Submit to Atmosphere Review for Atmosphere Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Application of Deep Learning in Ambient Air Quality Assessment

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Air Quality".

Deadline for manuscript submissions: closed (24 February 2023) | Viewed by 11312

Share This Special Issue

Special Issue Editors

Prof. Dr. Lianfa Li

E-Mail Website
Guest Editor

State Key Laboratory of Resources & Environmental Information System, Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
Interests: environmental machine learning; aerosol remote sensing; air quality assessment; spatiotemporal modeling by deep learning

Dr. Meredith Franklin

E-Mail Website1 Website2
Guest Editor

Department of Statistical Sciences, School of the Environment, University of Toronto, 700 University Ave, Toronto, ON, Canada
Interests: environmental statistics; spatial statistics; remote sensing; environmental epidemiology
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Jun Wu

E-Mail Website
Guest Editor

Program in Public Health, Susan and Henry Samueli College of Health Sciences, University of California, Irvine, CA 92697, USA
Interests: environmental exposure assessment, spatiotemporal modeling of air pollution and other environmental agents, machine learning, environmental epidemiology

Prof. Dr. Haidong Kan

E-Mail Website
Guest Editor

CMB Distinguished Professor of Environmental Health Sciences , School of Public Health, Fudan University, Shanghai 200032, China
Interests: air pollution epidemiology, climate change epidemiology, exposure assessment of air pollutants

Special Issue Information

Dear Colleagues,

For ambient air quality assessment, it is of the utmost importance to generate accurate pollution concentrations where prediction bias is minimized and models are interpretable. Both classical statistical and machine learning methods have been extensively used to estimate pollution concentrations with spatial and/or spatiotemporal covariates to improve accuracy in estimation. However, due to limitations in these methods, there is still a considerable gap between the obtained predictions and the ground truth.

In recent years, deep learning has been widely and successfully applied in the fields of computer vision, natural language processing, bioinformatics, material science, and others. However, in atmospheric sciences, limited monitoring data, monitoring data measured by instruments with varied quality and time and spatial coverage, the complexity of atmospheric processes in the formation of air pollutants, and the heterogeneity of the spatiotemporal distributions of air pollutants make it difficult for deep learning to be directly used to assess air quality, as there tend to be issues of potential inefficiency in learning, overfitting, and bias. Recent advances such as graph convolutional networks, attention mechanisms, and full residual encoder–decoders have helped to enhance learning using limited samples, reducing overfitting and bias in air quality assessment. In addition, interpretations of the models and the results are important for understanding model decision-making policies in predicting and improving modeling transparency. This is useful for tracking and reducing or eliminating errors and bias.

This Special Issue aims to promote the publication of original research and reviews that focus on applications of deep learning methods in ambient air quality assessment. These include the extraction and processing of important and/or new covariates such as meteorology, the use of remote sensing observations and other spatiotemporal data, the comparison of different methods to illustrate the effectiveness of deep learning, novel deep learning methods, as well as the interpretation of the models and results to improve model accuracy, efficiency, transparency, and interpretability.

We welcome all contributions related to applications of deep learning in ambient air quality assessment, particularly novel and effective original methods and interpretations.

Prof. Dr. Lianfa Li
Prof. Dr. Meredith Franklin
Prof. Dr. Jun Wu
Prof. Dr. Haidong Kan
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

ambient air quality assessment
accuracy
overfitting
bias
deep learning
exposure
spatiotemporal modeling
model interpretability
interpretation of results

Published Papers (5 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

21 pages, 859 KiB

Open AccessArticle

Deep Learning Based Calibration Time Reduction for MOS Gas Sensors with Transfer Learning

by Yannick Robin, Johannes Amann, Payman Goodarzi, Tizian Schneider, Andreas Schütze and Christian Bur

Atmosphere 2022, 13(10), 1614; https://doi.org/10.3390/atmos13101614 - 02 Oct 2022

Cited by 8 | Viewed by 2072

Abstract

In this study, methods from the field of deep learning are used to calibrate a metal oxide semiconductor (MOS) gas sensor in a complex environment in order to be able to predict a specific gas concentration. Specifically, we want to tackle the problem of long calibration times and the problem of transferring calibrations between sensors, which is a severe challenge for the widespread use of MOS gas sensor systems. Therefore, this contribution aims to significantly diminish those problems by applying transfer learning from the field of deep learning. Within the field of deep learning, transfer learning has become more and more popular. Nowadays, building a model (calibrating a sensor) based on pre-trained models instead of training from scratch is a standard routine. This allows the model to train with inherent information and reach a suitable solution much faster or more accurately. For predicting the gas concentration with a MOS gas sensor operated dynamically using temperature cycling, the calibration time can be significantly reduced for all nine target gases at the ppb level (seven volatile organic compounds plus carbon monoxide and hydrogen). It was possible to reduce the calibration time by up to 93% and still obtain root-mean-squared error (RMSE) values only double the best achieved RMSEs. In order to obtain the best possible transferability, different transfer methods and the influence of different transfer data sets for training were investigated. Finally, transfer learning based on neural networks is compared to a global calibration model based on feature extraction, selection, and regression to place the results in the context of already existing work. Full article

