Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.6
2.5
Journals
Atmosphere
Special Issues
Machine Learning in Air Pollution
share announcement

Machine Learning in Air Pollution

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Atmospheric Techniques, Instruments, and Modeling".

Deadline for manuscript submissions: closed (15 November 2023) | Viewed by 22413

Special Issue Editors

Dr. HwaMin Lee

E-Mail Website
Guest Editor
College of Medicine, Korea University, Seoul 02841, Korea
Interests: machine learning; deep learning; air pollution; particulate matter; cloud computing; big data
Special Issues, Collections and Topics in MDPI journals
Dr. Sungroul Kim

E-Mail Website
Guest Editor
Department of Environmental Health Sciences, Soonchunhyang University, Asan 31538, Korea
Interests: air pollutants measurement; exposure assessment; environmental health

Special Issue Information

Dear Colleagues,

Air pollution has emerged as a global problem beyond those of major cities. The OECD warns that urban air pollution will account for the largest proportion of deaths in the future, rather than water scarcity or poor sanitation. In particular, the results of a WHO survey found that 7 million people worldwide die early due to fine dust, illustrating that the health of citizens is threatened by air pollution. Therefore, we need to make efforts to solve the air pollution problem together across national and urban boundaries. Machine learning is a field of artificial intelligence (AI) that automates model creation for data analysis so that software learns and finds patterns based on data. With the advent of new computing technologies, machine learning today is different from machine learning in the past. With the development of new technologies, including deep learning, various machine learning algorithms are being developed that can be applied to big data analysis faster and faster by repeating complex calculations. In the field of air pollution, artificial intelligence has the potential for expansion to a variety of research areas, such as various monitoring, analysis, and prediction tasks using machine learning. This Special Issue intends to publish papers describing methods and studies using a variety of machine learning techniques, including deep learning, in air pollution. For this Special Issue, we invite submissions that closely interlink air pollution with machine learning, and which illustrate how machine learning can help to achieve air pollution research goals.

Dr. HwaMin Lee
Dr. Sungroul Kim
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Atmosphere is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • intelligent application for air pollution
  • air pollution
  • machine learning
  • deep learning
  • artificial intelligence
  • air quality
  • particulate matter

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 2297 KiB  
Article
Using Diverse Data Sources to Impute Missing Air Quality Data Collected in a Resource-Limited Setting
by Moses Mogakolodi Kebalepile, Loveness Nyaradzo Dzikiti and Kuku Voyi
Atmosphere 2024, 15(3), 303; https://doi.org/10.3390/atmos15030303 - 28 Feb 2024
Cited by 1 | Viewed by 1465
Abstract
The sustainable operation of ambient air quality monitoring stations in developing countries is not always possible. Intermittent failures and breakdowns at air quality monitoring stations often affect the continuous measurement of data as required. These failures and breakdowns result in missing data. This [...] Read more.
The sustainable operation of ambient air quality monitoring stations in developing countries is not always possible. Intermittent failures and breakdowns at air quality monitoring stations often affect the continuous measurement of data as required. These failures and breakdowns result in missing data. This study aimed to impute NO2, SO2, O3, and PM 10 to produce complete data sets of daily average exposures from 2010 to 2017. Models were built for (a) an individual pollutant at a monitoring station, (b) a combined model for the same pollutant from different stations, and (c) a data set with all the pollutants from all the monitoring stations. This study sought to evaluate the efficacy of the Multiple Imputation by Chain Equations (MICE) algorithm in successfully imputing air quality data that are missing at random. The application of classification and regression trees (CART) analysis using the MICE package in the R statistical programming language was compared with the predictive mean matching (PMM) method. The CART method performed better, with the pooled R-squared statistics of the imputed data ranging from 0.3 to 0.7, compared to a range of 0.02 to 0.25 for PMM. The MICE algorithm successfully resolved the incompleteness of the data. It was concluded that the CART method produced better reliable data than the PMM method. However, in this study, the pooled R2 values were accurate for NO2, but not so much for other pollutants. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

24 pages, 51226 KiB  
Article
Downscaling of Regional Air Quality Model Using Gaussian Plume Model and Random Forest Regression
by Marcin Kawka, Joanna Struzewska and Jacek W. Kaminski
Atmosphere 2023, 14(7), 1171; https://doi.org/10.3390/atmos14071171 - 20 Jul 2023
Cited by 1 | Viewed by 2777
Abstract
High PM10 concentrations are still a significant problem in many parts of the world. In many countries, including Poland, 50 μg/m3 is the permissible threshold for a daily average PM10 concentration. The number of people affected by [...] Read more.
High PM10 concentrations are still a significant problem in many parts of the world. In many countries, including Poland, 50 μg/m3 is the permissible threshold for a daily average PM10 concentration. The number of people affected by this threshold’s exceedance is challenging to estimate and requires high-resolution concentration maps. This paper presents an application of random forests for downscaling regional model air quality results. As policymakers and other end users are eager to receive detailed-resolution PM10 concentration maps, we propose a technique that utilizes the results of a regional CTM (GEM-AQ, with 2.5 km resolution) and a local Gaussian plume model. As a result, we receive a detailed, 250 m resolution PM10 distribution, which represents the complex emission pattern in a foothill area in southern Poland. The random forest results are highly consistent with the GEM-AQ and observed concentrations. We also discuss different strategies of training random forest on data using additional features and selecting target variables. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

12 pages, 397 KiB  
Article
A Quantum Machine Learning Approach to Spatiotemporal Emission Modelling
by Kelly Zheng, Jesse Van Griensven and Roydon Fraser
Atmosphere 2023, 14(6), 944; https://doi.org/10.3390/atmos14060944 - 28 May 2023
Cited by 3 | Viewed by 2449
Abstract
Despite the growing impact of emissions on our health and the environment, there remains an unmet need for emission concentration prediction and forecasting. The accumulating monitoring station and satellite data make the problem well-suited for quantum machine learning. This work takes a quantum [...] Read more.
Despite the growing impact of emissions on our health and the environment, there remains an unmet need for emission concentration prediction and forecasting. The accumulating monitoring station and satellite data make the problem well-suited for quantum machine learning. This work takes a quantum machine learning approach to the spatiotemporal prediction of emission concentration. A quantum quanvolutional neural network model was developed and compared to a classical spatiotemporal ConvLSTM model using an evaluation framework of baseline models and metrics of per-pixel loss and intersection over union accuracy. The quantum quanvolutional neural network developed successfully generates one-hour-ahead emission concentration forecasts with increasingly lower loss (6.5% and 30.5% less) and higher accuracy (18.4% and 18.6% higher) compared to the input-independent and random baselines at the end of training. The quantum model was also comparable to the classical ConvLSTM model, with slightly lower loss (4%) but also slightly lower accuracy (3.7%). The study’s results suggest that the quantum machine learning approach has the potential to improve emission concentration modeling and could become a powerful tool for accurately predicting air pollution. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

25 pages, 202627 KiB  
Article
Big-Data-Driven Machine Learning for Enhancing Spatiotemporal Air Pollution Pattern Analysis
by Mateusz Zareba, Hubert Dlugosz, Tomasz Danek and Elzbieta Weglinska
Atmosphere 2023, 14(4), 760; https://doi.org/10.3390/atmos14040760 - 21 Apr 2023
Cited by 19 | Viewed by 3472
Abstract
Air pollution is an important problem for public health. The spatiotemporal analysis is a crucial step for understanding the complex characteristics of air pollution. Using many sensors and high-resolution time-step observations makes this task a big data challenge. In this study, unsupervised machine [...] Read more.
Air pollution is an important problem for public health. The spatiotemporal analysis is a crucial step for understanding the complex characteristics of air pollution. Using many sensors and high-resolution time-step observations makes this task a big data challenge. In this study, unsupervised machine learning algorithms were applied to analyze spatiotemporal patterns of air pollution. The analysis was conducted using PM10 big data collected from almost 100 sensors located in Krakow, over a period of one year, with data being recorded at 1-h intervals. The analysis results using K-means and SKATER clustering revealed distinct differences between average and maximum values of pollutant concentrations. The study found that the K-means algorithm with Dynamic Time Warping (DTW) was more accurate in identifying yearly patterns and clustering in rapidly and spatially varying data, compared to the SKATER algorithm. Moreover, the clustering analysis of data after kriging greatly facilitated the interpretation of the results. These findings highlight the potential of machine learning techniques and big data analysis for identifying hot-spots, cold-spots, and patterns of air pollution and informing policy decisions related to urban planning, traffic management, and public health interventions. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

