Air Pollution Prediction Research Articles

Impact of the planetary boundary layer on air quality simulations over the Yangtze River Delta region, China

The city clusters in eastern coastal China have suffered from serious air pollution in the past decades, which is partially related to the complex local topography and meteorological conditions. The planetary boundary layer (PBL) scheme is a critical parameter for accurate meteorology simulations and air quality predictions. In this study, we analyze the impact of four typical PBL schemes, namely, Yonsei University (YSU), Mellor-Yamada-Nakanishi-Niino Level 2.5 (MYNN), Asymmetric Convective Model version 2 (ACM2), and Mellor-Yamada-Janjic (MYJ) PBL, within the Weather Research and Forecasting (WRF) model to assess their impacts on the simulations of air pollutant concentrations based on the Comprehensive Air Quality Model with Extensions (CAMx) for the Yangtze River Delta (YRD) region, one of the most developed city clusters in eastern China. The results indicate that the MYNN scheme performs best in terms of fine particulate matter (PM2.5) and nitrogen dioxide (NO2) simulations, with mean bias of 4.8 μg m−3 and 9.3 μg m−3 in summer and 11.7 μg m−3 and 5.4 μg m−3 in winter, respectively. The YSU scheme performs best for ozone (O3) prediction, with better simulation results in summer than in winter. Notably, some discrepancies among different PBL schemes in the prediction of air pollution are directly associated with the complex topography. For the prediction of PM2.5, the MYJ and YSU schemes tend to overestimate the concentrations in the plains of Jiangsu and northern Anhui while underestimating PM2.5 in the hilly areas compared with the MYNN scheme. Meanwhile, the performance of the ACM2 scheme is opposite to that of the MYJ and YSU schemes. For O3 predictions, MYJ overestimates O3 in the eastern coastal area and underestimates O3 in the inland areas in summer compared with the YSU scheme, while the ACM2 scheme is the opposite of the MYJ scheme, and the MYNN scheme consistently overestimates O3.

RETRACTED ARTICLE: Prediction of air pollutants and rural green tourism factors based on dynamic migration

RETRACTED ARTICLE: Prediction of air pollutants and rural green tourism factors based on dynamic migration

Heterogeneous spatiotemporal copula‐based kriging for air pollution prediction

AbstractAir pollutants have a significant negative impact on human health, especially cardiovascular and respiratory. An efficient and effective spatiotemporal model for air pollution prediction is urgently needed to help strengthen air pollution control and improve air quality. Empirical statistical models have been widely applied for spatiotemporal prediction. However, they are not capable of dealing well with space‐time heterogeneity and dependency, thereby achieving lower accuracy. Here, a hybrid frame named heterogeneous spatiotemporal copula‐based kriging is proposed for fine particulate matter (PM2.5) concentration prediction; it is a multi‐time, multi‐site kriging model based on spatiotemporal clustering. The proposed model is capable of addressing spatiotemporal heterogeneity effectively and accounting for the spatiotemporal dependence by copula‐based covariance functions. To evaluate the effectiveness of the proposed approach, an experiment on daily PM2.5 data in China in 2016 was carried out. The results (MAE = 6.48, RMSE = 10.68, = 0.919) show that the proposed model can achieve good performance in PM2.5 prediction, which is of great significance in regional air quality management.

Large scale air pollution prediction with deep convolutional networks

Large scale air pollution prediction with deep convolutional networks

Comparative assessment of modeling deep learning networks for modeling ground-level ozone concentrations of pandemic lock-down period

Covid-19 pandemic lock-down has resulted significant differences in air quality levels all over the world. In contrary to decrease seen in primary pollutant species, many of the countries have experienced elevated ground-level ozone levels in this period. Air pollution forecast gains more importance to achieve air quality management and take measures against the risks under such extra-ordinary conditions. Statistical models are indispensable tools for predicting air pollution levels. Considering the complex photochemical reactions involved in tropospheric ozone formation, modeling this pollutant requires efficient non-linear approaches. In this study, deep learning methods were applied to forecast hourly ozone levels during pandemic lock-down for an industrialized region in Turkey. With this aim, different deep learning methods were tested and efficiencies of the models were compared considering the calculated RMSE, MAE, R2 and loss values.