(This article belongs to the Special Issue Application of Deep Learning in Ambient Air Quality Assessment)

► Show Figures

Figure 1

17 pages, 9403 KiB

Open AccessArticle

Evaluation and Comparison of Different Machine Learning Models for NSAT Retrieval from Various Multispectral Satellite Images

by Ziting Wang and Meng Zhang

Atmosphere 2022, 13(9), 1429; https://doi.org/10.3390/atmos13091429 - 03 Sep 2022

Cited by 1 | Viewed by 1290

Abstract

As a key parameter of land surface energy balance models, near surface air temperature (NSAT) is an important indicator of the surface atmospheric environment and the urban thermal environment. At present, NSAT data are mainly captured by meteorological ground stations. In areas with a sparse distribution of meteorological stations, however, it is not possible to describe the heterogeneity of NSAT in continuous space. With the rapid development of satellite remote sensing technologies, there is now a significant method to retrieve NSAT from multispectral satellite images based on machine learning methods. In the literatures published so far, there is little reported research concerning the comprehensive evaluation and/or the systematic comparison of NSAT retrieval performances based on different machine learning models. Hence, the three most commonly-used machine learning models, Support Vector Regression (SVR), Multilayer Perceptron Neural Network (MLBPN), and Random Forest (RF), have been employed for the NSAT retrieval from various multispectral satellite images of MODIS daytime and nighttime data, Landsat 8 data, and Sentinel-2 data. Comparison of the NSAT retrieval results generated by the different machine learning models from the different types of satellite images reveals that (a) the RF-based model has a better NSAT retrieval performance than the SVR- or MLBPN-based models with respect to both the accuracy and stability, and (b) the NSAT results retrieved from the MODIS data were generally better than those from the Landsat 8 and Sentinel-2 data. To sum up, the conducted research in this article does not only provide a reference for practical applications relevant to NSAT retrievals, but also proposes an efficient RF-based model for NSAT retrieval from multispectral satellite images in continuous space. Full article

(This article belongs to the Special Issue Application of Deep Learning in Ambient Air Quality Assessment)

► Show Figures

Figure 1

23 pages, 5267 KiB

Open AccessArticle

Environmental Pollution Analysis and Impact Study—A Case Study for the Salton Sea in California

by Jerry Gao, Jia Liu, Rui Xu, Samiksha Pandey, Venkata Sai Kusuma Sindhoora Vankayala Siva and Dian Yu

Atmosphere 2022, 13(6), 914; https://doi.org/10.3390/atmos13060914 - 05 Jun 2022

Cited by 2 | Viewed by 2611

Abstract

A natural experiment conducted on the shrinking Salton Sea, a saline lake in California, showed that each one foot drop in lake elevation resulted in a 2.6% average increase in

P M_{2.5}

concentrations. The shrinking has caused the asthma rate continues to [...] Read more.

A natural experiment conducted on the shrinking Salton Sea, a saline lake in California, showed that each one foot drop in lake elevation resulted in a 2.6% average increase in

P M_{2.5}

concentrations. The shrinking has caused the asthma rate continues to increase among children, with one in five children being sent to the emergency department, which is related to asthma. In this paper, several data-driven machine learning (ML) models are developed for forecasting air quality and dust emission to study, evaluate and predict the impacts on human health due to the shrinkage of the sea, such as the Salton Sea. The paper presents an improved long short-term memory (LSTM) model to predict the hourly air quality (

O_{3}

and

CO

) based on air pollutants and weather data in the previous 5 h. According to our experiment results, the model generates a very good R2 score of 0.924 and 0.835 for

O_{3}

and

CO

, respectively. In addition, the paper proposes an ensemble model based on random forest (RF) and gradient boosting (GBoost) algorithms for forecasting hourly

P M_{2.5}

and

P M_{10}

using the air quality and weather data in the previous 5 h. Furthermore, the paper shares our research results for

P M_{2.5}

and

P M_{10}

prediction based on the proposed ensemble ML models using satellite remote sensing data. Daily

P M_{2.5}

and

P M_{10}

concentration maps in 2018 are created to display the regional air pollution density and severity. Finally, the paper reports Artificial Intelligence (AI) based research findings of measuring air pollution impact on asthma prevalence rate of local residents in the Salton Sea region. A stacked ensemble model based on support vector regression (SVR), elastic net regression (ENR), RF and GBoost is developed for asthma prediction with a good R2 score of 0.978. Full article

(This article belongs to the Special Issue Application of Deep Learning in Ambient Air Quality Assessment)

► Show Figures

Figure 1

18 pages, 4834 KiB

Open AccessArticle

Generating Fine-Scale Aerosol Data through Downscaling with an Artificial Neural Network Enhanced with Transfer Learning

by Menglin Wang, Meredith Franklin and Lianfa Li

Atmosphere 2022, 13(2), 255; https://doi.org/10.3390/atmos13020255 - 02 Feb 2022

Cited by 3 | Viewed by 2051

Abstract

Spatially and temporally resolved aerosol data are essential for conducting air quality studies and assessing the health effects associated with exposure to air pollution. As these data are often expensive to acquire and time consuming to estimate, computationally efficient methods are desirable. When coarse-scale data or imagery are available, fine-scale data can be generated through downscaling methods. We developed an Artificial Neural Network Sequential Downscaling Method (ASDM) with Transfer Learning Enhancement (ASDMTE) to translate time-series data from coarse- to fine-scale while maintaining between-scale empirical associations as well as inherent within-scale correlations. Using assimilated aerosol optical depth (AOD) from the GEOS-5 Nature Run (G5NR) (2 years, daily, 7 km resolution) and Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) (20 years, daily, 50 km resolution), coupled with elevation (1 km resolution), we demonstrate the downscaling capability of ASDM and ASDMTE and compare their performances against a deep learning downscaling method, Super Resolution Deep Residual Network (SRDRN), and a traditional statistical downscaling framework called dissever ASDM/ASDMTE utilizes empirical between-scale associations, and accounts for within-scale temporal associations in the fine-scale data. In addition, within-scale temporal associations in the coarse-scale data are integrated into the ASDMTE model through the use of transfer learning to enhance downscaling performance. These features enable ASDM/ASDMTE to be trained on short periods of data yet achieve a good downscaling performance on a longer time-series. Among all the test sets, ASDM and ASDMTE had mean maximum image-wise

R^{2}

of 0.735 and 0.758, respectively, while SRDRN, dissever GAM and dissever LM had mean maximum image-wise

R^{2}

of 0.313, 0.106 and 0.095, respectively. Full article

(This article belongs to the Special Issue Application of Deep Learning in Ambient Air Quality Assessment)

► Show Figures

Figure 1

20 pages, 12776 KiB

Open AccessArticle

Embedded Generative Air Pollution Model with Variational Autoencoder and Environmental Factor Effect in Ulaanbaatar City

by Bulgansaikhan Baldorj, Munkherdene Tsagaan, Lodoysamba Sereeter and Amanjol Bulkhbai

Atmosphere 2022, 13(1), 71; https://doi.org/10.3390/atmos13010071 - 31 Dec 2021

Cited by 1 | Viewed by 1778

Abstract

Air pollution is one of the most pressing modern-day issues in cities around the world. However, most cities have adopted air quality measurement devices that only measure the past pollution levels without paying attention to the influencing factors. To obtain preliminary pollution information with regard to environmental factors, we developed a variational autoencoder and feedforward neural network-based embedded generative model to examine the relationship between air quality and the effects of environmental factors. In the model, actual

S O_{2}

N O_{2}

P M_{2.5}

P M_{10}

, and

C O

measurements from 2016 to 2020 were used, which were assembled from 15 differently located ground monitoring stations in Ulaanbaatar city. A wide range of weather and fuel measurements were used as the data for the influencing factors, and were collected over the same period as the air pollution data were recorded. The prediction results concerned all measurement stations, and the results were visualized as a spatial–temporal distribution of pollution and the performance of individual stations. A cross-validated

R^{2}

was used to estimate the entire pollution distribution through the regions as

S O_{2}

: 0.81,

P M_{2.5}

: 0.76,

P M_{10}

: 0.89, and

C O

: 0.83. Pearson’s chi-squared tests were used for assessing each measurement station, and the contingency tables represent a high correlation between the actual and model results. The model can be applied to perform specific analysis of the interdependencies between pollution and environmental factors, and the performance of the model improves with long-range data. Full article

(This article belongs to the Special Issue Application of Deep Learning in Ambient Air Quality Assessment)

► Show Figures

Journal Menu

Journal Browser

Application of Deep Learning in Ambient Air Quality Assessment

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (5 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI