Using machine learning methods to identify particle types from doppler lidar measurements in iceland
Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscatter...
id |
ftunivsthongkong:oai:repository.ust.hk:1783.1-111756 |
---|---|
record_format |
openpolar |
spelling |
ftunivsthongkong:oai:repository.ust.hk:1783.1-111756 2023-05-15T16:46:40+02:00 Using machine learning methods to identify particle types from doppler lidar measurements in iceland Yang, Shu Peng, Fengchao von Löwis, Sibylle Petersen, Guðrún Nína Finger, David Christian 2021 http://repository.ust.hk/ir/Record/1783.1-111756 https://doi.org/10.3390/rs13132433 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2072-4292&rft.volume=13&rft.issue=(13)&rft.date=2021&rft.spage=&rft.aulast=Yang&rft.aufirst=&rft.atitle=Using+machine+learning+methods+to+identify+particle+types+from+doppler+lidar+measurements+in+iceland&rft.title=Remote+Sensing http://www.scopus.com/record/display.url?eid=2-s2.0-85109082360&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000670967300001 English eng http://repository.ust.hk/ir/Record/1783.1-111756 Remote Sensing, v. 13, (13), July 2021, article number 2433 2072-4292 https://doi.org/10.3390/rs13132433 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2072-4292&rft.volume=13&rft.issue=(13)&rft.date=2021&rft.spage=&rft.aulast=Yang&rft.aufirst=&rft.atitle=Using+machine+learning+methods+to+identify+particle+types+from+doppler+lidar+measurements+in+iceland&rft.title=Remote+Sensing http://www.scopus.com/record/display.url?eid=2-s2.0-85109082360&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000670967300001 Aerosols Iceland Lidar Machine learning Article 2021 ftunivsthongkong https://doi.org/10.3390/rs13132433 2021-09-10T00:02:51Z Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different clas-ses, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. Article in Journal/Newspaper Iceland The Hong Kong University of Science and Technology: HKUST Institutional Repository Remote Sensing 13 13 2433 |
institution |
Open Polar |
collection |
The Hong Kong University of Science and Technology: HKUST Institutional Repository |
op_collection_id |
ftunivsthongkong |
language |
English |
topic |
Aerosols Iceland Lidar Machine learning |
spellingShingle |
Aerosols Iceland Lidar Machine learning Yang, Shu Peng, Fengchao von Löwis, Sibylle Petersen, Guðrún Nína Finger, David Christian Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
topic_facet |
Aerosols Iceland Lidar Machine learning |
description |
Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different clas-ses, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. |
format |
Article in Journal/Newspaper |
author |
Yang, Shu Peng, Fengchao von Löwis, Sibylle Petersen, Guðrún Nína Finger, David Christian |
author_facet |
Yang, Shu Peng, Fengchao von Löwis, Sibylle Petersen, Guðrún Nína Finger, David Christian |
author_sort |
Yang, Shu |
title |
Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
title_short |
Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
title_full |
Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
title_fullStr |
Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
title_full_unstemmed |
Using machine learning methods to identify particle types from doppler lidar measurements in iceland |
title_sort |
using machine learning methods to identify particle types from doppler lidar measurements in iceland |
publishDate |
2021 |
url |
http://repository.ust.hk/ir/Record/1783.1-111756 https://doi.org/10.3390/rs13132433 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2072-4292&rft.volume=13&rft.issue=(13)&rft.date=2021&rft.spage=&rft.aulast=Yang&rft.aufirst=&rft.atitle=Using+machine+learning+methods+to+identify+particle+types+from+doppler+lidar+measurements+in+iceland&rft.title=Remote+Sensing http://www.scopus.com/record/display.url?eid=2-s2.0-85109082360&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000670967300001 |
genre |
Iceland |
genre_facet |
Iceland |
op_relation |
http://repository.ust.hk/ir/Record/1783.1-111756 Remote Sensing, v. 13, (13), July 2021, article number 2433 2072-4292 https://doi.org/10.3390/rs13132433 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2072-4292&rft.volume=13&rft.issue=(13)&rft.date=2021&rft.spage=&rft.aulast=Yang&rft.aufirst=&rft.atitle=Using+machine+learning+methods+to+identify+particle+types+from+doppler+lidar+measurements+in+iceland&rft.title=Remote+Sensing http://www.scopus.com/record/display.url?eid=2-s2.0-85109082360&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000670967300001 |
op_doi |
https://doi.org/10.3390/rs13132433 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
13 |
container_start_page |
2433 |
_version_ |
1766036775041499136 |