Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations

Estimating ground-level PM2.5 using subset regression model and machine learning algorithms in Asian megacity, Dhaka, Bangladesh

Fine particulate matter (PM2.5) has become a prominent pollutant due to rapid economic development, urbanization, industrialization, and transport activities, which has serious adverse effects on human health and the environment. Many studies have employed traditional statistical models and remote-sensing technologies to estimate PM2.5 concentrations. However, statistical models have shown inconsistency in PM2.5 concentration predictions, while machine learning algorithms have excellent predictive capacity, but little research has been done on the complementary advantages of diverse approaches. The present study proposed the best subset regression model and machine learning approaches, including random tree, additive regression, reduced error pruning tree, and random subspace, to estimate the ground-level PM2.5 concentrations over Dhaka. This study used advanced machine learning algorithms to measure the effects of meteorological factors and air pollutants (NOX, SO2, CO, and O3) on the dynamics of PM2.5 in Dhaka from 2012 to 2020. Results showed that the best subset regression model was well-performed for forecasting PM2.5 concentrations for all sites based on the integration of precipitation, relative humidity, temperature, wind speed, SO2, NOX, and O3. Precipitation, relative humidity, and temperature have negative correlations with PM2.5. The concentration levels of pollutants are much higher at the beginning and end of the year. Random subspace is the optimal model for estimating PM2.5 because it has the least statistical error metrics compared to other models. This study suggests ensemble learning models to estimate PM2.5 concentrations. This study will help quantify ground-level PM2.5 concentration exposure and recommend regional government actions to prevent and regulate PM2.5 air pollution.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11869-023-01329-w.

Water quality modelling using principal component analysis and artificial neural network

The study investigates the latent pollution sources and most significant parameters that cause spatial variation and develops the best input for water quality modelling using principal component analysis (PCA) and artificial neural network (ANN). The dataset, 22 water quality parameters were obtained from Department of Environment Malaysia (DOE). The PCA generated six significant principal component scores (PCs) which explained 65.40 % of the total variance. Parameters for water quality variation are mainlyrelated to mineral components, anthropogenic activities, and natural processes. However, in ANN three input combination models (ANN A, B, and C) were developed to identify the best model that can predict water quality index (WQI) with very high precision. ANN A model appears to have the best prediction capacity with a coefficient of determination (R²) = 0.9999 and root mean square error (RMSE) = 0.0537. These results proved that the PCA and ANN methods can be applied as tools for decision-making and problem-solving for better managing of river quality.

The development of dissolved oxygen forecast model using hybrid machine learning algorithm with hydro-meteorological variables

Dissolved oxygen (DO) forecasting is essential for aquatic managers responsible for maintaining ecosystem health and the management of water bodies affected by water quality parameters. This paper aims to forecast dissolved oxygen (DO) concentration using a multivariate adaptive regression spline (MARS) hybrid model coupled with maximum overlap discrete wavelet transformation (MODWT) as a feature decomposition approach for Surma River water using a set of water quality hydro-meteorological variables. The proposed hybrid model is compared with numerous machine learning methods, namely Bayesian ridge regression (BNR), k-nearest neighbourhood (KNN), kernel ridge regression (KRR), random forest (RF), and support vector regression (SVR). The investigational results show that the proposed model of MODWT-MARS has a better prediction than the comparing benchmark models and individual standalone counter parts. The result shows that the hybrid algorithms (i.e. MODWT-MARS) outperformed the other models (r = 0.981, WI = 0.990, RMAE = 2.47%, and MAE = 0.089). This hybrid method may serve to forecast water quality variables with fewer predictor variables.

Prediction of ground-level ozone by SOM-NARX hybrid neural network based on the correlation of predictors

Current approaches to ozone prediction using hybrid neural networks are numerous but not perfect. Decomposition algorithms ignore the correlation between predictors and ozone, and feature extraction methods rarely select appropriate predictors in terms of correlation, especially for VOCs. Therefore, this study proposes a hybrid neural network model SOM-NARX based on the correlation of predictors. The model is based on MIC to filter predictors, using SOM to make predictors as feature sequences and using NARX networks to make predictions. Data from the JCDZURI site were used for training, testing, and validation. The results show that the correlation of the predictors, classification numbers of SOM, neuron numbers, and delay steps can affect prediction accuracy. Model comparison shows that the SOM-NARX model has 13.82, 10.60, 6.58% and 12.05, 9.44, 68.14% RMSE, MAE, and MAEP in winter and summer, which is smaller than CNN-LSTM, CNN-BiLSTM, CNN-GRU, SOM-LSTM, SOM-BiLSTM, and SOM-GRU.

