Air Pollution Forecasting Research Articles

A Novel Hybrid Machine Learning Method (OR-ELM-AR) Used in Forecast of PM2.5 Concentrations and Its Forecast Performance Evaluation

Accurate forecast of PM2.5 pollution is highly needed for the timely prevention of haze pollution in many cities suffered from frequent haze pollution. In this work, an online recurrent extreme learning machine (OR-ELM) technique with online data update was used in the forecast of PM2.5 pollution for the first time, and a hybrid model (OR-ELM-AR) by combining autoregressive (AR) model was proposed to enhance its forecast ability to capture the variations of hourly PM2.5 concentration. Evaluation of forecast performances in terms of pollution levels, forecast times, spatial distributions were conducted over the Yangtze River Delta (YRD) region, China. Results indicated that the OR-ELM-AR model could quickly respond to short-term changes and had better forecast performance. Therefore, the OR-ELM-AR model is a promising tool for air pollution forecast of supporting the government to take urgent actions to reduce the frequency and severity of haze pollution in cities or regions.

Scalable Belief Updating for Urban Air Quality Modeling and Prediction

Air pollution is one of the major concerns in global urbanization. Data science can help to understand the dynamics of air pollution and build reliable statistical models to forecast air pollution levels. To achieve these goals, one needs to learn the statistical models which can capture the dynamics from the historical data and predict air pollution in the future. Furthermore, the large size and heterogeneity of today’s big urban data pose significant challenges on the scalability and flexibility of the statistical models. In this work, we present a scalable belief updating framework that is able to produce reliable predictions, using over millions of historical hourly air pollutant and meteorology records. We also present a non-parametric approach to learn the statistical model which reveals interesting periodical dynamics and correlations of the dataset. Based on the scalable belief update framework and the non-parametric model learning approach, we propose an iterative update algorithm to accelerate Gaussian process, which is notorious for its prohibitive computation with large input data. Finally, we demonstrate how to integrate information from heterogeneous data by regarding the beliefs produced by other models as the informative prior. Numerical examples and experimental results are presented to validate the proposed method.

Методи та інформаційні системи ідентифікації джерел радіоактивних атмосферних за-бруднень шляхом оберненого моделювання

The paper reviews the methods for identifying an unknown source of pollution by inverse mod-eling and information systems for air pollution forecasting and analysis. Several different for-eign and Ukrainian air pollution forecasting systems, such as the European Union's Nuclear Emergency Response System RODOS, have been developed on the basis of atmospheric transport models. However, the key data that determine the quality of forecasting in such sys-tems are the characteristics of the emission sources. In the case of detection of pollution from an unknown emission source, there should be performed inverse simulation. The use of the RODOS system, as well as other existing forecasting systems for such a task is possible but it requires multiple manual start of calculations of atmospheric transfer models in the reverse mode. Presented in the paper results of the application of inverse modeling methods during ra-diation incidents of the last decade demonstrate that modern methods of inverse modeling are sufficiently developed to set the task of automating inverse modeling in information systems for air pollution analysis and forecasting. Even though these methods not always can exactly identify the source of emissions due to the lack of measurements and poor conditioning of the inverse atmospheric transport problem, their application always leads to a significant reduction (by an order of magnitude or more) in the search for unknown sources compared to the detec-tion of pollutants. At present, in the existing forecasting systems the methods of inverse model-ing are only partially automated, namely for the case of known location and unknown emissions of the source of pollution. Therefore, this paper proposes the architecture of the future system for identifying unknown sources of emissions by inverse modeling.

