Statistical Approaches for Forecasting Primary Air Pollutants: A Review

Do machine learning methods improve prediction of ambient air pollutants with high spatial contrast? A systematic review

BACKGROUND & OBJECTIVE

The use of machine learning for air pollution modelling is rapidly increasing. We conducted a systematic review of studies comparing statistical and machine learning models predicting the spatiotemporal variation of ambient nitrogen dioxide (NO2), ultrafine particles (UFPs) and black carbon (BC) to determine whether and in which scenarios machine learning generates more accurate predictions.

METHODS

Web of Science and Scopus were searched up to June 13, 2024. All records were screened by two independent reviewers. Differences in the coefficient of determination (R2) and Root Mean Square Error (RMSE) between best statistical and machine learning methods were compared across categories of methodological elements.

RESULTS

A total of 38 studies with 46 model comparisons (30 for NO2, 8 for UFPs and 8 for BC) were included. Linear non-regularized methods and Random Forest were most frequently used. Machine learning outperformed statistical models in 34 comparisons. Mean differences (95% confidence intervals) in R2 and RMSE between best machine learning and statistical models were 0.12 (0.08, 0.17) and 20% (11%, 29%) respectively. Tree-based methods performed best in 12 of 17 multi-model comparisons. Nonlinear or regularization regression methods were used in only 12 comparisons and provided similar performance to machine learning methods.

CONCLUSION

This systematic review suggests that machine learning methods, especially tree-based methods, may be superior to linear non-regularized methods for predicting ambient concentrations of NO2, UFPs and BC. Additional comparison studies using nonlinear, regularized and a wider array of machine learning methods are needed to confirm their relative performance. Future air pollution studies would also benefit from more explicit and standardized reporting of methodologies and results.

Air quality prediction and control systems using machine learning and adaptive neuro-fuzzy inference system

Accurately predicting air quality concentrations is a challenging task due to the complex interactions of pollutants and their reliance on nonlinear processes. This study introduces an innovative approach in environmental engineering, employing artificial intelligence techniques to forecast air quality in Semnan, Iran. Comprehensive data on seven different pollutants was initially collected and analyzed. Then, several machine learning (ML) models were rigorously evaluated for their performance, and a detailed analysis was conducted. By incorporating these advanced technologies, the study aims to create a reliable framework for air quality prediction, with a particular focus on the case study in Iran. The results indicated that the adaptive neuro-fuzzy inference system (ANFIS) was the most effective method for predicting air quality across different seasons, showing high reliability across all datasets.

Frontiers and hotspots evolution between air pollution and Alzheimer's disease: A bibliometric analysis from 2013 to 2023

In recent years, the study of air pollution has received increasing attention from researchers, but a summary of Alzheimer's disease (AD) and air pollution is missed. Through combing the documents in the core dataset of Web of Science, this study analyzes current research based on specific keywords. CiteSpace and VOSviewer perform statistical analysis of measurement metrics to visualize a network of relevant content elements. The research devotes discussion to the relationship between air pollution and AD. Keyword hotspots include AD, children, oxidative stress, and system inflammation. Overall, 304 documents on air pollution and AD from 2013 to 2023 were retrieved from Web of Science. One hundred twenty-two journals published relevant articles, and the number of articles has increased gradually since the past decade. Research and development in AD and air pollution are progressing rapidly, but there is still a need for more connections with multidisciplinary technologies to explore cutting-edge hotspots.

Accurate PM2.5 urban air pollution forecasting using multivariate ensemble learning Accounting for evolving target distributions

Over the past decades, air pollution has caused severe environmental and public health problems. According to the World Health Organization (WHO), fine particulate matter (PM2.5), a key component reflecting air quality, is the fourth leading cause of death worldwide after cardiovascular disease, smoking, and diet. Various research efforts have aimed to develop PM2.5 forecasting models that can be integrated into a solution to mitigate the adverse effects of air pollution. However, PM2.5 forecasting is challenging because air pollution data are non-stationary and influenced by multiple random effects. This paper proposes an effective multivariate multi-step ensemble machine learning model for predicting continuous 24-h PM2.5 concentrations, considering meteorological conditions, the rolling mean of PM2.5 time series, and temporal features. PM2.5 is strongly correlated with space and time. Therefore, forecasting results from one location are insufficient to represent the level of air pollution for an entire city. In this study, we established six real-time air quality monitoring sites in different regions, including traffic, residential, and industrial areas in Ho Chi Minh City (HCMC), and generated forecasting results for each station. Various statistical methods are incorporated to evaluate the performance of the model. The experimental results confirm that the model performs well, substantially improving its forecasting accuracy compared to existing PM2.5 forecasting models developed for HCMC. In addition, we analyze to determine the contribution of different feature groups to model performance. The model can serve as a reference for citizens scheduling local travel and for healthcare providers to provide early warnings.

