MARVAir: Meteorology Augmented Residual-based Visual Approach for Crowdsourcing Air Quality Inference

Muyan Yao; Dan Tao; Jiangtao Wang; Ruipeng Gao; Kunning Sun

doi:10.1109/tim.2022.3193197

MARVAir: Meteorology Augmented Residual-based Visual Approach for Crowdsourcing Air Quality Inference

Muyan Yao, Dan Tao, Jiangtao Wang, Ruipeng Gao, Kunning Sun

Beijing Jiaotong University

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

127 Downloads (Pure)

Abstract

Air pollution has become a prominent problem in citizens’ everyday life. Since the weather stations are not densely distributed, it is difficult to get fine-grained PM2.5 (Particulate Matter <2.5 μm) data. We propose MARVAir to address limitations of traditional PM2.5 prediction mechanism. First, we use crowdsourcing and spiderbots to fetch visual and meteorological dataset respectively. Second, a ResNet based visual core is designed to learn the image data, and an 1D-CNN based meteorology core is deployed to tune the inference. Besides, we use decision-level fusion mechanism to unite the sub-models and provide precise yet everywhere available fine-grained PM2.5 inference. In addition, cloud-side model training is also proposed to restrict local energy consumption. Evaluation on dataset collected at 8 sites over nearly 2 years suggests that, MARVAir achieves a precision of 98.8 %, a recall of 99.0 %, and an F1 score of 98.9 % under various air conditions, which notably exceed baseline solutions.

Original language	English
Article number	2514310
Pages (from-to)	1-10
Number of pages	10
Journal	IEEE Transactions on Instrumentation and Measurement
Volume	71
Early online date	21 Jul 2022
DOIs	https://doi.org/10.1109/tim.2022.3193197
Publication status	Published - 2022

Bibliographical note

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

Keywords

Air quality
Interference
Crowdsourcing
Visual
PM2.5
Ubiquitous
Model fusion
Smartphones

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/tim.2022.3193197

Post-PrintAccepted author manuscript, 3.1 MB

Cite this

@article{88040130f702462fb74f24dd42a7a245,

title = "MARVAir: Meteorology Augmented Residual-based Visual Approach for Crowdsourcing Air Quality Inference",

abstract = "Air pollution has become a prominent problem in citizens{\textquoteright} everyday life. Since the weather stations are not densely distributed, it is difficult to get fine-grained PM2.5 (Particulate Matter <2.5 μm) data. We propose MARVAir to address limitations of traditional PM2.5 prediction mechanism. First, we use crowdsourcing and spiderbots to fetch visual and meteorological dataset respectively. Second, a ResNet based visual core is designed to learn the image data, and an 1D-CNN based meteorology core is deployed to tune the inference. Besides, we use decision-level fusion mechanism to unite the sub-models and provide precise yet everywhere available fine-grained PM2.5 inference. In addition, cloud-side model training is also proposed to restrict local energy consumption. Evaluation on dataset collected at 8 sites over nearly 2 years suggests that, MARVAir achieves a precision of 98.8 %, a recall of 99.0 %, and an F1 score of 98.9 % under various air conditions, which notably exceed baseline solutions.",

keywords = "Air quality, Interference, Crowdsourcing, Visual, PM2.5, Ubiquitous, Model fusion, Smartphones",

author = "Muyan Yao and Dan Tao and Jiangtao Wang and Ruipeng Gao and Kunning Sun",

note = "{\textcopyright} 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright {\textcopyright} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author{\textquoteright}s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it. ",

year = "2022",

doi = "10.1109/tim.2022.3193197",

language = "English",

volume = "71",

pages = "1--10",

journal = "IEEE Transactions on Instrumentation and Measurement",

issn = "0018-9456",

publisher = "IEEE",

}

TY - JOUR

T1 - MARVAir: Meteorology Augmented Residual-based Visual Approach for Crowdsourcing Air Quality Inference

AU - Yao, Muyan

AU - Tao, Dan

AU - Wang, Jiangtao

AU - Gao, Ruipeng

AU - Sun, Kunning

N1 - © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

PY - 2022

Y1 - 2022

N2 - Air pollution has become a prominent problem in citizens’ everyday life. Since the weather stations are not densely distributed, it is difficult to get fine-grained PM2.5 (Particulate Matter <2.5 μm) data. We propose MARVAir to address limitations of traditional PM2.5 prediction mechanism. First, we use crowdsourcing and spiderbots to fetch visual and meteorological dataset respectively. Second, a ResNet based visual core is designed to learn the image data, and an 1D-CNN based meteorology core is deployed to tune the inference. Besides, we use decision-level fusion mechanism to unite the sub-models and provide precise yet everywhere available fine-grained PM2.5 inference. In addition, cloud-side model training is also proposed to restrict local energy consumption. Evaluation on dataset collected at 8 sites over nearly 2 years suggests that, MARVAir achieves a precision of 98.8 %, a recall of 99.0 %, and an F1 score of 98.9 % under various air conditions, which notably exceed baseline solutions.

AB - Air pollution has become a prominent problem in citizens’ everyday life. Since the weather stations are not densely distributed, it is difficult to get fine-grained PM2.5 (Particulate Matter <2.5 μm) data. We propose MARVAir to address limitations of traditional PM2.5 prediction mechanism. First, we use crowdsourcing and spiderbots to fetch visual and meteorological dataset respectively. Second, a ResNet based visual core is designed to learn the image data, and an 1D-CNN based meteorology core is deployed to tune the inference. Besides, we use decision-level fusion mechanism to unite the sub-models and provide precise yet everywhere available fine-grained PM2.5 inference. In addition, cloud-side model training is also proposed to restrict local energy consumption. Evaluation on dataset collected at 8 sites over nearly 2 years suggests that, MARVAir achieves a precision of 98.8 %, a recall of 99.0 %, and an F1 score of 98.9 % under various air conditions, which notably exceed baseline solutions.

KW - Air quality

KW - Interference

KW - Crowdsourcing

KW - Visual

KW - PM2.5

KW - Ubiquitous

KW - Model fusion

KW - Smartphones

UR - http://www.scopus.com/inward/record.url?scp=85135246719&partnerID=8YFLogxK

U2 - 10.1109/tim.2022.3193197

DO - 10.1109/tim.2022.3193197

M3 - Article

SN - 0018-9456

VL - 71

SP - 1

EP - 10

JO - IEEE Transactions on Instrumentation and Measurement

JF - IEEE Transactions on Instrumentation and Measurement

M1 - 2514310

ER -

MARVAir: Meteorology Augmented Residual-based Visual Approach for Crowdsourcing Air Quality Inference

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this