RETRACTED ARTICLE: Urban air pollution diffusion status and sports training physical fitness measurement based on the Internet of things system

The sustainable development of modern industrial civilization and modern rapid development have brought many pollution problems. Especially in recent years, especially air pollution has become very popular, with the vigorous development of the Internet of things system and the popularity of mobile phones and portable intelligent terminals getting higher and higher. This project proposes to combine these two technologies to build a set of air pollution diffusion quality monitoring system based on Internet of things technology. This paper also uses a CFD method to study the number and pollution distribution of wind turbines in the city. It is hoped that the role and relationship among topography, wind field, and pollution distribution can be discussed in more detail, and the CFD method can be applied to the complex field of urban wind and pollution. The purpose of this paper is to find out the control of urban air pollution and to provide guidance, control, air pollution prediction, industrial zone design, and so on for using the CFD method to deal with urban air pollution. In recent years, with the change of the concept of offensive advocacy, offensive and defensive sides are using more physical violence and have a greater demand for physical fitness. Therefore, good physical fitness plays an important role in the fierce competition, and coaches at all levels pay more and more attention to sports training. However, due to the fact that the current concept of “physical fitness” is not clear and there is no complete division of the overall energy structure, this paper puts forward the definition of physical fitness test. This paper studies the pollution problem of modern industrial civilization and the development of Internet of things system and applies it to improve the physical fitness training, so as to improve the physical fitness of athletes.

Effects of air pollution on physiological traits of Ligustrum lucidum Ait. leaves in Luoyang, China

Leaves of trees experience the maximum brunt of exposure and undergo certain changes in physiological traits responding to air pollution, and then, the specific leaf traits can be the indicators of air pollution in an area. However, due to the diversity of sources, the composition of air pollutants is very complex. This makes it difficult to predict air pollution using physiological differentiation of leaves. The purpose of this investigation was to examine potential of Ligustrum lucidum Ait. leaf measurement as a method to predict the air pollutants in Luoyang, China. Leaves of roadside L. lucidum were studied from the city center with serious air pollution to relatively unpolluted areas. Leaf size, stomatal traits, and non-structural carbohydrate were measured. The particulate and gaseous pollutants (including sulfur dioxide, nitrogen dioxide, carbon monoxide, and ozone) were investigated too. The results showed that the leaf area and soluble sugar content decreased, while the aspect ratio of leaves increased in heavily polluted areas. As pollution increased, the stomatal traits in different crown positions were changed differently. No significant correlation was found between ozone content and the measured traits of leaves. The responses found in the physiological differentiation of the leaves reflect acclimation to air pollution. The soluble sugar content of the leaves could be used to indicate the short-term stress of air pollution, the area, and aspect ratio of leaves are indicative of the long-term stress due to air pollution. Therefore, physiological traits of L. lucidum leaves appeared to be significant predictive factors for the air pollutants in urban areas.

Air pollution concentration forecasting based on wavelet transform and combined weighting forecasting model

The continuous deterioration of air quality, the frequent occurrence and its following adverse effects of air pollution incidents have caused continuous public concerns. Therefore, achieving accurate prediction of air pollutants has significant role for governance efforts. In this paper, a combined weight forecasting model (CWFM) for NO2 concentration in Beijing is constructed based on three single prediction models. Firstly, the input data are decomposed by discrete wavelet transform to increase the dimensionality of the data. Secondly, DWT-LSTM, DWT-GRU and DWT-Bi-LSTM models are constructed using the wavelet decomposition results and Long short-term memory neural network (LSTM), Gated recurrent units (GRU) and Bi-directional long-short term memory neural network (Bi-LSTM), respectively, followed by comparison and contrast of the prediction results. Finally, the three single prediction models are incorporated into the combined weighted forecasting model by weight assignment. The results show that the combined weight forecasting model constructed in this paper can improve the prediction accuracy by combining the advantages of the every single prediction models, and by contrasting with any single prediction model, the combined model structure is more suitable for the prediction of NO2 concentration in Beijing.