18 pages, 2987 KiB  
Article
Short-Term Air Pollution Forecasting Using Embeddings in Neural Networks
by Enislay Ramentol, Stefanie Grimm, Moritz Stinzendörfer and Andreas Wagner
Atmosphere 2023, 14(2), 298; https://doi.org/10.3390/atmos14020298 - 2 Feb 2023
Cited by 3 | Viewed by 3028
Abstract
Air quality is a highly relevant issue for any developed economy. The high incidence of pollution levels and their impact on human health has attracted the attention of the machine-learning scientific community. We present a study using several machine-learning methods to forecast NO [...] Read more.
Air quality is a highly relevant issue for any developed economy. The high incidence of pollution levels and their impact on human health has attracted the attention of the machine-learning scientific community. We present a study using several machine-learning methods to forecast NO2 concentration using historical pollution data and meteorological variables and apply them to the city of Erfurt, Germany. We propose modelling the time dependency using embedding variables, which enable the model to learn the implicit behaviour of traffic and offers the possibility to elaborate on local events. In addition, the model uses seven meteorological features to forecast the NO2 concentration for the next hours. The forecasting model also uses the seasonality of the pollution levels. Our experimental study shows that promising forecasts can be achieved, especially for holidays and similar occasions which lead to shifts in usual seasonality patterns. While the MAE values of the compared models range from 4.3 to 15, our model achieves values of 4.4 to 7.4 and thus outperforms the others in almost every instance. Those forecasts again can for example be used to regulate sources of pollutants such as, e.g., traffic. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

14 pages, 2209 KiB  
Article
Development of a CNN+LSTM Hybrid Neural Network for Daily PM2.5 Prediction
by Hyun S. Kim, Kyung M. Han, Jinhyeok Yu, Jeeho Kim, Kiyeon Kim and Hyomin Kim
Atmosphere 2022, 13(12), 2124; https://doi.org/10.3390/atmos13122124 - 17 Dec 2022
Cited by 15 | Viewed by 4773
Abstract
A CNN+LSTM (Convolutional Neural Network + Long Short-Term Memory) based deep hybrid neural network was established for the citywide daily PM2.5 prediction in South Korea. The structural hyperparameters of the CNN+LSTM model were determined through comprehensive sensitivity tests. The input features were [...] Read more.
A CNN+LSTM (Convolutional Neural Network + Long Short-Term Memory) based deep hybrid neural network was established for the citywide daily PM2.5 prediction in South Korea. The structural hyperparameters of the CNN+LSTM model were determined through comprehensive sensitivity tests. The input features were obtained from the ground observations and GFS forecast. The performance of CNN+LSTM was evaluated by comparison with PM2.5 observations and with the 3-D CTM (three-dimensional chemistry transport model)-predicted PM2.5. The newly developed hybrid model estimated more accurate ambient levels of PM2.5 compared to the 3-D CTM. For example, the error and bias of the CNN+LSTM prediction were 1.51 and 6.46 times smaller than those by 3D-CTM simulation. In addition, based on IOA (Index of Agreement), the accuracy of CNN+LSTM prediction was 1.10–1.18 times higher than the 3-D CTM-based prediction. The importance of input features was indirectly investigated by sequential perturbing input variables. The most important meteorological and atmospheric environmental features were geopotential height and previous day PM2.5. The obstacles of the current CNN+LSTM-based PM2.5 prediction were also discussed. The promising result of this study indicates that DNN-based models can be utilized as an effective tool for air quality prediction. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

17 pages, 3361 KiB  
Article
A Novel Komodo Mlipir Algorithm and Its Application in PM2.5 Detection
by Linxuan Li and Ming Zhao
Atmosphere 2022, 13(12), 2051; https://doi.org/10.3390/atmos13122051 - 7 Dec 2022
Cited by 2 | Viewed by 2356
Abstract
The paper presents an improved Komodo Mlipir Algorithm (KMA) with variable inertia weight and chaos mapping (VWCKMA). In contrast to the original Komodo Mlipir Algorithm (KMA), the chaotic sequence initialization population generated by Tent mapping and Tent Chaos disturbance used in VWCKMA can [...] Read more.
The paper presents an improved Komodo Mlipir Algorithm (KMA) with variable inertia weight and chaos mapping (VWCKMA). In contrast to the original Komodo Mlipir Algorithm (KMA), the chaotic sequence initialization population generated by Tent mapping and Tent Chaos disturbance used in VWCKMA can effectively prevent the algorithm from falling into a local optimal solution and enhance population diversity. Individuals of different social classes can be controlled by the variable inertia weight, and the convergence speed and accuracy can be increased. For the purpose of evaluating the performance of the VWCKMA, function optimization and actual predictive optimization experiments are conducted. As a result of the simulation results, the convergence accuracy and convergence speed of the VWCKMA have been considerably enhanced for single-peak, multi-peak, and fixed-dimensional complex functions in different dimensions and even thousands of dimensions. To address the nonlinearity of PM2.5 prediction in practical problems, the weights and thresholds of the BP neural network were iteratively optimized using VWCKMA, and the BP neural network was then used to predict PM2.5 using the optimal parameters. Experimental results indicate that the accuracy of the VWCKMA-optimized BP neural network model is 85.085%, which is 19.85% higher than that of the BP neural network, indicating that the VWCKMA has a certain practical application. Full article
(This article belongs to the Special Issue Machine Learning in Air Pollution)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop