ◽  
Jake Schneider
Keyword(s):  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Willingness To Pay ◽  
The Past ◽  
High Pollution

Male, younger, and higher-income respondents as well as those who perceived high pollution in recent days showed greater willingness to pay for SMS air quality alerts. Willingness to pay was uncorrelated with actual recent high pollution. Recipients of SMS alerts indicated having received air pollution information via SMS, along with reporting a high-pollution day in the past week and having stayed indoors on the most recent day they perceived pollution to be high. However, alert recipients were not more accurate in identifying which specific days had high pollution than other respondents. Households that received a free N95 mask were more likely to report utilizing a mask with a filter during the past two weeks but not more likely to report using a mask with a filter on the specific days with high particulate matter.

scholarly journals Air Quality Index and Air Pollutant Concentration Prediction Based on Machine Learning Algorithms

2019 ◽  
Vol 9 (19) ◽  
pp. 4069 ◽  
Author(s):  
Huixiang Liu ◽  
Qing Li ◽  
Dongbing Yu ◽  
Yu Gu
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Air Quality ◽  
Regression Models ◽  
Quality Index ◽  
Air Pollutant ◽  
Air Quality Index ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Support Vector

Air pollution has become an important environmental issue in recent decades. Forecasts of air quality play an important role in warning people about and controlling air pollution. We used support vector regression (SVR) and random forest regression (RFR) to build regression models for predicting the Air Quality Index (AQI) in Beijing and the nitrogen oxides (NOX) concentration in an Italian city, based on two publicly available datasets. The root-mean-square error (RMSE), correlation coefficient (r), and coefficient of determination (R2) were used to evaluate the performance of the regression models. Experimental results showed that the SVR-based model performed better in the prediction of the AQI (RMSE = 7.666, R2 = 0.9776, and r = 0.9887), and the RFR-based model performed better in the prediction of the NOX concentration (RMSE = 83.6716, R2 = 0.8401, and r = 0.9180). This work also illustrates that combining machine learning with air quality prediction is an efficient and convenient way to solve some related environment problems.

Comparison of Modeled-to-Monitored PM2.5 Exposure Concentrations Resulting from Transportation Emissions in a Near-Road Community

2020 ◽  
Vol 2674 (12) ◽  
pp. 130-143
Author(s):  
Mayra Chavez ◽  
Wen-Whai Li
Keyword(s):  
Air Quality ◽  
Meteorological Data ◽  
Temporal Variations ◽  
Air Pollutant ◽  
Pollutant Emissions ◽  
Spatial And Temporal Variations ◽  
Quality Data ◽  
Background Concentrations ◽  
Regional Background ◽  
Transportation Emissions

Residents living in near-road communities are exposed to traffic-related air pollutants, which can adversely affect their health. Near-road communities are expected to observe significant spatial and temporal variations in pollutant concentrations. Determining these variations in the surrounding areas can help raise awareness among government agencies of these underserved communities living near highways. This study conducted traffic and air quality measurements along with emission and dispersion modeling of the exposure to transportation emissions of a near-road urban community adjacent to the US 54 highway (US 54), with annual average daily traffic (AADT) of 107,237. The objectives of this study were (i) to develop spatial and temporal patterns of pollutant concentration variation and (ii) to apportion the differences in exposure concentrations to background concentrations and those that are contributed from major highways. It was observed that: (a) particulate matter (PM2.5) in near-road communities is dominated by the regional background concentrations which account for more than 85% of the pollution; and (b) only near-road receptors are affected by the traffic-related air pollutant emissions from major highways while spatial and temporal variations of PM2.5 concentrations in near-road communities are less influenced by local traffic, subsiding rapidly to negligible concentrations at 300 m from the road. Modeled PM2.5 concentrations were compared with monitored data. For better air quality impact assessments, higher quality data such as time-specific traffic volume and fleet information as well as site-specific meteorological data could help yield more accurate concentration predictions. Modeled-to-monitored comparison shows that air quality in near-road communities is dominated by regional background concentrations.

scholarly journals Comparative Analysis of Indoor and Outdoor Particulate Matter Concentrations and Air Quality in Ogbomoso, Nigeria

