Search

Accurate prediction of the Particulate Matter 2.5 (PM 2.5) plays a crucial role in the accurate management of air pollution and prevention of respiratory diseases. However, PM 2.5 as a time series is extremely difficult to accurately predict. In this paper, a Hybrid Integration (HIG) algorithm that combines data pre-processing, time-series decomposition, signal decomposition, a prediction module, a matching strategy, and a hybrid integrated optimization algorithm is proposed. First, the optimal parameters for the four individual models were selected by integrating multiple evaluation perspectives. Additivity was then determined by Seasonal and Trend decomposition using LOWESS (STL), followed by refinement decomposition using signal decomposition. The four new sequences were reconstructed using Range Entropy (RangeEn) and mapped to the models. Additionally, Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) methods were optimized using the HIG algorithm. The results show that the HIG-RNN and HIG-LSTM are more advantageous than the ordinary method in terms of reasonable weight assignment. Finally, an innovative confusion test method was developed to test the stability of the prediction direction. To ensure generalizability, validation was performed using PM 2.5 data from two regions of China. The results show that the method significantly improves the prediction performance and provides a powerful tool for policy formulation and management. [Display omitted] • A hybrid integration (HIG) algorithm is proposed. • Prediction results were evaluated using the original COI and improved ICOI. • Creative time-frequency analysis bypasses traditional time series constraints. • RangeEn can assess entropy series for regularity to avoid excessive decomposition. • A pioneer confusion test for model direction consistency check was developed. [ABSTRACT FROM AUTHOR]

Fine inhalable particulate matter (PM 2.5) is one of the major air pollutants that affect human health and the environment. Detailed knowledge of the spatial distribution of PM 2.5 is meaningful for the prevention and control of air pollution. Satellite remote sensing has become an effective way to observe PM 2.5 concentrations. However, most studies have focused on mapping PM 2.5 concentrations from satellite-derived daytime aerosol optical depth (AOD), which cannot effectively depict the nighttime atmospheric environment. This paper aims to develop a method to derive nighttime PM 2.5 concentrations in Nanjing, China, using the National Polar-orbiting Partnership (NPP)/Visible Infrared Imaging Radiometer Suite (VIIRS) nighttime light remote sensing data during September–December 2020. The relationship between the satellite at-sensor radiance, PM 2.5 concentrations and other environmental factors was first explored based on the nighttime radiative transfer equation. Taking into account the pixel direct radiation and the background scattered radiation, the spatial independent variables for estimating nighttime PM 2.5 were determined. Five machine learning algorithms and multiple linear regression (MLR) were employed to develop models to estimate nighttime PM 2.5 concentrations. The results showed that the MLR model had obviously lower accuracy than the machine learning models, and the RF model outperformed the other models, with a coefficient of determination (R2) of 0.81 and a mean absolute error (MAE) of 7.85 μg·m−3. Then, the developed model was applied to map the nighttime PM 2.5 concentrations over Nanjing, which well characterized the nighttime atmospheric environment at a fine resolution. This paper proposes a method to map nighttime PM 2.5 concentrations from nighttime light remote sensing data and provides references for monitoring nighttime atmospheric environments in other regions. • The relationship between nighttime PM 2.5 and at-sensor radiance was analyzed based on nighttime radiative transfer process. • Both the direct radiation and the background scattered radiation were included to estimate PM 2.5 concentrations. • Models that estimate nighttime PM 2.5 concentrations from NPP/VIIRS nighttime light remote sensing data were developed. • The performances of different models for estimating nighttime PM 2.5 concentrations were tested. • Random forest outperforms other machine learning algorithms. [ABSTRACT FROM AUTHOR]

Beijing, the capital of China, has experienced rapid industrialization, urbanization and motorization in recent decades. Consequently, air pollution in Beijing, especially fine particulate matter (PM 2.5 ) pollution, has gradually become a severe environmental issue, due to the continuing growth in energy consumption and the resulting multiple pollutant emissions. In response to the increasingly serious PM 2.5 pollution, Beijing's government implemented a series of policies, measures and regulations on air pollution prevention and control and took some concrete actions to improve air quality. In this paper, firstly, we summarize China's ambient air quality standards, China's policies and regulations on air pollution prevention and control. Secondly, we illustrate historical evolution and current status of air pollution in Beijing. Finally, we introduce control measures and actions in Beijing and its surrounding areas. The paper aims to help environmental scientists and policy makers around the world understand the past and current air pollution in Beijing and control strategies and actions taken by Beijing's government. [ABSTRACT FROM AUTHOR]