Identifying a suitable model for predicting hourly pollutant concentrations by using low-cost microstation data and machine learning

Accurately predicting the concentration of PM_2.5 (fine particles with a diameter of 2.5 μm or less) is essential for health risk assessment and formulation of air pollution control strategies. At present, there is also a large amount of air pollution data. How to efficiently mine its hidden features to obtain the future concentration of pollutants is very important for the prevention and control of air pollution. Therefore we build a pollutant prediction model based on Lightweight Gradient Boosting Model (LightGBM) shallow machine learning and Long Short-Term Memory (LSTM) neural network. Firstly, the PM_2.5 pollutant concentration data of 34 air quality stations in Beijing and the data of 18 weather stations were matched in time and space to obtain an input data set. Subsequently, the input data set was cleaned and preprocessed, and the training set was obtained by methods such as input feature extraction, input factor normalization, and data outlier processing. The hourly PM_2.5 concentration value prediction was achieved in accordance with experiments conducted with the hourly PM_2.5 data of Beijing from January 1, 2018 to October 1, 2020. Ultimately, the optimal hourly series prediction results were obtained after model comparisons. Through the comparison of these two models, it is found that the RMSE predicted by LSTM model for each pollutant is nearly 50% lower than that of LightGBM, and is more consistent with the fitting curve between the actual observations. The exploration of the input step size of LSTM model found that the accuracy of 3-h input data was higher than that of 12-h input data. It can be used for the management and decision-making of environmental protection departments and the formulation of preventive measures for emergency pollution incidents.

An Improved Air Quality Index Machine Learning-Based Forecasting with Multivariate Data Imputation Approach

Accurate, timely air quality index (AQI) forecasting helps industries in selecting the most suitable air pollution control measures and the public in reducing harmful exposure to pollution. This article proposes a comprehensive method to forecast AQIs. Initially, the work focused on predicting hourly ambient concentrations of PM2.5 and PM10 using artificial neural networks. Once the method was developed, the work was extended to the prediction of other criteria pollutants, i.e., O3, SO2, NO2, and CO, which fed into the process of estimating AQI. The prediction of the AQI not only requires the selection of a robust forecasting model, it also heavily relies on a sequence of pre-processing steps to select predictors and handle different issues in data, including gaps. The presented method dealt with this by imputing missing entries using missForest, a machine learning-based imputation technique which employed the random forest (RF) algorithm. Unlike the usual practice of using RF at the final forecasting stage, we utilized RF at the data pre-processing stage, i.e., missing data imputation and feature selection, and we obtained promising results. The effectiveness of this imputation method was examined against a linear imputation method for the six criteria pollutants and the AQI. The proposed approach was validated against ambient air quality observations for Al-Jahra, a major city in Kuwait. Results obtained showed that models trained using missForest-imputed data could generalize AQI forecasting and with a prediction accuracy of 92.41% when tested on new unseen data, which is better than earlier findings.

The Relationship between PM2.5 and PM10 in Central Italy: Application of Machine Learning Model to Segregate Anthropogenic from Natural Sources

Particular Matter (PM) data are the most used for the assessment of air quality, but it is also useful to monitor VOC and CO. The health impact of PM increases with decreasing aerodynamic dimensions, therefore most of the monitoring is aimed at PM10 (fraction of PM with aerodynamic dimensions smaller than 10 µm) and PM2.5 (fraction with aerodynamic dimensions lower than 2.5 µm). Generally, anthropogenic emissions contribute mainly to PM2.5 levels, whereas natural sources can largely affect PM10 concentrations. PM2.5/PM10 ratio can be used as a proxy of the origin (anthropogenic vs natural) of the PM, providing a useful indication about the main sources of PM that characterizes a specific geographical or urban setting. This paper presents the results of the analysis of continuous measurements of PM10 and PM2.5 concentrations at eight stations of the regional air quality monitoring network in Abruzzo (Central Italy), in the period 2017–2018. The application of models based on machine learning technique shows that PM2.5/PM10 ratio can be used to classify PM emissions and to know the nature of the emission source (natural and anthropogenic), under determinate conditions, and properly taking into account the meteorological parameters.

Biogas maximization using data-driven modelling with uncertainty analysis and genetic algorithm for municipal wastewater anaerobic digestion

Anaerobic digestion processes create biogases that can be useful sources of energy. The development of data-driven models of anaerobic digestion processes via operating parameters can lead to increased biogas production rates, resulting in greater energy production, through process modification and optimization. This study assessed processed and unprocessed input operating parameter variables for the development of regression models with transparent structures ('white-box' models) to: (1) estimate biogas production rates from municipal wastewater treatment plant (MWTP) anaerobic digestors; (2) compare their performances to artificial neural network (ANN) and adaptive network-based fuzzy inference system (ANFIS) models with opaque structures ('black-box' models) using Monte Carlo Simulation for uncertainty analysis; and (3) integrate the models with a genetic algorithm (GA) to optimize operating parameters for maximization of MWTP biogas production rates. The input variables were anaerobic digestion operating parameters from a MWTP including volatile fatty acids, total/fixed/volatile solids, pH, and inflow rate, which were processed via correlation tests and principal component analysis. Overall, the results indicated that the processed data did not improve regression model performances. Additionally, the developed non-linear regression model with the unprocessed inputs had the best performance based on values including R = 0.81, RMSE = 0.95, and IA = 0.89. However, this model was less accurate, but interestingly had less uncertainty, as compared to ANN and ANFIS models which indicates the compromise between model accuracy and uncertainty. Thus, all three models were coupled with GA optimization with maximum biogas production rate estimates of 22.0, 23.1, and 28.6 m³/min for ANN, ANFIS, and non-linear regression models, respectively.