Uncertainty-Aware Deep Learning Architectures for Highly Dynamic Air Quality Prediction

Forecasting air pollution is considered as an essential key for early warning and control management of air pollution, especially in emergency situations, where big amounts of pollutants are quickly released in the air, causing considerable damages. Predicting pollution in such situations is particularly challenging due to the strong dynamic of the phenomenon and the various spatio-temporal factors affecting air pollution dispersion. In addition, providing uncertainty estimates of prediction makes the forecasting model more trustworthy, which helps decision-makers to take appropriate actions with more confidence regarding the pollution crisis. In this study, we propose a multi-point deep learning model based on convolutional long short term memory (ConvLSTM) for highly dynamic air quality forecasting. ConvLSTM architectures combines long short term memory (LSTM) and convolutional neural network (CNN), which allows to mine both temporal and spatial data features. In addition, uncertainty quantification methods were implemented on top of our model's architecture and their performances were further excavated. We conduct extensive experimental evaluations using a real and highly dynamic air pollution data set called Fusion Field Trial 2007 (FFT07). The results demonstrate the superiority of our proposed deep learning model in comparison to state-of-the-art methods including machine and deep learning techniques. Finally, we discuss the results of the uncertainty techniques and we derive insights.

Integrated Multiple Directed Attention-Based Deep Learning for Improved Air Pollution Forecasting

In recent years, human health across the world is becoming concerned by a constant threat of air pollution, which causes many chronic diseases and premature mortalities. Poor air quality does not have only serious adverse effects on human health and vegetation but also some major negative political, societal, and economic impacts. Hence, it is essential to invest more effort on accurate forecasting of ambient air pollution to provide practical and relevant solutions, achieve acceptable air quality, and plan for prevention. In this work, we propose a flexible and efficient deep learning-driven model to forecast concentrations of ambient pollutants. This article introduces first the traditional variational autoencoder (VAE) and the attention mechanism to develop the forecasting modeling strategy based on the innovative integrated multiple directed attention (IMDA) deep learning architecture. To assess the performance of the proposed forecasting methodology, experimental validation is then performed using air pollution data from four US states. Six statistical indicators have been used to evaluate the forecasting accuracy. A discussion of the results obtained finally demonstrates the satisfying performance of integrated multiple directed attention variational autoencoder (IMDA-VAE) methods to forecast different pollutants in different locations. Furthermore, results indicate that the proposed IMDA-VAE model can effectively improve air pollution forecasting performance and outperforms the deep learning models, namely VAE, long short-term memory (LSTM), gated recurrent units (GRU), bidirectional LSTM, bidirectional GRU, and ConvLSTM. We also showed that the forecasting results of the proposed model surpass the performance of LSTM and GRU with the attention mechanism.

Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks

Air pollution is becoming a rising and serious environmental problem, especially in urban areas affected by an increasing migration rate. The large availability of sensor data enables the adoption of analytical tools to provide decision support capabilities. Employing sensors facilitates air pollution monitoring, but the lack of predictive capability limits such systems’ potential in practical scenarios. On the other hand, forecasting methods offer the opportunity to predict the future pollution in specific areas, potentially suggesting useful preventive measures. To date, many works tackled the problem of air pollution forecasting, most of which are based on sequence models. These models are trained with raw pollution data and are subsequently utilized to make predictions. This paper proposes a novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas. These images are further enhanced with weather data to boost the classification accuracy. The proposed approach exploits generative adversarial networks combined with data augmentation techniques to mitigate the class imbalance problem. The experiments show that the proposed method achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data. This is a remarkable result considering that the historic air pollution data is directly related to the output—future air pollution data, whereas the proposed architecture uses camera images to recognize the air pollution—which is an inherently much more difficult problem.

The Temporal Evolution of PM2.5 Pollution Events in Taiwan: Clustering and the Association with Synoptic Weather

This study conducted a cluster analysis on the fine particulate matter (PM2.5) data over Taiwan from 2006 to 2015 and diagnosed their association with the synoptic weather patterns. Five clusters are identified via a hierarchical clustering algorithm; three of them correspond to severe events, each with a distinct pattern of temporal evolution within the 240-h window. The occurrence of the different clusters exhibits strong seasonal variation. Two of the polluted clusters are more frequently associated with weak synoptic weather, while the other one is related to northeasterly winds and fronts. Detailed case studies show that the weather patterns’ temporal evolutions clearly modulate the transition among various pollution clusters by influencing the changes in local circulation and atmospheric stability. In winter, the clusters characterizing severe PM2.5 pollution events occur when Taiwan is influenced by persistent weak synoptic condition, while in autumn, the long-range transport by strong northerly winds leads to the occurrence of severe PM2.5 pollution. The current results shed light on the potential of combining the data-driven approach and the numerical weather forecasting model to provide extended range forecasts of local air pollution forecasts.

Real-time information on air pollution and avoidance behavior: evidence from South Korea.

This study provides new empirical evidence on the relationship between information about air pollution and avoidance behavior. Many countries provide real-time information to describe the current level of air pollution exposure. However, little research has been done on people’s reactions to that real-time information. Using data on attendance at professional baseball games in South Korea, this study investigates whether real-time information on particulate matter affects individuals’ decisions to participate in outdoor activities. Regression models that include various fixed effects are used for the analysis, with the results showing that real-time alerts reduce the number of baseball game spectators by 7%, and that the size of the effect is not statistically different from that of air pollution forecasts. The study demonstrates that providing real-time information can be a way to protect the public’s health from the threat of air pollution. Moreover, the findings suggest that having easy access to the relevant information and an awareness of the risks involved are necessary for a real-time information policy to succeed.

Evaluating the potential health benefits associated with the air quality alerts system in Paris: a difference-in-differences analysis.

Background: In order to fight against air pollution and attenuate adverse health effects, many big cities in different countries adopt public policies based on a system of air quality alerts, triggered when air pollution forecasts predict a day with one or more pollutants concentrations beyond the regulatory standars. These programs focus exclusively on reducing emissions on days when air pollution warnings exceed the threshold level and, despite the large investment on this kind of measures, their effectiveness and their benefits on the population health have never been verified. The potential health benefits associated with air quality alert policies implemented in the city of Paris is assessed herein. Methods: Data of daily mortality for non-accidental, cardiovascular and respiratory causes were obtained from the French National Institute of Health and Medical Research for the period going from 2000 to 2015. Data of mean daily PM10 concentrations were collected from the local air quality monitoring networks. A quasi-experimental design was used by combining a propensity-score-matching method with Difference-in-Differences models. The difference in mean daily PM10 concentrations and in daily mortality was compared between eligible and non-eligible days before and after the definition of regulatory standards for PM10 concentrations (2000-2007 versus 2008-2015) and before and after the implementation of lower thresholds values (2008-2011 versus 2012-2015). Results: A significant reduction associated to the implementation of the air quality alerts system in Paris was detected in PM10 concentrations but no evidence was found for an impact on mortality. Conclusions: By capitalizing on natural experiments, this study addresses the question of the pertinence of local public health policies with regard to air quality and health issues and its findings suggest that investing on long-term interventions could be preferable to emergency measures concentrate exclusively on acute-air polluted days.

Improvement of chemical initialization in the air quality forecast system in North Macedonia, based on WRF-Chem model

Urban air quality is determined by a complex interaction of factors associated with anthropogenic emissions, atmospheric circulation, and geographic factors. Most of the urban-present pollution aerosols and trace gases are toxic to human health and responsible for damage of flora, fauna, and materials. The air quality prediction system based on state-of-the-art Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) has been configured and designed for North Macedonia. An extensive set of experiments have been performed with different model settings to forecast simultaneously the weather and air quality over the country. The initial results and the finding from other similar studies suggest that chemical initialization plays a significant role in a more accurate, both qualitative and quantitative forecast and assessment of urban air pollution. The main objective of the present research is to develop and test for a novel chemical initialization input in the air quality forecast system in North Macedonia. It is performed using ensemble technique in respect to treatment of the mobile emissions data using scaling factors. The WRF-Chem prediction has shown a high sensitivity to different scaling methods. While scaling of the overall mobile annual emissions tends to produce some discrepancies regarding the PM10 concentration level (overestimation during summer and underestimation during winter), an improved approach that utilizes scaling, in a wider range, only the mobile emissions originated from household heating offers the possibility of more detailed parameter fitting. The verification results indicate that the best accuracy across all scores for the winter months was achieved when scaling up the baseline pollutant input using a higher factor, while in the other seasons, the best results were achieved when scaling down the baseline pollutant emissions by a significant factor. Taking all into account, we can conclude that the seasonal variation in the pollutant input to the atmosphere is a significant factor in simulating the pollution in this region. Therefore, these seasonal variations must be taken into account when fitting the pollutant emission input to any model.

A Methodology to Increase the Accuracy of Particulate Matter Predictors Based on Time Decomposition

Particulate matter (PM) is one of the most harmful air pollutants to human health studied worldwide. In this scenario, it is of paramount importance to monitor and predict PM concentration. Artificial neural networks (ANN) are commonly used to forecast air pollution levels due to their accuracy. The use of partition on prediction problems is well known because decomposition of time series allows the latent components of the original series to be revealed. It is a matter of extracting the “deterministic” component, which is easy to predict the random components. However, there is no evidence of its use in air pollution forecasting. In this work, we introduce a different approach consisting of the decomposition of the time series in contiguous monthly partitions, aiming to develop specialized predictors to solve the problem because air pollutant concentration has seasonal behavior. The goal is to reach prediction accuracy higher than those obtained by using the entire series. Experiments were performed for seven time series of daily particulate matter concentrations (PM2.5 and PM10–particles with diameter less than 2.5 and 10 micrometers, respectively) in Finland and Brazil, using four ANNs: multilayer perceptron, radial basis function, extreme learning machines, and echo state networks. The experimental results using three evaluation measures showed that the proposed methodology increased all models’ prediction capability, leading to higher accuracy compared to the traditional approach, even for extremely high air pollution events. Our study has an important contribution to air quality prediction studies. It can help governments take measures aiming air pollution reduction and preparing hospitals during extreme air pollution events, which is related to the following United Nations sustainable developments goals: SDG 3—good health and well-being and SDG 11—sustainable cities and communities.

Nonlinear and lagged meteorological effects on daily levels of ambient PM2.5 and O3: Evidence from 284 Chinese cities

Numerous studies have linked the dispersion and deposition of atmospheric pollutants to meteorology. However, the lag structure of the effects lacks investigation. A two-stage analysis was used to assess the effects of meteorological factors on daily levels of particulate matter with an atmospheric diameter of less than 2.5 μg (PM2.5) and ozone (O3) in 284 major Chinese cities during 2015–2018. A quantile regression model combined with a distributed lag nonlinear model was first used to estimate the city-specific nonlinear and delayed effects of meteorology on air pollutants. Then, a multivariate meta-analysis was utilized to pool the city-specific effect estimates across China. In general, the meteorological effects were nonlinear. The wind speed, temperature, and rainfall were observed to be the primary meteorological factors influencing PM2.5 concentration, while temperature, relative humidity, and sunshine duration played crucial roles in influencing O3 concentration. Additionally, diverse meteorological lag pattern effects were also noted. For PM2.5, the effects of rainfall and wind were delayed and lasted for 2–4 d, while the effects of relative humidity, temperature, and sunshine duration peaked in real time and then quickly became negative or vanished after 1 d. For O3, the effects of relative humidity and sunshine duration were limited to 5 d, and rainfall and temperature only exerted significant impacts on the current day. This large-scale study thoroughly investigated the delayed and nonlinear association between meteorology and air pollution, and it presented important implications for the development of air pollution forecasts and control strategies from the meteorological perspective.

Using the MLR and Neuro-Fuzzy Methods to Forecast Air Pollution Datasets

The forecasting of time series data is essential by following statistical and intelligent techniques. Particular matter (PM10) is a time series dataset used to scale the air pollution as a dependent variable while there are many types of pollutants used as independent variables. MLR model has been used as a traditional linear approach to forecasting PM10 data. Combining NF as a nonlinear intelligent method with MLR in a hybrid MLR-NF method has been proposed for improving PM10 forecasts and handling the nonlinearity of datasets. The forecasting results reflected that the hybrid method outperformed the traditional method. Although a multiple linear regression (MLR) model has been used for air quality forecasting depending on several meteorological variables in many recent studies, the MLR model is unable to identify the nonlinear pattern of these types of data. Malaysian datasets of PM10 and several climate pollutants will be studied in this paper. The objective of this study is to forecast PM10 and obtain the best results and minimum forecasting error. In this paper, the dependent variable will be forecasted by using traditional and intelligent methods. MLR has been used as a traditional method to forecast PM10. Neuro-fuzzy (NF) in the adapted copy, which calls the adaptive neuro-fuzzy inference system (ANFIS) is combined with MLR and used as an intelligent method to forecast PM10. The results reflect that MLR-NF outperformed MLR for forecasting PM10 data. In conclusion, MLR-NF can be used to forecast PM10 for more accurate results compared to traditional methods.

PREDICT URBAN AIR POLLUTION IN SURABAYA USING RECURRENT NEURAL NETWORK – LONG SHORT TERM MEMORY

Air is one of the primary needs of living things. If the condition of air is polluted, then the lives of humans and other living things will be disrupted. So it is needed to perform special handling to maintain air quality. One way to facilitate the prevention of air pollution is to make air pollution forecasting by utilizing past data. Through the Environmental Office, the Surabaya City Government has monitored air quality in Surabaya every 30 minutes for various air quality parameters including CO, NO, NO2, NOx, PM10, SO2 and meteorological data such as wind direction, wind direction, wind speed, wind speed, global radiation, humidity, and air temperature. These data are very useful to build a prediction model for the forecast of air pollution in the future. With the large amount and variance of data generated from monitoring air quality in Surabaya city, a qualified algorithm is needed to process it. One algorithm that can be used is Recurrent Neural Network - Long Short Term Memory (RNN-LSTM). RNN-LSTM is built for sequential data processing such as time-series data. In this study, several analyses are performed. There are trend analysis, correlation analysis of pollutant values to meteorological data, and predictions of carbon monoxide pollutants using the Recurrent Neural Network - LSTM in the city of Surabaya correlated with meteorological data. The results of this study indicate that the best prediction model using RNN-LSTM with RMSE calculation gets an error of 1,880 with the number of hidden layer 2 and epoch 50 scenarios. The predicted results built can be used as a reference in determining the policy of the city government to deal with air pollution going forward.

An ensemble learning based hybrid model and framework for air pollution forecasting.

As advance of economy and industry, the impact of air pollution has gradually gained attention. In order to predict air quality, there were many studies that exploited various machine learning techniques to build predictive model for pollutant concentration or air quality prediction. However, enhancing the prediction performance always is the common problem of existing studies. Traditional templates based on machine learning and deep learning methods, such as GBTR (gradient boosted tree regression), SVR (support vector machine-based regression), and LSTM (long short-term memory), are most promising approaches to address these problems. Some previous researches showed that ensemble learning technology can improve predictive performance of other domains. In order to improve the accuracy of forecasting, in this paper, we propose a hybrid model and framework to improve the forecasting accuracy of air pollution. We not only exploit stacking-based ensemble learning scheme with Pearson correlation coefficient to calculate the correlation between different machine learning models to integrate various forecasting models together, but also construct a framework based on Spark+Hadoop machine learning and TensorFlow deep learning framework to physically integrate these models to demonstrate the next 1 to 8h' air pollution forecasting. We also conduct experiments and compare the result with GBTR, SVR, LSTM, and LSTM2 (version 2) models to demonstrate the proposed hybrid model's predictive performance. The experimental results show that the hybrid model is superior to the existing models used for predicting air pollution.

A Domain-Specific Bayesian Deep-Learning Approach for Air Pollution Forecast

Predicting air pollution concentration is crucial and beneficial for public health. This study proposes a domain-specific Bayesian deep-learning model for long-term air pollution forecast in China and the United Kingdom. Our proposed model carries three novelties: First, a domain-specific knowledge is integrated to take into account the strong statistical relationship between PM <inline-formula><tex-math notation="LaTeX">$_{2.5}$</tex-math></inline-formula> and PM <inline-formula><tex-math notation="LaTeX">$_{10}$</tex-math></inline-formula> as a regularization term; Second, an attention layer is included to capture the influential historical feature and the recursive temporal correlation of air quality data; Third, results generated from different multi-step forecast strategies are combined based on corresponding uncertainty measures to improve our model’s performance. Our model outperforms other baseline models. Results show that incorporating Bayesian and domain-specific knowledge into the deep learning model can reduce the prediction errors by a maximum of 3.7% and 12.4%, for Beijing and London, respectively. Specifically, incorporating domain-specific knowledge into the Bayesian deep-learning model reduces prediction errors whilst the integration of Bayesian techniques allows the fusion of different forecast strategies to improve prediction accuracy. In future, additional influential domain-specific features can be added to further improve our deep-learning model’s prediction accuracy and interpretability.

A Long Short-Term Memory (LSTM) Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea

Air pollution not only damages the environment but also leads to various illnesses such as respiratory tract and cardiovascular diseases. Nowadays, estimating air pollutants concentration is becoming very important so that people can prepare themselves for the hazardous impact of air pollution beforehand. Various deterministic models have been used to forecast air pollution. In this study, along with various pollutants and meteorological parameters, we also use the concentration of the pollutants predicted by the community multiscale air quality (CMAQ) model which are strongly related to PM 2.5 concentration. After combining these parameters, we implement various machine learning models to predict the hourly forecast of PM 2.5 concentration in two big cities of South Korea and compare their results. It has been shown that Long Short Term Memory network outperforms other well-known gradient tree boosting models, recurrent, and convolutional neural networks.

Markov Weighted Fuzzy Time-Series Model Based on an Optimum Partition Method for Forecasting Air Pollution

Air pollution is one of the main environmental issues faced by most countries around the world. Forecasting air pollution occurrences is an essential topic in air quality research due to the increase in awareness of its association with public health effects, and its development is vital to managing air quality. However, most previous studies have focused on enhancing accuracy, while very few have addressed uncertainty analysis, which may lead to insufficient results. The fuzzy time-series model is a better option in air pollution forecasting. Nevertheless, it has a limitation caused by utilizing a random partitioning of the universe of discourse. This study proposes a novel Markov weighted fuzzy time-series model based on the optimum partition method. Fitting the optimum partition method has been done based on five different partition methods via two stages. The proposed model is first applied for forecasting air pollution using air pollution index (API) data collected from an air monitoring station located in Klang city, Malaysia. The performance of the proposed model is evaluated based on three statistical criteria, which are the mean absolute percentage error, mean squared error and Theil’s U statistic, using the daily API data. For further validation of the model, it is also implemented for benchmark enrolment data from the University of Alabama. According to the analysis results, the proposed model greatly improved the performance of air pollution index and enrolment prediction accuracy, for which it outperformed several state-of-the-art fuzzy time-series models and classic time-series models. Thus, the proposed model could be a better option for air quality forecasting for managing air pollution.

A Novel LSTM for Multivariate Time Series with Massive Missingness.

Multivariate time series with missing data is ubiquitous when the streaming data is collected by sensors or any other recording instruments. For instance, the outdoor sensors gathering different meteorological variables may encounter low material sensitivity to specific situations, leading to incomplete information gathering. This is problematic in time series prediction with massive missingness and different missing rate of variables. Contribution addressing this problem on the regression task of meteorological datasets by employing Long Short-Term Memory (LSTM), capable of controlling the information flow with its memory unit, is still missing. In this paper, we propose a novel model called forward and backward variable-sensitive LSTM (FBVS-LSTM) consisting of two decay mechanisms and some informative data. The model inputs are mainly the missing indicator, time intervals of missingness in both forward and backward direction and missing rate of each variable. We employ this information to address the so-called missing not at random (MNAR) mechanism. Separately learning the features of each parameter, the model becomes adapted to deal with massive missingness. We conduct our experiment on three real-world datasets for the air pollution forecasting. The results demonstrate that our model performed well along with other LSTM-derivation models in terms of prediction accuracy.

Time series forecasting of ozone levels in the Metropolitan Area of Monterrey, Mexico

Based on the limitations of air quality models to forecast air pollution, statistical models are convenient and suitable tools to predict pollutant concentrations. This research work proposes a SARMA model to forecast ozone maxima concentrations in five sites of the Metropolitan Area of Monterrey, Mexico. The design of the model includes diverse novel features: meteorological variables were considered as predictors, short-term ozone concentrations (4 times in the day) were forecasted, and appropriated transformations of meteorological parameters were included. The performance measures applied to assess the SARMA model demonstrated that this statistical model is reliable to predict short-term ozone concentrations and it is consistent with the general dynamics of the ozone formation in the metropolitan area.