Abstract The principal motivation of this work is to evaluate the existing fuel use (gasoline or ethanol) and new alternative source of power supply (electricity) for vehicles in Brazil, and to assess potential to consume less petroleum and non-renewable fuels, in order to reduce the air pollution and greenhouse gas emissions. In the literature, there are several relevant published works which focus on this topic for developed countries, and other countries, such as Brazil are not fully investigated; therefore this gap was a motivation for this study. The methods consider the fuel production, electricity generation and powertrain production, the vehicle use phase stages and powertrain end of life only, which includes the recycling of vehicles and batteries. The goal and scope of this study is to evaluate and to compare the environmental impacts of vehicles in the Brazilian context. A life cycle assessment is carried out in this paper to assess the well-to-wheels for different scenarios of fuels consumption and powertrains configurations for a vehicle. The five analyzed scenarios are: conventional internal combustion engine vehicle fuelled by gasoline, conventional internal combustion engine vehicle fuelled by hydrous ethanol, conventional internal combustion engine vehicle fuelled by a mixture of gasoline and hydrous ethanol (flex-fuel vehicle), plug-in hybrid electric vehicle and battery electric vehicle. The common functional unit assumed for the analysis was 1.0 km traveled. The results show that the scenarios that use ethanol as fuel have higher environmental impacts for the categories of acidification, eutrophication and photochemical oxidation. The scenarios using gasoline have the higher impacts for abiotic depletion, fossil fuels abiotic depletion potential and global warming potential. Vehicles using lithium ions batteries have the highest impacts for human toxicity. The battery electric vehicle has smallest environmental impacts in general way, followed by vehicles using ethanol. The Brazilian government should increase its investment and develop the use of electric vehicles, since the country's electric mix is renewable, as well as further encourage the use of ethanol, since it generates less environmental impacts than gasoline. Highlights • Engines fuelled by ethanol are environmental favorable in four impact categories. • Ethanol engines have the worst environmental performance in three impact categories. • Electric vehicles yield higher human toxicity values due to the electricity generation. • Electric vehicles can reduce the greenhouse gas emissions compared to combustion vehicles. • Vehicles use phase have the greatest environmental impacts in all analyzed categories. [ABSTRACT FROM AUTHOR]

A growing literature on the pollution haven hypothesis has surged for decades. In this paper, we employ a city-level data set of 150 Chinese cities in 2014, and take spatial spillovers into account by using spatial econometric models, to investigate whether foreign capital inflows drive environmental degradation in China. The results suggest that foreign direct investment is negatively related to air pollution in China, indicating evidence of pollution halo hypothesis. Moreover, foreign direct investment has significant spatial technological spillovers, improving air quality in China. This study also finds that there is no evidence of an inverted U-shaped curve between income and air pollution. As income levels increase, air quality continues to worsen. The development of the tertiary industry is found to have a positive effect on air pollution. Densely populated cities tend to demand for better environmental quality. From the above analysis, it follows that policies handles are urgently needed to improve air quality in China. [ABSTRACT FROM AUTHOR]

This paper proposes a novel complementary approach to evaluate the public health benefits of air pollution control, where the joint impact on individuals' quality and length of life is fully quantified using Markov modelling. A Markov model which captures, for the first time: (i) air pollution's influence on population individuals' quality of life and life expectancy at baseline and (ii) dynamics in individuals' susceptibility to air pollution exposure, is developed. In order to represent the body of epidemiological evidence on the cardio-respiratory effects of long-term exposure to fine particulate air pollution, the model is structured around three diseases: chronic obstructive pulmonary disease, coronary heart disease and lung cancer. Application of the model provides the first estimates of age and gender-specific quality-adjusted life years (QALY) gains from air quality improvement in the UK. Reducing mean PM2.5 concentrations by 1μg/m3 in London and in England and Wales is expected to yield more than 63,000 and 540,000QALYs respectively, to adults aged 40 and above over their remaining lifetime, discounting at 3.5%p.a. At a WTP value for a QALY of £65,000, which is in line with recommendations for the UK, the expected discounted monetary benefit of the intervention amounts to £4 billion in London and £34 billion in England and Wales. [ABSTRACT FROM AUTHOR]