A novel multi-model data-driven ensemble approach for the prediction of particulate matter concentration

Accuracy in the prediction of the particulate matter (PM_2.5 and PM₁₀) concentration in the atmosphere is essential for both its monitoring and control. In this study, a novel neuro fuzzy ensemble (NF-E) model was proposed for prediction of hourly PM_2.5 and PM₁₀ concentration. The NF-E involves careful selection of relevant input parameters for base modelling and using an adaptive neuro fuzzy inference system (ANFIS) model as a nonlinear kernel for obtaining ensemble output. The four base models used include ANFIS, artificial neural network (ANN), support vector regression (SVR) and multilinear regression (MLR). The dominant input parameters for developing the base models were selected using two nonlinear approaches (mutual information and single-input single-output ANN-based sensitivity analysis) and a conventional Pearson correlation coefficient. The NF-E model was found to predict both PM_2.5 and PM₁₀ with higher generalization ability and least error. The NF-E model outperformed all the single base models and other linear ensemble techniques with a Nash-Sutcliffe efficiency (NSE) of 0.9594 and 0.9865, mean absolute error (MAE) of 1.63 μg/m³ and 1.66 μg/m³ and BIAS of 0.0760 and 0.0340 in the testing stage for PM_2.5 and PM₁₀, respectively. The NF-E could improve the efficiency of other models by 4-22% for PM_2.5 and 3-20% for PM₁₀ depending on the model.

Airborne particulate matter in Tehran's ambient air

In recent decades, particulate matter (PM) concentrations in Tehran have exceeded the World Health Organization's (WHO) guideline on most days. In this study, a search protocol was defined by identifying the keywords, to carry out a systematic review of the concentrations and composition of PM in Tehran's ambient air. For this purpose, searches were done in Scopus, PubMed, and Web of Science in 2019. Among the founded articles (197 in Scopus, 61 in PubMed, and 153 in Web of Science). The results show that in Tehran, the annual average PM₁₀ exceeded the WHO guidelines and for more than 50.0% of the days, the PM_2.5 concentration was more than WHO 24-h guidance value. The PM concentration in Tehran has two seasonal peaks due to poorer dispersion and suspension from dry land, respectively. Tehran has two daily PM peaks due to traffic and changes in boundary-layer heights; one just after midnight and the other during morning rush hour. Indoor concentrations of PM10 and PM2.5 in Tehran were 10.6 and 21.8 times higher than the corresponding values in ambient air. Tehran represents a unique case of problems of controlling PM because of its geographical setting, emission sources, and land use. This review provided a comprehensive assessment for decision makers to assist them in making appropriate policy decisions to improve the air quality. Considering factors such as diversity of resources, temporal and spatial variations, and urban location is essential in developing control plans. Also future studies should focus more on PM reduction plans.

Application of periodic parameters and their effects on the ANN landfill gas modeling

To reach a practical landfill gas management system and to diminish the negative environmental impacts from landfills, accurate methane (CH₄) prediction is essential. In this study, the preprocessing steps including minimizing multicollinearity, removal of outliers, and errors with missing data imputation are applied to enhance the data quality. This study is the first at employing periodic parameters in the two-stage non-linear auto-regressive model with exogenous inputs (NARX) with the aim of providing a convenient and precise approach to predict the daily CH₄ collection rate from a municipal landfill in Regina, SK, Canada. Using a stepwise procedure, various volumes of training data were assessed, and concluded that employing the 3-year training data reduced the mean absolute percentage error (MAPE) of the CH₄ prediction model by 26.97% at the testing stage. The favorable artificial neural network model performance was obtained using the day of the year (DOY) as a sole input of the time series model with MAPE of 2.12% showing its acceptable ability in CH₄ prediction. Using an only DOY-based model is especially remarkable because of its simplicity and high accuracy showing a convenient and effective approach in time landfill gas modeling, particularly for the landfills with no reliable climatic data.

Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data

Remotely sensed soil moisture forecasting through satellite-based sensors to estimate the future state of the underlying soils plays a critical role in planning and managing water resources and sustainable agricultural practices. In this paper, Deep Learning (DL) hybrid models (i.e., CEEMDAN-CNN-GRU) are designed for daily time-step surface soil moisture (SSM) forecasts, employing the gated recurrent unit (GRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and convolutional neural network (CNN). To establish the objective model’s viability for SSM forecasting at multi-step daily horizons, the hybrid CEEMDAN-CNN-GRU model is tested at 1st, 5th, 7th, 14th, 21st, and 30th day ahead period by assimilating a comprehensive pool of 52 predictor dataset obtained from three distinct data sources. Data comprise satellite-derived Global Land Data Assimilation System (GLDAS) repository a global, high-temporal resolution, unique terrestrial modelling system, and ground-based variables from Scientific Information Landowners (SILO) and synoptic-scale climate indices. The results demonstrate the forecasting capability of the hybrid CEEMDAN-CNN-GRU model with respect to the counterpart comparative models. This is supported by a relatively lower value of the mean absolute percentage and root mean square error. In terms of the statistical score metrics and infographics employed to test the final model’s utility, the proposed CEEMDAN-CNN-GRU models are considerably superior compared to a standalone and other hybrid method tested on independent SSM data developed through feature selection approaches. Thus, the proposed approach can be successfully implemented in hydrology and agriculture management.

Application of artificial neural networks to predict the heavy metal contamination in the Bartin River

In this study, copper (Cu), iron (Fe), zinc (Zn), manganese (Mn), nickel (Ni), and lead (Pb) analyses were performed, and the results were modelled by artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Samples were taken from 3 stations selected on the Bartin River for 1 year between December 2012 and December 2013. Radial basis neural network (RBANN), multilayer perceptron (MLP) neural networks models, and adaptive neuro-fuzzy inference system (ANFIS) were applied to the data in order to predict the heavy metal concentrations. As a result of the study, the RMSE and MAE values of all the heavy metal models were found to have very low error values during the test phase, and it was found that the models created using MLP had R² values higher than 0.77 during the test phase; the test phase R² values of the models using RBN method were found to be ranging between 0.773 and 0.989, and the test phase R² value of the ANFIS model was higher than 0.80. If sorted from the best model to the worst by taking the MAE and RMSE values into consideration based on the test evaluation results, according to the heavy metal types, where all of the MLP, RBN, and ANFIS models were generally approximate to each other, RBN was successful for Cu, Zn, and Mn, while MLP model was successful for Ni and ANFIS model for Fe and Pb. According to the results, it can be inferred that the heavy metal contents can be estimated approximately with artificial intelligence models and relatively easy-to-measure parameters; it will be possible to detect heavy metals which are harmful to the viability of the rivers, both quickly and economically.

Chemometrics for environmental monitoring: a review

Environmental monitoring is necessary to ensure the overall health and conservation of an ecosystem. However, ecosystems (e.g. air, water, soil), are complex, involving numerous processes (both native and external), inputs, contaminants, and living organisms. As such, monitoring an environmental system is not a trivial task. The data obtained from natural systems is often multifaceted and convoluted, as a multitude of inputs can be intertwined within the matrix of the information obtained as part of a study. This means that trends and important results can be easily overlooked by conventional and single dimensional data analysis protocols. Recently, chemometric methods have emerged as a powerful method for maximizing the details contained within a chemical data set. Specifically, chemometrics refers to the use of mathematical and statistical analysis methods to evaluate chemical data, beyond univariant analysis. This type of analysis can provide a quantitative description of environmental measurements, while also having the capacity to reveal previously overlooked trends in data sets. Applying chemometrics to environmental data allows us to identify and describe the inter-relationship of environmental drivers, sources of contamination, and their potential impact upon the environment. This review aims to provide a detailed understanding of chemometric techniques, how they are currently used in environmental monitoring, and how these techniques can be used to improve current practices. An enhanced ability to monitor environmental conditions and to predict trends would be greatly beneficial to government and research agencies in their ability to develop environmental policies and analytical procedures.

Application of a multi-stage neural network approach for time-series landfill gas modeling with missing data imputation

To mitigate the greenhouse gas effect, accurate and precise landfill gas prediction models are required for more precise prediction of the amount and recovery time of methane gas from landfills. When the study associates to greenhouse gas emissions problems, time series prediction models are of considerable interests, in which significant past records of gas data are required. This study is the first to specially impute the missing methane (CH₄) data for applying in time series artificial neural network (ANN) model in an attempt to predict daily CH₄ generation rate from a landfill in Regina, SK, Canada. Pre-processing was conducted on data to evaluate independent and significant meteorological input variables and provide suitable dataset for developing CH₄ generation models. A two-stage time series model proposed in this study was performed by missing data imputation at the first stage, followed by a neural network auto-regressive model with exogenous inputs (NARX) at the second stage. The model with 3 layers, 5 climatic variables and 9 neurons in the hidden layer was the optimal structure. This model shows the high performance in CH₄ prediction with the average index of agreement of 0.92 and the average mean absolute percentage error (MAPE) of 3.03% during the testing stage. Missing data imputation coupled with NARX method decreased the mean squared error (MSE) of the model by 84% (compared to Multilayer Perceptrons neural network model) in the testing period representing the effectiveness of missing data estimation coupling with time series ANN models in daily CH₄ generation prediction.