Performance evaluation of photographic measurement in the machine-learning prediction of ground PM2.5 concentration

The scarcity and sparsity of meteorological vertical observations have caused severe restrictions in the accurate forward prediction and backward analysis of weather and air pollution. In this study, we used a common camera to automatically photograph the daytime and nighttime lights at an urban site in Beijing during 2019–2020, to support or act as a possible alternative to radiosonde measurement. The photo features characterize the scattering effect of atmospheric particulate matter on visible sunlight or lamps and record cloud, fog, and precipitation processes. The probability distributions of the mean blue brightness (B) and the mean red brightness (R) are significantly different for both the sky-part and the ground-part pixels of the photo. The B/R ratio of the sky part (B/R_sky) is exponentially and negatively correlated with ground PM2.5 concentration. During the daytime, B/R_sky has a higher priority than the boundary layer height (BLH) in the determination of PM2.5 concentration by a decision tree model, whereas the BLH plays a key role at night, and the importance of B/R_sky is comparable to that of the BLH in the decision tree. The photo features were adopted as input variables into a simple multi-layer perceptron (MLP) model (3-layer neural network) predicting PM2.5 concentration, with a root mean square error of 1–3 μg/m3, indicating that the auto-shooting camera is a competitive alternative of meteorological measurement. Because of the low cost of installation, the broad application of auto-photography can make up for deficiencies of sounding observation, i.e., sparse temporal and spatial resolution, and can be accessed by the public in real time.

COLLABORATIVE AIR QUALITY MAPPING OF DIFFERENT METROPOLITAN CITIES OF INDIA

Abstract. Environmental pollution has become extremely serious as a result of today's technological advancements all over the world. One of the most important environmental and public health risks is air pollution. The exponential growth of population, vehicular density on highways, urbanization, and other factors are rising air pollution in cities, necessitating techniques for monitoring and forecasting air quality or determining its health consequences. Various experiments are being conducted on city air quality and its distribution through the built climate. The amount of emissions in the air varies according to the time of day as depicted it is merely high in morning time between 9 to 10 am and between 5 to 6 pm in all cities. These collected data are also characterized as peak hour, average hour, and off-peak hour. It also varies geographically and during special occasions. Since computing and showcasing of air pollution levels require terrain data, air quality data from the open sources i.e. CPCB (central pollution control board, India), and air pollution prediction models. Acculumating the data of the air pollution parameter from the open sources of cities based on typically very crowded, averagely crowded, and thinly crowded areas across the city and then mapping it on ArcGIS. The data monitoring has been done for the whole year merely main emphasizes has been done on the three seasons autumn, winter, and summer (January, May, and August). Also, in winter the value of having pollutants is high due to winter inversion and in the morning also the value is higher, and in monsoon, due to precipitation, it decreases. The dispersion model help in considering the wind speed and direction, the computed data from each source location reaching out to the monitoring sensing station from the comparatively adding to the value of pollutant. With the help of questionnaires, computed out to the result that people residing or having the workplace near to the busy crossing are more promising to have the health-related issue like chocking, respiratory diseases. Men are merely more affected by this between the age of 37 to 63 years.

Evaluation on Risk Assessment on Indoor Air Pollution: A Case Study of Delhi-NCR Region

The study is focused at delineating the major causes of air pollutants in Delhi NCR region in different aspects specifically in terms of computation of Air Quality index. The major air eight pollutants are considered for calculation of Air Quality index i.e. CO, NO., SO2, PM2.5, PM10, O3, NH3, and Pb. The prediction of air pollution is performed in two phases. The first phase computes the Air Quality Index values for all the pollutants in a day. The second phase computes threshold value of Air Quality Index as an average of previous values. The air pollution for the days in chosen month is predicted by comparing the threshold value with the average of the previous two-month values. A computer aided program is drafted and compiled on JAVA programming language of Oracle Corporation using BlueJ development environment in order to compute the Air Quality index. The program uses pollutant level values user enters and it analyses the different levels for pollutants and thereafter computes the Air Quality index level of every pollutant and tells the prominent pollutants along with its final computed value. The AQI generated can be used to analyse the level of exposures a person faces in day-to-day life and how remedies can be opted to cure the exposure towards indoor air pollution. The collected pollutants data and computed Air Quality index shows that the people in DELHI-NCR region are exposed to huge air pollution and it is relevant to the indoor air quality also.The study lessening that the air contaminations at indoor, individuals should utilise the clean energies and an improvement should be done in ovens to consume the fuel productively and vent outflows to the outside. Air cleaners that can improve the air quality productively can be helpful to cop up the scenario.

Statistical Approaches for Forecasting Primary Air Pollutants: A Review

Air pollutant forecasting can be used to quantitatively estimate pollutant reduction trends. Combining bibliometrics with the evolutionary tree and Markov chain methods can achieve a superior quantitative analysis of research hotspots and trends. In this work, we adopted a bibliometric method to review the research status of statistical prediction methods for air pollution, used evolutionary trees to analyze the development trend of such research, and applied the Markov chain to predict future research trends for major air pollutants. The results indicate that papers mainly focused on the effects of air pollution on human diseases, urban pollution exposure models, and land use regression (LUR) methods. Particulate matter (PM), nitrogen oxides (NOx), and ozone (O3) were the most investigated pollutants. Artificial neural network (ANN) methods were preferred in studies of PM and O3, while LUR were more widely used in studies of NOx. Additionally, multi-method hybrid techniques gradually became the most widely used approach between 2010 and 2018. In the future, the statistical prediction of air pollution is expected to be based on a mixed method to simultaneously predict multiple pollutants, and the interaction between pollutants will be the most challenging aspect of research on air pollution prediction. The research results summarized in this paper provide technical support for the accurate prediction of atmospheric pollution and the emergency management of regional air quality.

A novel hybrid fine particulate matter (PM2.5) forecasting and its further application system: Case studies in China

AbstractAir pollution has received more attention from many countries and scientists due to its high threat to human health. However, air pollution prediction remains a challenging task because of its nonstationarity, randomness, and nonlinearity. In this research, a novel hybrid system is successfully developed for PM2.5 concentration prediction and its application in health effects and economic loss assessment. First, an efficient data mining method is adopted to capture and extract the primary characteristic of PM2.5 dataset and alleviate the noises' adverse effects. Second, Harris hawks optimization algorithm is introduced to tune the extreme learning machine model with high prediction accuracy, then the optimized extreme learning machine can be established to obtain the forecasting values of PM2.5 series. Next, PM2.5‐related health effects and economic costs was estimated based on the predicted PM2.5 values, the related health effects, and environmental value assessment methods. Several experiments are designed using three daily PM2.5 datasets from Beijing, Tianjin, and Shijiazhuang. Lastly, the corresponding experimental results showed that this proposed system can not only provide early warning information for environmental management, assist in the formulation of effective measures to reduce air pollutant emissions, and prevent health problems but also help for further research and application in different fields, such as health issues due to PM2.5 pollutant.