Over the past decade there has been significant pressure to minimise emissions and safety risks related to commercial driving. This pressure to meet the triple bottom line of cost, environment, and society has often resulted in the rapid application of vehicle technologies designed to mitigate undesired effects. Often the cognitive and behavioural effects of technologies on the commercial driver have not received in-depth analysis to determine comprehensive viability. As such, this paper aims to identify a timescale for implementation for future technologies for UK road freight, and likely associated human factors issues, improving upon the currently employed 'trial-and-error' approach to implementation which may carry high economic, environmental, safety-related risk. Thought experiments are carried out to broadly explore these future systems. Furthermore, this work aims to examine whether technology alone will be enough to meet future CO2 reduction targets, and assess the role of behavioural and systems interventions for future research. [ABSTRACT FROM AUTHOR]

Along with China's modern industrialization, challenges on smog crisis are raising dramatically in the past decade. The sources of municipal smog are multiple and complex, one of which is construction dust emission due to the rapid urbanization. In literature, there are studies focusing on the end-pipe treatment of construction dust; however, very little research has been conducted from the perspective of dust mitigation in developing countries. To fill in this research gap, this paper investigates the current situation of construction dust prevention and control in China, with the aim of providing insights for mitigating dust pollution caused by the construction industry. Through a combination of the content analysis, on-site observation, questionnaire survey and interviews with experienced professionals, a total of 11 related regulations are thoroughly reviewed, and the main sources of construction dust production are identified. A case study is further presented to demonstrate the prevailing dust control measures on site. Recommendations are proposed in order to increase the awareness of related stakeholders, including formulation of targeted regulations, establishment of an appropriate charging scheme, development of a feasible monitoring system, and enhancement of training and dissemination. [ABSTRACT FROM AUTHOR]

The control of emission gas from incinerators appears as a key issue for the improvement of the incineration technology. In this paper, we developed new sorbent materials based on calcium hydroxyapatite (Ca–HA) matrix. Using gelatine and bio–glass as porous and structural agents, which are largely available and have reasonable costs, powder of Ca–HA could be easily formulated into desired morphologies. As an example, a Ca–HA based accumulator having good porosity and mechanical stability was obtained by mixing Ca–HA powder with gelatine, bio–glass and water, followed by molding, then calcination steps. This accumulator showed an interesting capacity for the collection and tracing of Cd used as single model heavy metal in gas phase. [ABSTRACT FROM AUTHOR]

More timely and accurate air quality forecasting could contribute to better public health protection and air pollution prevention. Particulates are a significant indicator for measuring the degree of air pollution. This paper reports on research to model an early warning tool for coarse particulates when assessing the impact of the 12 satellite-derived and ground-based meteorological pollutants out of 30 pollutants considered using hourly Australian data from January 2018–December 2020. A one-dimensional convolutional neural network (CNN) was integrated with a one-directional fully gated recurrent unit (GRU) to forecast consecutive hours' air quality. The CNN model acts as a spatial feature extractor, whereas the new generation GRU makes it computationally efficient. The resultant hybrid ' CNN-GRU' is then comprehensively benchmarked outperforming an ensemble of six other deep learning models. The proposed model's efficacy is indicated at the four most air polluted Australian postcodes in the testing phase. A detailed error analysis with visual and statistical metrics for air quality forecasting ascertains the proposed model's countermeasure to reduce harm and loss. The practical tool is immensely beneficial and can be widely deployed to the regions of public health concern where air pollution is a significant hazard. [Display omitted] • A novel early warning hybrid PM10 forecasting framework designed for Australia. • 30 satellite and ground-based meteorological pollutants were considered with 7 modeling approaches. • CNN integrated with GRU outperformed the other models. • Early warning AI model show potential in the health, environment sector, and decision-making. [ABSTRACT FROM AUTHOR]

In this paper, we propose a behavioral approach to determine the extent to which the consumer/citizen distinction affects interpretations of monetary values in stated preferences methods. We perform a field experiment dealing with air pollution, where some (randomly selected) subjects are given the opportunity to behave politically by signing a petition for environmental protection prior to stating their private preferences in a standard contingent valuation exercise. We show that signing has the potential to influence respondents' willingness to pay values. Results indicate that even market-like situations are not immune to citizen behavior. [ABSTRACT FROM AUTHOR]

Abstract: This study summarize the barriers of low carbon technology transfer. Based on analysis of the findings of the literature on technology transfer, this paper presents a summary of key areas for future action in order to facilitate the transfer of low carbon technology to developing countries. [Copyright &y& Elsevier]

The purpose of this paper is to integrate the concepts of ecosystem services and disservices when assessing the efficacy of using urban forests for mitigating pollution. A brief review of the literature identifies some pollution mitigation ecosystem services provided by urban forests. Existing ecosystem services definitions and typologies from the economics and ecological literature are adapted and applied to urban forest management and the concepts of ecosystem disservices from natural and semi-natural systems are discussed. Examples of the urban forest ecosystem services of air quality and carbon dioxide sequestration are used to illustrate issues associated with assessing their efficacy in mitigating urban pollution. Development of urban forest management alternatives that mitigate pollution should consider scale, contexts, heterogeneity, management intensities and other social and economic co-benefits, tradeoffs, and costs affecting stakeholders and urban sustainability goals. [Copyright &y& Elsevier]

Abstract: Gas–solid carbonation of Air Pollution Control (APC) residues is a CO2 Capture and Storage (CCS) technology, where highly reactive Mg- or Ca-bearing materials adsorb CO2 and form stable Mg- or Ca-carbonates. The carbonation kinetics of this reaction have been studied at different temperatures, CO2 concentrations, and at atmospheric pressure in order to select the best operative conditions on the basis of CO2 stored and reaction time. The samples were initially heated up to the operative conditions under argon atmosphere and then carbonated under a CO2–argon atmosphere. All carbonation kinetics were characterized by a rapid chemically controlled reaction followed by a slower product layer diffusion-controlled process. Maximum conversions between 60% and 80% were achieved, depending on the operative temperature and CO2 concentration. Temperature did not notably affect the maximum conversion obtained in the experiments performed at temperatures equal or above 400°C; the influence on the kinetics was masked by the change in initial composition due to dehydroxylation reaction and surface area while heating up to the operative temperature. A slight influence of CO2 concentration on the kinetics was observed, whereas no influence on the maximum conversion was noticed. The obtained results suggest that the flue gases with 10vol.% CO2 concentration can be directly used to form stable carbonates, thus lumping capture and storage in a single step. The APC residues produced from the existing incineration plants would cover only 0.02–0.05% of the total CO2 European storage capacity required to comply with the Kyoto protocol objectives. Nevertheless, the proposed carbonation route could be applied to other residues, such as Cement Kiln Dust, Paper mill residues and Stainless Steel Desulphurization slags, characterized by a high content of free calcium oxides and hydroxides, thus increasing the impact of this process option. [Copyright &y& Elsevier]

Abstract: This paper illustrates the mechanism of gas–solid contacting in a multistage counter-current fluidized bed reactor attached with downcomers. Experimental hold-up study has been carried out extensively using the air and lime particles as gas and solid phases, respectively. The reactor was operated in continuous regime for two-phase system over a wide range of operating conditions including height of the downcomer to determine the solids hold-up at each stage of the reactor. The data was generated under steady and stable operation of the column. Based on the experimental data, empirical correlation is proposed for predicting the solids hold-up in the multistage fluidization. The results in this study assume importance from the standpoint of design and steady operation of multistage fluidized bed reactor with downcomer as an air pollution control system for control of gaseous emissions in the industries. [Copyright &y& Elsevier]

Abstract: Anthropogenic release of greenhouse gases, especially CO2 and CH4 has been recognized as one of the main causes of global warming. Several measures under the Kyoto Protocol 1997 have been drawn up to reduce the greenhouse gases emission. One of the measures is Clean Development Mechanisms (CDM) that was created to enable developed countries to cooperate with developing countries in emission reduction activities. In Malaysia, palm oil industry particularly from palm oil mill effluent (POME) anaerobic treatment has been identified as an important source of CH4. However, there is no study to quantify the actual CH4 emission from the commercial scale wastewater treatment facility. Hence, this paper shall address the CH4 emission from the open digesting tanks in Felda Serting Hilir Palm Oil Mill. CH4 emission pattern was recorded for 52weeks from 3600m3 open digesting tanks. The findings indicated that the CH4 content was between 13.5% and 49.0% which was lower than the value of 65% reported earlier. The biogas flow rate ranged between 0.8lmin−1 m−2 and 9.8lmin−1 m−2. Total CH4 emission per open digesting tank was 518.9kgday−1. Relationships between CH4 emission and total carbon removal and POME discharged were also discussed. Fluctuation of biogas production was observed throughout the studies as a result of seasonal oil palm cropping, mill activities, variation of POME quality and quantity discharged from the mill. Thus only through long-term field measurement CH4 emission can be accurately estimated. [Copyright &y& Elsevier]