2020 ◽  
Vol 10 (28) ◽  
Author(s):  
Musibau O. Jelili ◽  
Adeniyi S. Gbadegesin ◽  
Abimbola T. Alabi
Keyword(s):  
Particulate Matter ◽  
Air Quality ◽  
World Health ◽  
Health Concern ◽  
Coefficient Of Determination ◽  
Outdoor Air ◽  
Outdoor Air Quality ◽  
The World ◽  
Particle Pollution ◽  
Indoor And Outdoor

Background Airborne particulates are an issue in many urban regions around the world and their detrimental impact on human health has increasingly become a public health concern. Objectives The aim of the present study was to examine particle pollution in an urban settlement in Nigeria. This study examines the extent, spatial variation, and sources of indoor and outdoor particulate matter (PM) concentrations in Ogbomoso, Nigeria. Methods The survey research method was adopted. Sampling included 385 buildings across selected precincts and different residential zones in the town of Ogbomoso. Particulate matter analytes (PM1, PM2.5 and PM10) within/around each building were measured with a particle counter and details on domestic utilities/practices were obtained with a questionnaire. Analysis of variance was used to determine inter-zonal variations in PM levels and simple linear regression was used to analyze the relationship between indoor and outdoor air quality. Results Indoor and outdoor respirable particle (PM2.5) concentrations were lower than the World Health Organization (WHO) Interim Target limit of 75 μg/m3, while concentrations of inhalable particles (PM10) were higher than the set limit of 150 μg/m3 for daily averages. Coarse particles dominated, with an accumulative PM2.5/PM10 ratio of 0.24. The inter-zonal analysis of PM concentrations revealed that indoor and outdoor PM levels varied significantly by residential zone (p = 0.0005; p = 0.01, respectively). Regression analysis showed a significant but weak relationship between indoor and outdoor PM levels (r = +0.221), while the coefficient of determination (R2 = 0.049) showed that only about 5% of the variation in indoor air quality was associated with outdoor air quality. Particle pollution inducers were identified in the residents' waste disposal methods and adopted fuels/energy sources, with firewood and charcoal linked with increased concentrations of particulate matter. Conclusions Air quality was relatively poor in the study area given observed particulate matter concentrations. Cleaner fuels, effective waste management systems and improved roads are needed to foster better air quality in the study area. Competing Interests The authors declare no competing financial interests

scholarly journals Spatial Extent and Distribution of Ambient Airborne Particulate Matter (PM2.5) in Selected Land Use Sites in Nairobi, Kenya

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Caroline Kiai ◽  
Christopher Kanali ◽  
Joseph Sang ◽  
Michael Gatari
Keyword(s):  
Land Use ◽  
Air Pollution ◽  
Particulate Matter ◽  
Air Quality ◽  
Low Cost ◽  
Airborne Particulate Matter ◽  
Spatial Extent ◽  
Airborne Particulate ◽  
Concentration Levels ◽  
Pm2.5 Concentration

Air pollution is one of the most important environmental and public health concerns worldwide. Urban air pollution has been increasing since the industrial revolution due to rapid industrialization, mushrooming of cities, and greater dependence on fossil fuels in urban centers. Particulate matter (PM) is considered to be one of the main aerosol pollutants that causes a significant adverse impact on human health. Low-cost air quality sensors have attracted attention recently to curb the lack of air quality data which is essential in assessing the health impacts of air pollutants and evaluating land use policies. This is mainly due to their lower cost in comparison to the conventional methods. The aim of this study was to assess the spatial extent and distribution of ambient airborne particulate matter with an aerodynamic diameter less than 2.5 μm (PM2.5) in Nairobi City County. Seven sites were selected for monitoring based on the land use type: high- and low-density residential, industrial, agricultural, commercial, road transport, and forest reserve areas. Calibrated low-cost sensors and cyclone samplers were used to monitor PM2.5 concentration levels and gravimetric measurements for elemental composition of PM2.5, respectively. The sensor percentage accuracy for calibration ranged from 81.47% to 98.60%. The highest 24-hour average concentration of PM2.5 was observed in Viwandani, an industrial area (111.87 μg/m³), and the lowest concentration at Karura (21.25 μg/m³), a forested area. The results showed a daily variation in PM2.5 concentration levels with the peaks occurring in the morning and the evening due to variation in anthropogenic activities and the depth of the atmospheric boundary layer. Therefore, the study suggests that residents in different selected land use sites are exposed to varying levels of PM2.5 pollution on a regular basis, hence increasing the potential of causing long-term health effects.

Sign in / Sign up

Export Citation Format

Share Document