No Cover Image

Journal article 20848 views 148 downloads

Machine learning-based rapid response tools for regional air pollution modelling

D. Xiao, F. Fang, J. Zheng, C.C. Pain, I.M. Navon, Dunhui Xiao Orcid Logo

Atmospheric Environment, Volume: 199, Pages: 463 - 473

Swansea University Author: Dunhui Xiao Orcid Logo

Check full text

DOI (Published version): 10.1016/j.atmosenv.2018.11.051

Abstract

A parameterised non-intrusive reduced order model (P-NIROM) based on proper orthogonal decomposition (POD) and machine learning methods has been firstly developed for model reduction of pollutant transport equations. Our motivation is to provide rapid response urban air pollution predictions and con...

Full description

Published in: Atmospheric Environment
ISSN: 13522310
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa46447
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-12-06T20:27:44Z
last_indexed 2023-01-11T14:23:16Z
id cronfa46447
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-09-27T17:11:28.8301034</datestamp><bib-version>v2</bib-version><id>46447</id><entry>2018-12-06</entry><title>Machine learning-based rapid response tools for regional air pollution modelling</title><swanseaauthors><author><sid>62c69b98cbcdc9142622d4f398fdab97</sid><ORCID>0000-0003-2461-523X</ORCID><firstname>Dunhui</firstname><surname>Xiao</surname><name>Dunhui Xiao</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-12-06</date><deptcode>AERO</deptcode><abstract>A parameterised non-intrusive reduced order model (P-NIROM) based on proper orthogonal decomposition (POD) and machine learning methods has been firstly developed for model reduction of pollutant transport equations. Our motivation is to provide rapid response urban air pollution predictions and controls. The varying parameters in the P-NIROM are pollutant sources. The training data sets are obtained from the high fidelity modelling solutions (called snapshots) for selected parameters (pollutant sources, here) over the parameter space . From these training data sets, the machine learning method is used to generate the relationship between the reduced solutions and inputs (pollutant sources) over . Furthermore a set of hyper-surface functions associated with each POD basis function is constructed for representing the fluid dynamics over the reduced space. The accuracy of the P-NIROM is highly dependent on the quality of the training set, here obtained from the high fidelity model. Over existing machine learning methods, the P-NIROM algorithm proposed here has the advantages that (1) it is combined with NIROM, thus providing rapid and reasonably accurate solutions; and (2) it is a robust and efficient approach for representation of any parametrised partial differential equations as the model parameters/inputs vary. In this study, we demonstrate the way how to implement the P-NIROM for the pollutant transport equation (but not limited to due to its robustness). Its predictive capability is illustrated in a three-dimensional (3-D) simulation of power plant plumes over a large region in China, where the varying parameters are the emission intensity at three locations. Results indicate that in comparison to the high fidelity model, the CPU cost is reduced by factor up to five orders of magnitude while reasonable accuracy remains.</abstract><type>Journal Article</type><journal>Atmospheric Environment</journal><volume>199</volume><journalNumber/><paginationStart>463</paginationStart><paginationEnd>473</paginationEnd><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>13522310</issnPrint><issnElectronic/><keywords>Machine learning, Finite element, Proper orthogonal decomposition, Reduced order modelling, Air pollution</keywords><publishedDay>15</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-02-15</publishedDate><doi>10.1016/j.atmosenv.2018.11.051</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>AERO</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2022-09-27T17:11:28.8301034</lastEdited><Created>2018-12-06T14:51:52.1008041</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering</level></path><authors><author><firstname>D.</firstname><surname>Xiao</surname><order>1</order></author><author><firstname>F.</firstname><surname>Fang</surname><order>2</order></author><author><firstname>J.</firstname><surname>Zheng</surname><order>3</order></author><author><firstname>C.C.</firstname><surname>Pain</surname><order>4</order></author><author><firstname>I.M.</firstname><surname>Navon</surname><order>5</order></author><author><firstname>Dunhui</firstname><surname>Xiao</surname><orcid>0000-0003-2461-523X</orcid><order>6</order></author></authors><documents><document><filename>0046447-12122018163852.pdf</filename><originalFilename>xiao2018(3).pdf</originalFilename><uploaded>2018-12-12T16:38:52.1730000</uploaded><type>Output</type><contentLength>1317601</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-11-24T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2022-09-27T17:11:28.8301034 v2 46447 2018-12-06 Machine learning-based rapid response tools for regional air pollution modelling 62c69b98cbcdc9142622d4f398fdab97 0000-0003-2461-523X Dunhui Xiao Dunhui Xiao true false 2018-12-06 AERO A parameterised non-intrusive reduced order model (P-NIROM) based on proper orthogonal decomposition (POD) and machine learning methods has been firstly developed for model reduction of pollutant transport equations. Our motivation is to provide rapid response urban air pollution predictions and controls. The varying parameters in the P-NIROM are pollutant sources. The training data sets are obtained from the high fidelity modelling solutions (called snapshots) for selected parameters (pollutant sources, here) over the parameter space . From these training data sets, the machine learning method is used to generate the relationship between the reduced solutions and inputs (pollutant sources) over . Furthermore a set of hyper-surface functions associated with each POD basis function is constructed for representing the fluid dynamics over the reduced space. The accuracy of the P-NIROM is highly dependent on the quality of the training set, here obtained from the high fidelity model. Over existing machine learning methods, the P-NIROM algorithm proposed here has the advantages that (1) it is combined with NIROM, thus providing rapid and reasonably accurate solutions; and (2) it is a robust and efficient approach for representation of any parametrised partial differential equations as the model parameters/inputs vary. In this study, we demonstrate the way how to implement the P-NIROM for the pollutant transport equation (but not limited to due to its robustness). Its predictive capability is illustrated in a three-dimensional (3-D) simulation of power plant plumes over a large region in China, where the varying parameters are the emission intensity at three locations. Results indicate that in comparison to the high fidelity model, the CPU cost is reduced by factor up to five orders of magnitude while reasonable accuracy remains. Journal Article Atmospheric Environment 199 463 473 13522310 Machine learning, Finite element, Proper orthogonal decomposition, Reduced order modelling, Air pollution 15 2 2019 2019-02-15 10.1016/j.atmosenv.2018.11.051 COLLEGE NANME Aerospace Engineering COLLEGE CODE AERO Swansea University 2022-09-27T17:11:28.8301034 2018-12-06T14:51:52.1008041 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering D. Xiao 1 F. Fang 2 J. Zheng 3 C.C. Pain 4 I.M. Navon 5 Dunhui Xiao 0000-0003-2461-523X 6 0046447-12122018163852.pdf xiao2018(3).pdf 2018-12-12T16:38:52.1730000 Output 1317601 application/pdf Accepted Manuscript true 2019-11-24T00:00:00.0000000 true eng
title Machine learning-based rapid response tools for regional air pollution modelling
spellingShingle Machine learning-based rapid response tools for regional air pollution modelling
Dunhui Xiao
title_short Machine learning-based rapid response tools for regional air pollution modelling
title_full Machine learning-based rapid response tools for regional air pollution modelling
title_fullStr Machine learning-based rapid response tools for regional air pollution modelling
title_full_unstemmed Machine learning-based rapid response tools for regional air pollution modelling
title_sort Machine learning-based rapid response tools for regional air pollution modelling
author_id_str_mv 62c69b98cbcdc9142622d4f398fdab97
author_id_fullname_str_mv 62c69b98cbcdc9142622d4f398fdab97_***_Dunhui Xiao
author Dunhui Xiao
author2 D. Xiao
F. Fang
J. Zheng
C.C. Pain
I.M. Navon
Dunhui Xiao
format Journal article
container_title Atmospheric Environment
container_volume 199
container_start_page 463
publishDate 2019
institution Swansea University
issn 13522310
doi_str_mv 10.1016/j.atmosenv.2018.11.051
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Aerospace Engineering
document_store_str 1
active_str 0
description A parameterised non-intrusive reduced order model (P-NIROM) based on proper orthogonal decomposition (POD) and machine learning methods has been firstly developed for model reduction of pollutant transport equations. Our motivation is to provide rapid response urban air pollution predictions and controls. The varying parameters in the P-NIROM are pollutant sources. The training data sets are obtained from the high fidelity modelling solutions (called snapshots) for selected parameters (pollutant sources, here) over the parameter space . From these training data sets, the machine learning method is used to generate the relationship between the reduced solutions and inputs (pollutant sources) over . Furthermore a set of hyper-surface functions associated with each POD basis function is constructed for representing the fluid dynamics over the reduced space. The accuracy of the P-NIROM is highly dependent on the quality of the training set, here obtained from the high fidelity model. Over existing machine learning methods, the P-NIROM algorithm proposed here has the advantages that (1) it is combined with NIROM, thus providing rapid and reasonably accurate solutions; and (2) it is a robust and efficient approach for representation of any parametrised partial differential equations as the model parameters/inputs vary. In this study, we demonstrate the way how to implement the P-NIROM for the pollutant transport equation (but not limited to due to its robustness). Its predictive capability is illustrated in a three-dimensional (3-D) simulation of power plant plumes over a large region in China, where the varying parameters are the emission intensity at three locations. Results indicate that in comparison to the high fidelity model, the CPU cost is reduced by factor up to five orders of magnitude while reasonable accuracy remains.
published_date 2019-02-15T03:58:01Z
_version_ 1763752942378156032
score 11.016258

Similar Items