During coal combustion, different pollutants such as fly ash, sulfur oxides (SO2 and SO3), nitrogen oxides (NOx=NO+NO2) and volatile organic compounds (VOCs) are emitted. These pollutants are harmful to the environment and human health. Therefore different air-pollution-control technologies are used. Usually these technologies are designed for removing only a single pollutant. An integrated system for SO2, NOx and VOC simultaneous emission control is presented in the paper. The technology uses a high-energy electron-beam from an accelerator and ammonia to treat simultaneously SO2 and NOx, the obtained by-product can be used as a fertilizer. The industrial-demonstration plant at EPS Pomorzany in Szczecin is under optimization tests now. Moreover, the tests carried out with the pilot plant at EPS Kaweˆczyn have demonstrated the possibility of volatile-organic-compounds destruction and their final toxicity reduction. [Copyright &y& Elsevier]

The role of precursors' concentrations and meteorological conditions on the emerging ozone pollution problem in China has received wide attention, especially after the releasing of the Air Pollution Prevention Control and Action Plan (APPC) since 2013. With the decreasing trend of PM 2.5 nationwide, the effect of the strict control measures on increasing ozone variation has less been studied due to the challenge of complexity of nonlinear relationship among a number of factors on ozone formation. This paper evaluated the influence of both ozone precursors and meteorology on maximum daily average 8 h (MDA8) ozone at two urban sites and one rural site in Hebei province, China, from 2013 to 2017, by using a combined application of Kolmogorov-Zurbenko (KZ) filter and artificial neural network (ANN) model. Results showed that R2 was 0.80 between the measured and the simulated MDA8 ozone concentration when using meteorological factors and precursors' concentrations as input variables for ANN model. However, ANN model has limitation in estimating O 3 concentration peaks. The values of threat score (TS), probability of detection (POD) and false alarm rate (FAR) for MDA8 ozone concentration were 39%, 44% and 21%, respectively, throughout three studied sites in Hebei province. The annual average percentage change of precursor-related ozone was 0.67% from 2014 to 2017. Temperature, atmospheric pressure and boundary layer height were shown to account for 64% of the variability in long-term ozone levels. Ozone variation in Hebei province was reproduced mainly by meteorological parameters, and the contribution from precursors' concentration was smaller during the years when the APPC was implemented. [Display omitted] • Ozone level was estimated based on precursors' level and meteorological factors. • The ambient ozone concentration estimated by ANN model was acceptable. • Meteorology dominates the ozone variation in 2013–2017 in Hebei province. [ABSTRACT FROM AUTHOR]

• Coastal cities have higher PPCE, and northern cities have lower PPCE. • The overall performance of PPCE in 112 APPCK cities is relatively low. • 61 Cities have the high annual average reduction potential rate of PM2.5 pollution. • The technological progress is a significant contributor for improvement of Chinese cities. The State Council of China initiated an air pollution prevention and control key (APPCK) city program to drive the national economic development and air pollution control since 2003. However, little known about whether the initiation is efficient. This paper examined the PM2.5 pollution control efficiency (PPCE) of 112 Chinese APPCK cities in 2003–2017 using Super-slack-based measure (Super-SBM) model with undesirable outputs. Results show that: (1) PPCEs of coastal cities (e.g., Shanghai, Guangzhou, and Suzhou) are much higher than those of less-developed northern cities (e.g., Jiaozuo, Anyang and Kaifeng); (2) the overall PPCE of 112 APPCK cities is relatively low and improvable; (3) the annual average growth rate of global Malmquist-Luenberger productivity index is 6.3%; (4) the technological progress is a significant contributor to improve the PPCE of these cities with 3.1% global technological change. These results provide reference to not only the policy-makers of China for synergies and tradeoffs between economic development and PM2.5 pollution control but also the studies on PM2.5 pollution control efficiency in the international context. [ABSTRACT FROM AUTHOR]

Most developing countries in the world face the common challenges of reducing air pollution and advancing the process of sustainable development, especially in China. Air pollution research is a complex system and one of the main methods is through numerical simulation. The air quality model is an important technical method, it allows researchers to better analyze air pollutants in different regions. In addition, the SCB is a high-humidity and foggy area, and the concentration of atmospheric pollutants is always high. However, research on this region, one of the four most polluted regions in China, is still lacking. Reviewing the application of air quality models in the SCB air pollution has not been reported thoroughly. To fill these gaps, this review provides a comprehensive narration about i) The status of air pollution in SCB; ii) The application of air quality models in SCB; iii) The problems and application prospects of air quality models in the research of air pollution. This paper may provide a theoretical reference for the prevention and control of air pollution in the SCB and other heavily polluted areas in China and give some1inspirations for air pollution forecast in other countries with complex terrain. [Display omitted] • Current situation of air pollution in the Sichuan Basin of China is reviewed. • The development and classification of air quality models are summarized. • Application of air quality models in the study of Sichuan Basin air pollution are discussed. • Problems in the application and future research directions of air quality models are provided. [ABSTRACT FROM AUTHOR]