Chemical Characterization and Seasonality of Ambient Particles (PM2.5) in the City Centre of Addis Ababa

Ambient air pollution is a growing public health concern in major African cities, including Addis Ababa (Ethiopia), where little information is available on fine particulate matter (PM2.5, with aerodynamic diameter <2.5 µm) pollution. This paper aims to characterize annual PM2.5, including bulk composition and seasonal patterns, in Addis Ababa. We collected 24-h PM2.5 samples in the central city every 6 days from November 2015 to November 2016. The mean (±SD) daily PM2.5 concentration was 53.8 (±25.0) µg/m3, with 90% of sampled days exceeding the World Health Organization's guidelines. Principal components were organic matter (OM, 44.5%), elemental carbon (EC, 25.4%), soil dust (13.5%), and SNA (sulfate, nitrate, and ammonium ions, 8.2%). Higher PM2.5 concentrations were observed during the heavy rain season, while crustal dust concentrations ranged from 2.9 to 37.6%, with higher levels during dry months. Meteorological variables, vehicle emissions, biomass fuels, unpaved roads, and construction activity contribute to poor air quality. Compared to the Air Quality Index (AQI), 31% and 36% of observed days were unhealthy for everyone and unhealthy for sensitive groups, respectively. We recommend adopting effective prevention strategies and pursuing research on vehicle emissions, biomass burning, and dust control to curb air pollution in the city.

Modelling of Urban Air Pollutant Concentrations with Artificial Neural Networks Using Novel Input Variables

Since operating urban air quality stations is not only time consuming but also costly, and because air pollutants can cause serious health problems, this paper presents the hourly prediction of ten air pollutant concentrations (CO2, NH3, NO, NO2, NOx, O3, PM1, PM2.5, PM10 and PN10) in a street canyon in Münster using an artificial neural network (ANN) approach. Special attention was paid to comparing three predictor options representing the traffic volume: we included acoustic sound measurements (sound), the total number of vehicles (traffic), and the hour of the day and the day of the week (time) as input variables and then compared their prediction powers. The models were trained, validated and tested to evaluate their performance. Results showed that the predictions of the gaseous air pollutants NO, NO2, NOx, and O3 reveal very good agreement with observations, whereas predictions for particle concentrations and NH3 were less successful, indicating that these models can be improved. All three input variable options (sound, traffic and time) proved to be suitable and showed distinct strengths for modelling various air pollutant concentrations.

Tackling environmental challenges in pollution controls using artificial intelligence: A review

This review presents the developments in artificial intelligence technologies for environmental pollution controls. A number of AI approaches, which start with the reliable mapping of nonlinear behavior between inputs and outputs in chemical and biological processes in terms of prediction models to the emerging optimization and control algorithms that study the pollutants removal processes and intelligent control systems, have been developed for environmental clean-ups. The characteristics, advantages and limitations of AI methods, including single and hybrid AI methods, were overviewed. Hybrid AI methods exhibited synergistic effects, but with computational heaviness. The up-to-date review summarizes i) Various artificial neural networks employed in wastewater degradation process for the prediction of removal efficiency of pollutants and the search of optimizing experimental conditions; ii) Evaluation of fuzzy logic used for intelligent control of aerobic stage of wastewater treatment process; iii) AI-aided soft-sensors for precisely on-line/off-line estimation of hard-to-measure parameters in wastewater treatment plants; iv) Single and hybrid AI methods applied to estimate pollutants concentrations and design monitoring and early-warning systems for both aquatic and atmospheric environments; v) AI modelings of short-term, mid-term and long-term solid waste generations, and various ANNs for solid waste recycling and reduction. Finally, the future challenges of AI-based models employed in the environmental fields are discussed and proposed.

Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China

Air pollution is one of the serious environmental problems that humankind faces and also a hot topic in Northeastern Asia. Therefore, the accurate prediction of PM2.5 (particulate matter with an aerodynamic diameter of ≤2.5 μm) is very significant in the management of human health and the decision-making of government for the environmental management. In this study, a spatiotemporal convolutional neural network (CNN) and long short-term (LSTM) memory (CNN-LSTM) model (also called PM (particulate matter) predictor) was proposed and used to predict the next day's daily average PM2.5 concentration in Beijing City. The spatiotemporal correlation analysis using the mutual information (MI) was performed, considering not only the linear correlation but also nonlinear correlation between target and observation parameters; in addition, it was fully considered for the whole area of China with the target monitoring station as the center and also for the historic air quality and meteorological data. As a result, the spatiotemporal feature vector (STFV) which reflects both linear and nonlinear correlations between parameters was effectively constructed. The PM predictor secured a fast and accurate prediction performance by efficiently extracting the inherent features of the latent air quality and meteorological input data associated with PM2.5 through CNN and by fully reflecting the long-term historic process of input time series data through LSTM. The air quality and meteorological data from the 384 monitoring stations which represents the whole area of China with Beijing City as the center during the 3 years (Jan. 1st, 2015 to Dec. 31th, 2017) were used to verify the validity of the proposed method. In conclusion, the proposed method was proved to have a better stability and prediction performance compared to multi-layer perceptron (MLP) and LSTM models.