Multisensor and Multimodel Monitoring and Investigation of a Wintertime Air Pollution Event Ahead of a Cold Front Over Eastern China

AbstractGiven the limitations in pollutant measurements (e.g., coverage, observation errors) and air quality model uncertainties (e.g., with parameterizations and emissions), a multisensor and multimodel approach offers additional benefits compared to a single‐instrument and deterministic approach for monitoring, investigating, and predicting air pollution events. In this study, we use multisensors (including the spaceborne MODIS, OCO‐2, AIRS, and OMPS instruments as well as surface instruments) and multimodels (including WRF‐Chem and WRF‐CO2) to investigate a severe air pollution event on December 9, 2016 over eastern China. During this episode, a strong cold front moved southward. At the leading edge of the front, WRF‐CO2 simulates an enhanced XCO2 belt while WRF‐Chem simulates a belt of high PM2.5 concentration. The XCO2 and PM2.5 belts are generally colocated, due to coemission of CO2 and pollutants (or their precursors). Satellite observations including MODIS AOD, OCO‐2 XCO2, OMPS NO2, AIRS CO, and surface data confirm the simulated pollution and XCO2 belts. Later on, the front became distorted due to terrain blocking and mountain channel flows. Both observations and simulations show that the channel winds between Mountains Dabie and Huang transport the haze plume into Jiangxi province, enhancing pollution in the region. It is concluded that the multisensor (including space‐based and ground‐based instruments) and multimodel (e.g., WRF‐CO2, WRF‐Chem) approach can be used to collectively monitor and investigate air pollution events, given that emissions of the involved species have generally similar spatial distributions.

Using High-Frequency Information and RH to Estimate AQI Based on SVR.

The Environmental Protection Administration of Taiwan’s Executive Yuan has set up many air quality monitoring stations to monitor air pollution in the environment. The current weather forecast also includes information used to predict air pollution. Since air quality indicators have a considerable impact on people, the development of a simple, fast, and low-cost method to measure the AQI value is a worthy topic of research. In this study, a method was proposed to estimate AQI. Visibility had a clear positive relationship with AQI. When images and AQI were compared, it was easy to see that visibility decreased with the AQI value increase. Distance is the main factor affecting visibility, so measuring visibility with images has also become a research topic. Images with high and low PM2.5 concentrations were used to obtain regions of interest (RoI). The pixels in the RoI were calculated to obtain high-frequency information. The high-frequency information of RoI, RH, and true AQI was used for training via SVR, which was used to generate the model for AQI estimation. One year of experimental samples was collected for the experiment. Two indices were used to evaluate the performance of the proposed method. The results showed that the proposed method could be used to estimate AQI with acceptable performance in a simple, fast, and low-cost way.

Air Pollution Evaluation by Combining Stationary, Smart Mobile Pollution Monitoring and Data-Driven Modelling

Air pollution has become a major issue in large cities because increasing traffic, industrialization and it becomes more difficult to manage due to its hazardous effects on the human health and many air pollution-triggering factors. This paper puts forth a machine learning approach to evaluate the accuracy and potential of such mobile generated information for prediction of air pollution. Temperature, wind, humidity play a vital role in influencing the pollution dispersion and accumulation, majorly influencing the prediction of pollution levels. Thus, this paper includes the atmospheric condition information registered throughout the study period in order to understand the influence of these factors on air pollution monitoring. Data driven modelling is an efficient way of extracting valuable information from generated data sets, however it is less efficient when the data is incomplete or contains inaccuracies. This modelling approach has true potential for real time operations because it can detect non-linear spatial relationships between sensing units and could aggregate results for regional investigation. Neural networks comparatively showed good capability in air quality prediction than support vector regression.

Deep Learning Model for Air Quality Prediction Based on Big Data

Air pollution and its harm to human health has become a serious problem in many cities around the world. In recent years, research interests in measuring and predicting the quality of air around people has spiked. Since the Internet of things has been widely used in different domains to improve the quality for people by connecting multiple sensors. In this work an IOT based air pollution monitoring with prediction system is proposed. The internet of Things is a action interrelated computing devices that are given unique identifiers and the capability of exchange information over a system without anticipating that human to human or human to machine communication. The deep learning algorithm approach is to evaluate the accuracy for the prediction of air pollution. The main objective of the project is used to predict the air Quality. The large dataset works with LSTM for better air quality prediction. The prediction accuracy of air quality with LSTM, the evaluation indicator Root means square error is chosen to measure performance.