• A mathematic model is built to evaluate the air pollution of heating consumption. • The coal substitution policy can reduce the PM2.5 concentrations by about 20 μg/m3. • Effect of renewable energy and its development to air quality is considered. • PM2.5 concentration in 2030 will drop by about 27% in Northern China compared to 2016. The Air Pollution Prevention and Control Action Plan proposed in 2013 has contributed to the fossil fuel reduction in central heating, but the consumption of scattered coal in rural areas should not be overlooked as it accounts for nearly 50% pollutant emissions during the heating season. Air Pollution Prevention and Control Action Plan for Beijing-Tianjin-Hebei and Surrounding Areas was issued to solve the problem of scattered coal consumption and improve the heating energy structure in 2017. In this paper, an air quality-heating model is established to evaluate the air quality improvement potential and far-reaching influence of scattered coal consumption reduction in rural areas. Distinct from other air quality evaluation models, the proposed model is to evaluate the regional air quality related to the heating factors. The results indicate that the coal substitution policy can reduce PM2.5 concentrations in the heating season by about 20 μg/m3 in Beijing-Tianjin-Hebei and surrounding areas. Furthermore, predictions about the variation of PM2.5 concentration in the heating season are conducted, which indicate that the PM2.5 concentration of Beijing, Tianjin, Hebei and surrounding areas in 2030 will drop by 48%, 35%, 29% and 23% respectively compared to that in 2016. The reduction could be further enhanced to be 55%, 40%, 32% and 27% with the consideration of clean power development. This study is conducive to evaluate the clean heating technologies role in improving the environment and air quality. [ABSTRACT FROM AUTHOR]

Owing to the high nonlinearity and noise in the air quality index (AQI), tackling the uncertainties and fuzziness in the forecasting process is still a prevalent problem. Therefore, this study developed an intelligent hybrid air-quality forecasting system based on feature selection and a modified evolving interval type-2 quantum fuzzy neural network (eIT2QFNN), which provides accurate air-quality forecasting information by considering climate influencing factors. The main contributions of this study are as follows. The optimal input structure of the model is determined by the proposed second-stage feature-selection model, which can better extract the influencing variables and remove redundant information. Moreover, a novel multi-objective chaotic Bonobo optimizer algorithm is proposed to improve the eIT2QFNN. The modified eIT2QFNN implements AQI prediction by considering the importance of influencing variables that can cope with the uncertainties and fuzziness in the forecasting process. Finally, the Diebold-Mariano and modified Diebold-Mariano tests are employed to evaluate the performance of the proposed system. The experimental results demonstrate that our proposed system significantly improves the modeling performance in terms of high accuracy and compact structure, and can thus serve as an effective tool for air-quality management. Image 1 • An intelligent multi-variable air quality forecasting system is creatively proposed. • Two-stage feature selection is developed to determine the optimal input variables. • A multi-objective optimization algorithm is proposed to find the weight of variables. • eIT2QFNN is applied to forecast air quality with multiple factors considered. • The proposed system outperforms comparison models with high accuracy and efficiency. This paper proposes an intelligent multivariable air-quality forecasting system that can provide effective information for air-pollution prevention. [ABSTRACT FROM AUTHOR]

Long-term exposure to fine particulate matter (PM 2.5) poses a great threat to public health in China. To this end, the Chinese government promulgated the Air Pollution Prevention and Control Action Plan (the Action Plan) in 2013. However, the health benefits of the Action Plan have not been well explained. In this paper, the underlying causes of changes in premature mortality attributable to PM 2.5 pollution and the response of this mitigation policy in China were explored using sensitivity analysis. The simulated annual average PM 2.5 concentration reduced by 24.9% over mainland China from 2008 to 2016. Subsequently, national premature mortality would decrease by 14.4% from 1.14 million (95% CI: 0.54, 1.55) in 2008 to 0.98 million (95% CI: 0.44, 1.38) in 2016. Specifically, premature mortality reduced by 209,600 cases (−18.3%) owing to PM 2.5 reduction during 2008–2016, of which 188,500 cases were from 2014 to 2016 due to the Action Plan in 2013. Note that the health benefits were limited when compared with air quality improvements, mainly due to that the IER functions have a stable curve at higher concentration intervals. Meanwhile, premature mortality would have increased by 14.2% from 2008 to 2016 owing to demographic changes, substantially weakening the impact of the decrease in PM 2.5 and baseline mortality. The effectiveness of China's new air pollution mitigation policy was proved through the research. However, considering the non-linear response of mortality to PM 2.5 changes and the aggravation of demography trends, stronger emission control steps should be further taken to protect public health in China. Image 1 • Trends of PM 2.5 and attributable mortality before and after control policies were contrasted. • Underlying causes of changes in PM 2.5 -related deaths were analyzed comprehensively. • The influence of different factors on PM 2.5 -related deaths were analyzed in detail. • The implementation of the Action Plan has brought substantial health benefits. • Demographic and baseline mortality also play a part in changes in PM 2.5 -related deaths. [ABSTRACT FROM AUTHOR]