Predicting ground-level PM2.5 concentrations in the Beijing-Tianjin-Hebei region: A hybrid remote sensing and machine learning approach

An accurate estimation of PM_2.5 (fine particulate matters with diameters ≤ 2.5 μm) concentration is critical for health risk assessment and generating air pollution control strategies. In this study, a hybrid remote sensing and machine learning approach, named RSRF model is proposed to estimate daily ground-level PM_2.5 concentrations, which integrates Random Forest (RF), one of machine learning (ML) models, and aerosol optical depth (AOD), one of remote sensing (RS) products. The proposed RSRF model provides an opportunity for an adequate characterization of real-time spatiotemporal PM_2.5 distributions at uninhabited places and complex surfaces. It also offers advantages in handling complicated non-linear relationships among a large number of meteorological, environmental and air pollutant factors, as well as ever-increasing environmental data sets. The applicability of the proposed RSRF model is tested in the Beijing-Tianjin-Hebei region (BTH region) during 2015-2017. Deep Blue (DB) AOD from Aqua-retrieved Collection 6.1 (C_61) aerosol products of Moderate Resolution Imaging Spectroradiometer (MODIS) is validated with Aerosol Robotic Network. The validation results indicate C_61 DB AOD has a high correlation with ground based AOD in the BTH region. The proposed RSRF model performed well in characterizing spatiotemporal variations of annual and seasonal PM_2.5 concentrations. It not only is useful to quantify the relationships between PM_2.5 and relevant factors such as DB AOD, meteorological and air pollutant variables, but also can provide decision support for air pollution control at a regional environment during haze periods.

Meteorological correlates and AirQ+ health risk assessment of ambient fine particulate matter in Tehran, Iran

There are few studies in the world that have been evaluated the mortality due to exposure to particulate matter smaller than 2.5 µm by AirQ+ software. Therefore, the study aimed to correlate between fine particulate matter (PM2.5) and meteorological variables and estimate all-cause annual mortality and mortality from cerebrovascular disease (stroke), ischemic heart disease (IHD), acute lower respiratory infection (ALRI), lung cancer (LC), chronic obstructive pulmonary disease (COPD) attributed to long-term exposure to ambient PM2.5 in Tehran from March 2017 to March 2018 using the WHO AirQ+ software. Data related to air quality, meteorological condition, population and the baseline incidence rates of health endpoints in Tehran were gathered from government agencies. The association between the PM2.5 concentrations and meteorological variables in the period of study were assessed by correlation analysis. The results of correlation analysis showed a weak positive correlation between PM2.5 concentrations and average monthly temperature (r = 0.42, P < 0.05) and average monthly humidity (r = 0.37, P < 0.05) in Tehran. The quantitative risk assessment related to all-cause annual mortality, the mortality of IHD, stroke, COPD, LC and ALRI were estimated 6710, 3797, 1145, 172, 135 and 27 cases, respectively. The results of regression association analysis between PM_2.5 and the number of recorded deaths was showed that with an increase of one microgram per cubic meter of PM_2.5, it is expected that about 27 cases will be added to air pollution mortality in Tehran.

Developing air exchange rate models by evaluating vehicle in-cabin air pollutant exposures in a highway and tunnel setting: case study of Tehran, Iran

The passengers inside vehicles could be exposed to high levels of air pollutants particularly while driving on highly polluted and congested traffic roadways. In order to study such exposure levels and its relation to the cabin ventilation condition, a monitoring campaign was conducted to measure the levels inside the three most common types of vehicles in Tehran, Iran (a highly air polluted megacity). In this regard, carbon monoxide (CO) and particulate matter (PM) were measured for various ventilation settings, window positions, and vehicle speeds while driving on the Resalat Highway and through the Resalat Tunnel. Results showed on average in-cabin exposure to particle number and PM₁₀ for the open windows condition was seven times greater when compared to closed windows and air conditioning on. When the vehicle was passing through the tunnel, in-cabin CO and particle number increased 100 and 30%, respectively, compared to driving on highway. Air exchange rate (AER) is a significant factor when evaluating in-cabin air pollutants level. AER was measured and simulated by a model developed through a Monte Carlo analysis of uncertainty and considering two main affecting variables, vehicle speed and fan speed. The lowest AER was 7 h^-1 for the closed window and AC on conditions, whereas the highest AER was measured 70 h^-1 for an open window condition and speed of 90 km h^-1. The results of our study can assist policy makers in controlling in-cabin pollutant exposure and in planning effective strategies for the protection of public health.