Ethnoracial Disparities in Nitrogen Dioxide Pollution in the United States: Comparing Data Sets from Satellites, Models, and Monitors

In the United States (U.S.), studies on nitrogen dioxide (NO2) trends and pollution-attributable health effects have historically used measurements from in situ monitors, which have limited geographical coverage and leave 66% of urban areas unmonitored. Novel tools, including remotely sensed NO2 measurements and estimates of NO2 estimates from land-use regression and photochemical models, can aid in assessing NO2 exposure gradients, leveraging their complete spatial coverage. Using these data sets, we find that Black, Hispanic, Asian, and multiracial populations experience NO2 levels 15-50% higher than the national average in 2019, whereas the non-Hispanic White population is consistently exposed to levels that are 5-15% lower than the national average. By contrast, the in situ monitoring network indicates more moderate ethnoracial NO2 disparities and different rankings of the least- to most-exposed ethnoracial population subgroup. Validating these spatially complete data sets against in situ observations reveals similar performance, indicating that all these data sets can be used to understand spatial variations in NO2. Integrating in situ monitoring, satellite data, statistical models, and photochemical models can provide a semiobservational record, complete geospatial coverage, and increasingly high spatial resolution, enhancing future efforts to characterize, map, and track exposure and inequality for highly spatially heterogeneous pollutants like NO2.

Spatiotemporal informer: A new approach based on spatiotemporal embedding and attention for air quality forecasting

Accurate prediction of air pollution is essential for public health protection. Air quality, however, is difficult to predict due to the complex dynamics, and its accurate forecast still remains a challenge. This study suggests a spatiotemporal Informer model, which uses a new spatiotemporal embedding and spatiotemporal attention, to improve AQI forecast accuracy. In the first phase of the proposed forecast mechanism, the input data is transformed by the spatiotemporal embedding. Next, the spatiotemporal attention is applied to extract spatiotemporal features from the embedded data. The final forecast is obtained based on the attention tensors. In the proposed forecast model, the input is a 3-dimensional data that consists of air quality data (AQI, PM2.5, O3, SO2, NO2, CO) and geographic information, and the output is a multi-positional, multi-temporal data that shows the AQI forecast result of all the monitoring stations in the study area. The proposed forecast model was evaluated by air quality data of 34 monitoring stations in Beijing, China. Experiments showed that the proposed forecast model could provide highly accurate AQI forecast: the average of MAPE values for from 1 h to 20 h ahead forecast was 11.61%, and it was much smaller than other models. Moreover, the proposed model provided a highly accurate and stable forecast even at the extreme points. These results demonstrated that the proposed spatiotemporal embedding and attention techniques could sufficiently capture the spatiotemporal correlation characteristics of air quality data, and that the proposed spatiotemporal Informer could be successfully applied for air quality forecasting.

Recent Advances in Triboelectric Nanogenerators: From Technological Progress to Commercial Applications

Serious climate changes and energy-related environmental problems are currently critical issues in the world. In order to reduce carbon emissions and save our environment, renewable energy harvesting technologies will serve as a key solution in the near future. Among them, triboelectric nanogenerators (TENGs), which is one of the most promising mechanical energy harvesters by means of contact electrification phenomenon, are explosively developing due to abundant wasting mechanical energy sources and a number of superior advantages in a wide availability and selection of materials, relatively simple device configurations, and low-cost processing. Significant experimental and theoretical efforts have been achieved toward understanding fundamental behaviors and a wide range of demonstrations since its report in 2012. As a result, considerable technological advancement has been exhibited and it advances the timeline of achievement in the proposed roadmap. Now, the technology has reached the stage of prototype development with verification of performance beyond the lab scale environment toward its commercialization. In this review, distinguished authors in the world worked together to summarize the state of the art in theory, materials, devices, systems, circuits, and applications in TENG fields. The great research achievements of researchers in this field around the world over the past decade are expected to play a major role in coming to fruition of unexpectedly accelerated technological advances over the next decade.