Air pollution has endangered both ecological environment and human health. Long-term prediction of air quality index (AQI) is an effective approach to early warning of, and prompt response to, pollution events to support cleaner industrial production. However, existing approaches to forecasting long-term air quality need further improvement. In this paper, we proposed a novel spatial-temporal deep learning algorithm based on bidirectional gated recurrent unit integrated with attention mechanism (BiAGRU), for more accurate air quality forecasting. The historical air quality measurements and meteorological monitoring data were constructed as a spatial-temporal matrix suitable for model input. The performance of the proposed BiAGRU model was evaluated by a series of metrics. The RMSE, MAE, R 2 and Fractional Bias (FB) values of the proposed BiAGRU model are 31.10, 23.06, 0.60, and 0.015, respectively, for 24 h multi-step ahead prediction assignments using Huaihai Economic Zone dataset. Quantitative comparison between models indicates the developed BiAGRU model outperformed various traditional machine learning algorithms and advanced deep neural network methods in term of lower error bias and higher accuracy and regression scores. This work is of importance to strengthen regional prevention and control of air pollution. Image 1 • A novel artificial intelligence methodology for multi-step ahead forecasting and analysis of air quality. • Inclusion of spatial information improves regional air quality forecasting. • Model performance is evaluated against comprehensive metrics. • The novel spatial-temporal BiAGRU model outperformed several state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Air pollution are known to have negative impacts on human health and the ecosystem, and it also contributes to climate change. Hence, prevention and control of air pollution is an urgent need in China, and air pollution prediction can provide reliable information for this process. Therefore, it is essential to establish effective air pollution prediction with an early warning model. Currently, one widely used air pollution prediction technology is the error correction model. However, this traditional method does not use data preprocessing technology. Therefoere, this paper presents an improved hybrid model named CEEMD-SLM-ECM (Complementary Set Empirical Mode Decomposition-Statistical Learning Model-Error Correction Model), which used the CEEMD data preprocessing technology together with statistical learning models. Furthermore, selected AQI (air quality index) data of 17 port cities in the 21st Century Maritime Silk Road Economic Belt were selected to test the forecasting ability of the proposed model. Data analysis shows that the CEEMD-SLM-ECM model has much higher accuracy compared with the traditional error correction model. So, the CEEMD-SLM-ECM is a very effective predictive model that can provide accurate prediction for air quality early warning. • A new improved error correction model CEEMD-SLM-ECM is established. • Data preprocessing is helpful for improving the prediction accuracy. • CEEMD-SLM-ECM is effective for AQI forecasting. [ABSTRACT FROM AUTHOR]

• A systematic review was conducted on traffic contribution estimates reported by 155 previous studies. • Our analysis included 169 cities worldwide. • Traffic contribution to PM in Europe, North America and Oceania is 36% lower than other regions. • Traffic contribution is 28% lower among studies published after 2005. • Traffic contribution is 24% lower among cities with less than 500,000 inhabitants. Quantifying traffic contribution to air pollution in urban settings is required to inform traffic management strategies and environmental policies that aim at improving air quality. Assessments and comparative analyses across multiple urban areas are challenged by the lack of datasets and methods available for global applications. In this study, we quantify the traffic contribution to particulate matter concentration in multiple cities worldwide by synthesising 155 previous studies reported in the World Health Organization (WHO)'s air pollution source apportionment data for PM 10 and PM 2.5. We employed a Bayesian multilevel meta -regression that accounts for uncertainties and captures both within- and between-study variations (in estimation methods, study protocols, etc.) through study-specific and location-specific explanatory variables. The final sample analysed in this paper covers 169 cities worldwide. Based on our analysis, traffic contribution to air pollution (particulate matter) varies from 5% to 61% in cities worldwide, with an average of 27%. We found that variability in the traffic contribution estimates reported worldwide can be explained by the region of study, publication year, PM size fraction, and population. Specifically, traffic contribution to air pollution in cities located in Europe, North America, or Oceania is on average 36% lower relative to the rest of the world. Traffic contribution is 28% lower among studies published after 2005 than those published on or before 2005. Traffic contribution is on average 24% lower among cities with less than 500,000 inhabitants and 19% higher when estimated based on PM 10 relative to PM 2.5. This quantitative summary overcomes challenges in the data and provides useful information for health impact modellers and decision-makers to assess impacts of traffic reduction policies. [ABSTRACT FROM AUTHOR]

Most of the previous researches estimate influencing factors impact on air quality average without considering the heterogeneity of influential factors on different levels of air quality. In order to detect the different effects of influencing factors on air quality index (AQI) between lower-AQI and higher-AQI cities, this study applies a spatial quantile regression model (SQRM) to investigate heterogeneity of influential factors on AQI, while accounting for spatial autocorrelation of AQI. The results show that heterogeneity effects of windspeed, terrain slope, urbanization sprawl and spatial autocorrelation on AQI are large across the entire AQI spectrum, while heterogeneity effects of precipitation, temperature, relative humidity, terrain fluctuation and urbanization intensity on AQI are not obvious. The spatial positive autocorrelation of AQI in higher-AQI cities is greater than that in lower-AQI cities. Compared with higher-AQI cities, the negative impact of terrain slope on AQI is lager in lower-AQI cities. One unit increase in wind speed contributes AQI to decrease 9.31 to 5.64 then to 5.39 for lower, medium and higher-AQI cities. One unit increase in urbanization sprawl would lead AQI increase 25.6 to 15.6 then to 10.5 for lower, medium and higher-AQI cities. The heterogeneity analysis of meteorological, topographic and socioeconomic factors effects on air quality are of guiding significance for realizing the differentiation of policy measures for air pollution prevention and control. Image 1 • Nighttime light data is used to construct urbanization indicators. • SQRM detects heterogeneity of influential factors on lower and higher AQI cities. • Spatial positive autocorrelation of AQI is not balanced across entire AQI spectrum. • Wind speed contributes to air quality to different extent in cities of China. • Effects of urbanization breadth and intensity on AQI are positive and negative. This paper detects the heterogeneity of influencing factors on AQI between lower-AQI and higher-AQI cities in China. [ABSTRACT FROM AUTHOR]

Theoretical predictions on the impact of environmental regulations on firm value in stock market are inconclusive. This paper examines whether and how stock market reacts to environmental regulations in China. We find that overall market-wide reactions are inconclusive while the cross-sectional tests show that stocks in polluting industries significantly and robustly underperform other stocks. Moreover, the worsening effect of environmental regulations on firm value is more pronounced among firms without political connections and firms located in rons with more effective judicial enforcement as the investors expect that these regulations will be effectively enforced. Our results show that China's green campaign does have value implications for stock markets. • China's Air Pollution Prevention and Control Action Plan affects shareholder value. • High-polluting stocks significantly underperform low-polluting stocks. • Stocks without political connections in high-polluting industries show lower returns. • Better judicial enforcement makes the differences in shareholder value stronger. [ABSTRACT FROM AUTHOR]

As air pollution becomes more and more severe, air quality prediction has become an important approach for air pollution management and prevention. In recent years, a number of methods have been proposed to predict air quality, such as deterministic methods, statistical methods as well as machine learning methods. However, these methods have some limitations. Deterministic methods require expensive computations and specific knowledge for parameter identification, while the forecasting performance of statistical methods is limited due to the linear assumption and the multicollinearity problem. Most of the machine learning methods, on the other hand, cannot capture the time series patterns or learn from the long-term dependencies of air pollutant concentrations. Furthermore, there is a lack of methods that could generate high prediction accuracy for air quality forecasting at larger temporal resolutions, such as daily and weekly or even monthly. This paper, therefore, proposes a deep learning-based method namely transferred bi-directional long short-term memory (TL-BLSTM) model for air quality prediction. The methodology framework utilizes the bi-directional LSTM model to learn from the long-term dependencies of P M 2.5 , and applies transfer learning to transfer the knowledge learned from smaller temporal resolutions to larger temporal resolutions. A case study is conducted in Guangdong, China to test the proposed methodology framework. The performance of the framework is compared with other commonly seen machine learning algorithms, and the results show that the proposed TL-BLSTM model has smaller errors, especially for larger temporal resolutions. • A transfer learning-based bi-directional long short-term memory model is proposed. • BLSTM achieves better prediction performance at smaller temporal granularities. • Transfer learning can lower the error of BLSTM at larger temporal granularities. • Self-transfer learning contributes little to improve, or even worsens the performance. [ABSTRACT FROM AUTHOR]