A picture tells a thousand…exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiology

BACKGROUND

Artificial intelligence (AI) is revolutionizing our world, with applications ranging from medicine to engineering.

OBJECTIVES

Here we discuss the promise, challenges, and probable data sources needed to apply AI in the fields of exposure science and environmental health. In particular, we focus on the use of deep convolutional neural networks to estimate environmental exposures using images and other complementary data sources such as cell phone mobility and social media information.

DISCUSSION

Characterizing the health impacts of multiple spatially-correlated exposures remains a challenge in environmental epidemiology. A shift toward integrated measures that simultaneously capture multiple aspects of the urban built environment could improve efficiency and provide important insights into how our collective environments influence population health. The widespread adoption of AI in exposure science is on the frontier. This will likely result in new ways of understanding environmental impacts on health and may allow for analyses to be efficiently scaled for broad coverage. Image-based convolutional neural networks may also offer a cost-effective means of estimating local environmental exposures in low and middle-income countries where monitoring and surveillance infrastructure is limited. However, suitable databases must first be assembled to train and evaluate these models and these novel approaches should be complemented with traditional exposure metrics.

CONCLUSIONS

The promise of deep learning in environmental health is great and will complement existing measurements for data-rich settings and could enhance the resolution and accuracy of estimates in data poor scenarios. Interdisciplinary partnerships will be needed to fully realize this potential.

Forecasting air quality time series using deep learning

This paper presents one of the first applications of deep learning (DL) techniques to predict air pollution time series. Air quality management relies extensively on time series data captured at air monitoring stations as the basis of identifying population exposure to airborne pollutants and determining compliance with local ambient air standards. In this paper, 8 hr averaged surface ozone (O₃) concentrations were predicted using deep learning consisting of a recurrent neural network (RNN) with long short-term memory (LSTM). Hourly air quality and meteorological data were used to train and forecast values up to 72 hours with low error rates. The LSTM was able to forecast the duration of continuous O₃ exceedances as well. Prior to training the network, the dataset was reviewed for missing data and outliers. Missing data were imputed using a novel technique that averaged gaps less than eight time steps with incremental steps based on first-order differences of neighboring time periods. Data were then used to train decision trees to evaluate input feature importance over different time prediction horizons. The number of features used to train the LSTM model was reduced from 25 features to 5 features, resulting in improved accuracy as measured by Mean Absolute Error (MAE). Parameter sensitivity analysis identified look-back nodes associated with the RNN proved to be a significant source of error if not aligned with the prediction horizon. Overall, MAE's less than 2 were calculated for predictions out to 72 hours.

IMPLICATIONS

Novel deep learning techniques were used to train an 8-hour averaged ozone forecast model. Missing data and outliers within the captured data set were replaced using a new imputation method that generated calculated values closer to the expected value based on the time and season. Decision trees were used to identify input variables with the greatest importance. The methods presented in this paper allow air managers to forecast long range air pollution concentration while only monitoring key parameters and without transforming the data set in its entirety, thus allowing real time inputs and continuous prediction.

A review on experimental design for pollutants removal in water treatment with the aid of artificial intelligence

Water pollution occurs mainly due to inorganic and organic pollutants, such as nutrients, heavy metals and persistent organic pollutants. For the modeling and optimization of pollutants removal, artificial intelligence (AI) has been used as a major tool in the experimental design that can generate the optimal operational variables, since AI has recently gained a tremendous advance. The present review describes the fundamentals, advantages and limitations of AI tools. Artificial neural networks (ANNs) are the AI tools frequently adopted to predict the pollutants removal processes because of their capabilities of self-learning and self-adapting, while genetic algorithm (GA) and particle swarm optimization (PSO) are also useful AI methodologies in efficient search for the global optima. This article summarizes the modeling and optimization of pollutants removal processes in water treatment by using multilayer perception, fuzzy neural, radial basis function and self-organizing map networks. Furthermore, the results conclude that the hybrid models of ANNs with GA and PSO can be successfully applied in water treatment with satisfactory accuracies. Finally, the limitations of current AI tools and their new developments are also highlighted for prospective applications in the environmental protection.

Permissible emission limit estimation via iterative back-calculation: Case of Assaluyeh energy zone, southern Iran

In the present research work, an environmental policy procedure for setting a cap on emissions, as a crucial step in any total emission control system, has been provided and evaluated. It is shown that general regulations on emission intensities and rates do not guarantee that ambient air quality standards are met in intense industrial zones. Local emission limits are necessary to meet ambient air quality standards in these zones. To that end, we used dispersion simulators to back-calculate pollutant concentration thresholds for a large and intense energy system in the Assaluyeh region of southern Iran. Verified modeling results indicate 218 d of pollutant concentration threshold exceedance in Assaluyeh in a simulated year. Back-calculation to assess the total permissible emission level indicates the need for 68% reduction in total emission to meet ambient air quality standards. We then used the model to help identify effective control strategies, including emission reductions and appropriate timing of specific operations. Integr Environ Assess Manag 2018;14:130-138. © 2017 SETAC.

Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters

Outdoor air pollution costs millions of premature deaths annually, mostly due to anthropogenic fine particulate matter (or PM2.5). Quito, the capital city of Ecuador, is no exception in exceeding the healthy levels of pollution. In addition to the impact of urbanization, motorization, and rapid population growth, particulate pollution is modulated by meteorological factors and geophysical characteristics, which complicate the implementation of the most advanced models of weather forecast. Thus, this paper proposes a machine learning approach based on six years of meteorological and pollution data analyses to predict the concentrations of PM2.5 from wind (speed and direction) and precipitation levels. The results of the classification model show a high reliability in the classification of low (<10 µg/m3) versus high (>25 µg/m3) and low (<10 µg/m3) versus moderate (10–25 µg/m3) concentrations of PM2.5. A regression analysis suggests a better prediction of PM2.5 when the climatic conditions are getting more extreme (strong winds or high levels of precipitation). The high correlation between estimated and real data for a time series analysis during the wet season confirms this finding. The study demonstrates that the use of statistical models based on machine learning is relevant to predict PM2.5 concentrations from meteorological data.

Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations

Biological oxygen demand (BOD) is the most significant water quality parameter and indicates water pollution with respect to the present biodegradable organic matter content. European countries are therefore obliged to report annual BOD values to Eurostat; however, BOD data at the national level is only available for 28 of 35 listed European countries for the period prior to 2008, among which 46% of data is missing. This paper describes the development of an artificial neural network model for the forecasting of annual BOD values at the national level, using widely available sustainability and economical/industrial parameters as inputs. The initial general regression neural network (GRNN) model was trained, validated and tested utilizing 20 inputs. The number of inputs was reduced to 15 using the Monte Carlo simulation technique as the input selection method. The best results were achieved with the GRNN model utilizing 25% less inputs than the initial model and a comparison with a multiple linear regression model trained and tested using the same input variables using multiple statistical performance indicators confirmed the advantage of the GRNN model. Sensitivity analysis has shown that inputs with the greatest effect on the GRNN model were (in descending order) precipitation, rural population with access to improved water sources, treatment capacity of wastewater treatment plants (urban) and treatment of municipal waste, with the last two having an equal effect. Finally, it was concluded that the developed GRNN model can be useful as a tool to support the decision-making process on sustainable development at a regional, national and international level.

The development of a combined mathematical model to forecast the incidence of hepatitis E in Shanghai, China

Background

Sporadic hepatitis E has become an important public health concern in China. Accurate forecasting of the incidence of hepatitis E is needed to better plan future medical needs. Few mathematical models can be used because hepatitis E morbidity data has both linear and nonlinear patterns. We developed a combined mathematical model using an autoregressive integrated moving average model (ARIMA) and a back propagation neural network (BPNN) to forecast the incidence of hepatitis E.

Methods

The morbidity data of hepatitis E in Shanghai from 2000 to 2012 were retrieved from the China Information System for Disease Control and Prevention. The ARIMA-BPNN combined model was trained with 144 months of morbidity data from January 2000 to December 2011, validated with 12 months of data January 2012 to December 2012, and then employed to forecast hepatitis E incidence January 2013 to December 2013 in Shanghai. Residual analysis, Root Mean Square Error (RMSE), normalized Bayesian Information Criterion (BIC), and stationary R square methods were used to compare the goodness-of-fit among ARIMA models. The Bayesian regularization back-propagation algorithm was used to train the network. The mean error rate (MER) was used to assess the validity of the combined model.

Results

A total of 7,489 hepatitis E cases was reported in Shanghai from 2000 to 2012. Goodness-of-fit (stationary R²=0.531, BIC= −4.768, Ljung-Box Q statistics=15.59, P=0.482) and parameter estimates were used to determine the best-fitting model as ARIMA (0,1,1)×(0,1,1)₁₂. Predicted morbidity values in 2012 from best-fitting ARIMA model and actual morbidity data from 2000 to 2011 were used to further construct the combined model. The MER of the ARIMA model and the ARIMA-BPNN combined model were 0.250 and 0.176, respectively. The forecasted incidence of hepatitis E in 2013 was 0.095 to 0.372 per 100,000 population. There was a seasonal variation with a peak during January-March and a nadir during August-October.

Conclusions

Time series analysis suggested a seasonal pattern of hepatitis E morbidity in Shanghai, China. An ARIMA-BPNN combined model was used to fit the linear and nonlinear patterns of time series data, and accurately forecast hepatitis E infections.