The application of machine learning to air pollution research: A bibliometric analysis

Machine learning (ML) is an advanced computer algorithm that simulates the human learning process to solve problems. With an explosion of monitoring data and the increasing demand for fast and accurate prediction, ML models have been rapidly developed and applied in air pollution research. In order to explore the status of ML applications in air pollution research, a bibliometric analysis was made based on 2962 articles published from 1990 to 2021. The number of publications increased sharply after 2017, comprising approximately 75% of the total. Institutions in China and United States contributed half of all publications with most research being conducted by individual groups rather than global collaborations. Cluster analysis revealed four main research topics for the application of ML: chemical characterization of pollutants, short-term forecasting, detection improvement and optimizing emission control. The rapid development of ML algorithms has increased the capability to explore the chemical characteristics of multiple pollutants, analyze chemical reactions and their driving factors, and simulate scenarios. Combined with multi-field data, ML models are a powerful tool for analyzing atmospheric chemical processes and evaluating the management of air quality and deserve greater attention in future.

The research hotspots and trends of volatile organic compound emissions from anthropogenic and natural sources: A systematic quantitative review

Volatile organic compound (VOC) emissions have attracted wide attention due to their impacts on atmospheric quality and public health. However, most studies reviewed certain aspects of natural VOCs (NVOCs) or anthropogenic VOCs (AVOCs) rather than comprehensively quantifying the hotspots and evolution trends of AVOCs and NVOCs. We combined the bibliometric method with the evolution tree and Markov chain to identify research focus and uncover the trends in VOC emission sources. This study found that research mainly focused on VOC emission characteristics, effects on air quality and health, and VOC emissions under climate change. More studies concerned on AVOCs than on NVOCs, and AVOC emissions have shifted with a decreasing proportion of transport emissions and an increasing share of solvent utilization in countries with high emissions and publications (China and the USA). Research on AVOCs is imperative to develop efficient and economical abatement techniques specific to solvent sources or BTEX species to mitigate the detrimental effects. Research on NVOCs originating from human sources risen due to their application in medicine, while studies on sources sensitive to climate change grew slowly, including plants, biomass burning, microbes, soil and oceans. Research on the long-term responses of NVOCs derived from various sources to climate warming is warranted to explore the evolution of emissions and the feedback on global climate. It is worthwhile to establish an emission inventory with all kinds of sources, accurate estimation, high spatial and temporal resolution to capture the emission trends in the synergy of industrialization and climate change as well as to simulate the effects on air quality. We review VOC emissions from both anthropogenic and natural sources under climate change and their effects on atmospheric quality and health to point out the research directions for the comprehensive control of global VOCs and mitigation of O₃ pollution.

University Academic Performance Development Prediction Based on TDA

With the rapid development of higher education, the evaluation of the academic growth potential of universities has received extensive attention from scholars and educational administrators. Although the number of papers on university academic evaluation is increasing, few scholars have conducted research on the changing trend of university academic performance. Because traditional statistical methods and deep learning techniques have proven to be incapable of handling short time series data well, this paper proposes to adopt topological data analysis (TDA) to extract specified features from short time series data and then construct the model for the prediction of trend of university academic performance. The performance of the proposed method is evaluated by experiments on a real-world university academic performance dataset. By comparing the prediction results given by the Markov chain as well as SVM on the original data and TDA statistics, respectively, we demonstrate that the data generated by TDA methods can help construct very discriminative models and have a great advantage over the traditional models. In addition, this paper gives the prediction results as a reference, which provides a new perspective for the development evaluation of the academic performance of colleges and universities.

Evaluation of data preprocessing and feature selection process for prediction of hourly PM10 concentration using long short-term memory models

Studies have confirmed that PM₁₀, defined as respirable particles with diameters of 10 μm and smaller, has adverse effects on human health and the environment. Various estimation methods are employed to determine the PM₁₀ concentration using historical data on controlling PM₁₀ air pollution, early warning, and protecting public health and the environment. The present study analyses different Long Short-Term Memory (LSTM) models that can predict hourly PM₁₀ concentration. In parallel, the study also investigates the effectiveness of the data preprocessing and feature selection (DPFS) process on the prediction accuracy of the LSTM models. For this purpose, three different LSTM models, namely Vanilla, Bi-Directional, and Stacked, were developed. Then, a comprehensive data preprocessing stage is used to eliminate missing and erroneous data and outliers from real-world raw data, and a feature selection process is applied to extract unnecessary features. The LSTM models consider three air quality parameters, including SO₂, O₃, and CO, and three meteorological factors, including relative humidity, wind direction, and wind speed. The prediction performances of the LSTM models are compared using the RMSE, MAE and R² performance index according to whether DPFS is used in the models or not. As a result, when the DPFS process was applied, the proposed LSTM models achieved high prediction performance and can be used to predict hourly PM₁₀ concentrations. Overall, the DPFS process significantly enhanced the developed LSTM models' prediction performance. Furthermore, the proposed model might be a useful tool for city administrators to make decisions and improve air quality management efforts.

National Land Use Regression Model for NO2 Using Street View Imagery and Satellite Observations

Land use regression (LUR) models are widely applied to estimate intra-urban air pollution concentrations. National-scale LURs typically employ predictors from multiple curated geodatabases at neighborhood scales. In this study, we instead developed national NO₂ models relying on innovative street-level predictors extracted from Google Street View [GSV] imagery. Using machine learning (random forest), we developed two types of models: (1) GSV-only models, which use only GSV features, and (2) GSV + OMI models, which also include satellite observations of NO₂. Our results suggest that street view imagery alone may provide sufficient information to explain NO₂ variation. Satellite observations can improve model performance, but the contribution decreases as more images are available. Random 10-fold cross-validation R² of our best models were 0.88 (GSV-only) and 0.91 (GSV + OMI)─a performance that is comparable to traditional LUR approaches. Importantly, our models show that street-level features might have the potential to better capture intra-urban variation of NO₂ pollution than traditional LUR. Collectively, our findings indicate that street view image-based modeling has great potential for building large-scale air quality models under a unified framework. Toward that goal, we describe a cost-effective image sampling strategy for future studies based on a systematic evaluation of image availability and model performance.

Time series-based PM2.5 concentration prediction in Jing-Jin-Ji area using machine learning algorithm models

Globally all countries encounter air pollution problems along their development path. As a significant indicator of air quality, PM_2.5 concentration has long been proven to be affecting the population’s death rate. Machine learning algorithms proven to outperform traditional statistical approaches are widely used in air pollution prediction. However research on the model selection discussion and environmental interpretation of model prediction results is still scarce and urgently needed to lead the policy making on air pollution control. Our research compared four types of machine learning algorisms LinearSVR, K-Nearest Neighbor, Lasso regression, Gradient boosting by looking into their performance in predicting PM_2.5 concentrations among different cities and seasons. The results show that the machine learning model is able to forecast the next day PM_2.5 concentration based on the previous five days' data with better accuracy. The comparative experiments show that based on city level the Gradient Boosting prediction model has better prediction performance with mean absolute error (MAE) of 9 ug/m³ and root mean square error (RMSE) of 10.25–16.76 ug/m³, lower compared with the other three models, and based on season level four models have the best prediction performances in winter time and the worst in summer time. And more importantly the demonstration of models' different performances in each city and each season is of great significance in environmental policy implications.

New Technologies to Decontaminate Pollutants in Water: A Report about the State of the Art

The growing increase in the world population was accompanied by a massive development of industrialization [...].

Modelling and Forecasting Temporal PM2.5 Concentration Using Ensemble Machine Learning Methods

Exposure of humans to high concentrations of PM2.5 has adverse effects on their health. Researchers estimate that exposure to particulate matter from fossil fuel emissions accounted for 18% of deaths in 2018—a challenge policymakers argue is being exacerbated by the increase in the number of extreme weather events and rapid urbanization as they tinker with strategies for reducing air pollutants. Drawing on a number of ensemble machine learning methods that have emerged as a result of advancements in data science, this study examines the effectiveness of using ensemble models for forecasting the concentrations of air pollutants, using PM2.5 as a representative case. A comprehensive evaluation of the ensemble methods was carried out by comparing their predictive performance with that of other standalone algorithms. The findings suggest that hybrid models provide useful tools for PM2.5 concentration forecasting. The developed models show that machine learning models are efficient in predicting air particulate concentrations, and can be used for air pollution forecasting. This study also provides insights into how climatic factors influence the concentrations of pollutants found in the air.

Modelling the Interaction between Air Pollutant Emissions and Their Key Sources in Poland

The main purpose of this study is to investigate the relationships between key sources of air pollutant emissions (sources of energy production, factories which are particularly harmful to the environment, the fleets of cars, environmental protection expenditure) and the main environmental air pollution (SO2, NOx, CO and PM) in Poland. Models based on MLP neural networks were used as predictive models. Global sensitivity analysis was used to demonstrate the significant impact of individual network input variables on the output variable. To verify the effectiveness of the models created, the actual data were compared with the data obtained through modelling. Projected courses of changes in the variables under study correspond with the real data, which confirms that the proposed models generalize acquired knowledge well. The high MLP network quality parameters of 0.99–0.85 indicate that the network generalizes the acquired knowledge accurately. The sensitivity analysis for NOx, CO and PM pollutants indicates the significance of all input variables. For SO2, it showed significance for four of the six variables analysed. The predictions made by the neural models are not very different from the experimental values.