Predicting the ground-level pollutants concentrations and identifying the influencing factors using machine learning, wavelet transformation, and remote sensing techniques

This study was conducted to evaluate the performance of the support vector regression (SVR) model with and without applying wavelet transformation for predicting the PM10, PM2.5, SO2, NO2, CO, and O3 in Isfahan metropolis, central Iran. Ground-based data, TerraClimate, and MODIS products were used to predict air pollution parameters. These factors were first trained using the SVR and Wavelet-SVR models, and their performance was then compared using the error evaluation statistics. Uncertainties were evaluated using local errors and the clustering method. The influencing factors were lastly determined using the permutation features importance method. The results indicated that the Wavelet-SVR model resulted in improving the performance of prediction compared to the SVR model. The mean prediction interval values were also decreased after applying the wavelet transformation on the SVR model. It was found that the dominant agents affecting the temporal changes of study pollutants are soil moisture and meteorological drought. Urban development and increased energy consumption were observed in the areas with the highest air pollution. Researchers and stakeholders can use these findings to assess air pollution hazards and to improve air quality and human living conditions in metropolises.

Modeling of atmospheric particulate matters via artificial intelligence methods.

Nowadays, pollutants continue to be released into the atmosphere in increasing amounts with each passing day. Some of them may turn into more harmful forms by accumulating in different layers of the atmosphere at different times and can be transported to other regions with atmospheric events. Particulate matter (PM) is one of the most important air pollutants in the atmosphere, and it can be released into the atmosphere by natural and anthropogenic processes or can be formed in the atmosphere as a result of chemical reactions. In this study, it was aimed to predict PM10 and PM2.5 components measured in an industrial zone selected by adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), classification and regression trees (CART), random forest (RF), k-nearest neighbor (KNN), and extreme learning machine (ELM) methods. To this end, in the first stage of the study, the dataset consisting of air pollutants and meteorological data was created, the temporal and qualitative evaluation of these data was performed, and the PM (PM10 and PM2.5) components were modeled using the "R" software environment by artificial intelligence methods. The ANFIS model was more successful in predicting the PM10 (R2 = 0.95, RMSE = 5.87, MAE = 4.75) and PM2.5 (R2 = 0.97, RMSE = 3.05, MAE = 2.18) values in comparison with other methods. As a result of the study, it was clearly observed that the ANFIS model could be used in the prediction of air pollutants.

The evaluation on artificial neural networks (ANN) and multiple linear regressions (MLR) models for predicting SO2 concentration

Nowadays air quality is the main issue in urban areas that have been affecting human health, the environment, and the ecosystem. So, governmental authorities, environmental and health agencies usually need the prediction of daily air pollutants. This prediction is often based on statistical relations between various conditions and air pollution. This study aims to compare the performance of Multiple Linear Regression (MLR) and Multi-layer perceptron (MLP) for predicting SO2 concentration in the air of the Tehran. Different parameters namely meteorological parameters, urban traffic data, urban green space information, and time parameters were chosen for the prediction of SO2 daily concentration. Considering result, the correlation coefficient (R2), and root means square error (RMSE) of the MLR model are 0.708, and 6.025, respectively while these values for the MLP equal 0.9 and 0.42. According to the result of sensitivity analysis, the value of the one-day time delay, park indicator, season/year, and the total area parks were the main factors influencing SO2 concentration. MLP model suggested in this research could be applied to support, analysis, and improve predicting air pollution and air quality management. This study shows the importance of modeling and application of ANN in presenting management strategies to reduce urban pollution.