Supercooled liquid water cloud classification using lidar backscatter peak properties
The use of depolarization lidar to measure atmospheric volume depolarization ratio (VDR) is a common technique to classify cloud phase (liquid or ice). Previous work using a machine learning framework, applied to peak properties derived from co-polarised attenuated backscatter data, has been demonst...
Main Authors: | , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/egusphere-2023-1085 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-1085/ |
id |
ftcopernicus:oai:publications.copernicus.org:egusphere111675 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:egusphere111675 2023-07-30T03:58:19+02:00 Supercooled liquid water cloud classification using lidar backscatter peak properties Whitehead, Luke Edgar McDonald, Adrian James Guyot, Adrien 2023-07-10 application/pdf https://doi.org/10.5194/egusphere-2023-1085 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-1085/ eng eng doi:10.5194/egusphere-2023-1085 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-1085/ eISSN: Text 2023 ftcopernicus https://doi.org/10.5194/egusphere-2023-1085 2023-07-17T16:24:18Z The use of depolarization lidar to measure atmospheric volume depolarization ratio (VDR) is a common technique to classify cloud phase (liquid or ice). Previous work using a machine learning framework, applied to peak properties derived from co-polarised attenuated backscatter data, has been demonstrated to effectively detect supercooled liquid water containing clouds (SLCC). However, the training data from Davis Station, Antarctica, includes no warm liquid water clouds (WLCC), potentially limiting the model’s accuracy in regions where WLCC are present. In this work, we apply the Davis model to a 9-month Micro Pulse Lidar dataset collected in Christchurch, New Zealand, a location which includes WLCC. We then evaluate the results relative to a reference VDR cloud phase mask. We found that the Davis model performed relatively poorly at detecting SLCC with an accuracy of 0.62, often misclassifying WLCC as SLCC. We then trained a new model, using data from Christchurch, to perform SLCC detection on the same set of co-polarized attenuated backscatter peak properties. Our new model performed well, with accuracy scores as high as 0.89, highlighting the effectiveness of the machine learning technique when appropriate training data relevant to the location is used. Text Antarc* Antarctica Copernicus Publications: E-Journals Christchurch ENVELOPE(164.167,164.167,-82.467,-82.467) Davis Station ENVELOPE(77.968,77.968,-68.576,-68.576) Davis-Station ENVELOPE(77.968,77.968,-68.576,-68.576) New Zealand |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
The use of depolarization lidar to measure atmospheric volume depolarization ratio (VDR) is a common technique to classify cloud phase (liquid or ice). Previous work using a machine learning framework, applied to peak properties derived from co-polarised attenuated backscatter data, has been demonstrated to effectively detect supercooled liquid water containing clouds (SLCC). However, the training data from Davis Station, Antarctica, includes no warm liquid water clouds (WLCC), potentially limiting the model’s accuracy in regions where WLCC are present. In this work, we apply the Davis model to a 9-month Micro Pulse Lidar dataset collected in Christchurch, New Zealand, a location which includes WLCC. We then evaluate the results relative to a reference VDR cloud phase mask. We found that the Davis model performed relatively poorly at detecting SLCC with an accuracy of 0.62, often misclassifying WLCC as SLCC. We then trained a new model, using data from Christchurch, to perform SLCC detection on the same set of co-polarized attenuated backscatter peak properties. Our new model performed well, with accuracy scores as high as 0.89, highlighting the effectiveness of the machine learning technique when appropriate training data relevant to the location is used. |
format |
Text |
author |
Whitehead, Luke Edgar McDonald, Adrian James Guyot, Adrien |
spellingShingle |
Whitehead, Luke Edgar McDonald, Adrian James Guyot, Adrien Supercooled liquid water cloud classification using lidar backscatter peak properties |
author_facet |
Whitehead, Luke Edgar McDonald, Adrian James Guyot, Adrien |
author_sort |
Whitehead, Luke Edgar |
title |
Supercooled liquid water cloud classification using lidar backscatter peak properties |
title_short |
Supercooled liquid water cloud classification using lidar backscatter peak properties |
title_full |
Supercooled liquid water cloud classification using lidar backscatter peak properties |
title_fullStr |
Supercooled liquid water cloud classification using lidar backscatter peak properties |
title_full_unstemmed |
Supercooled liquid water cloud classification using lidar backscatter peak properties |
title_sort |
supercooled liquid water cloud classification using lidar backscatter peak properties |
publishDate |
2023 |
url |
https://doi.org/10.5194/egusphere-2023-1085 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-1085/ |
long_lat |
ENVELOPE(164.167,164.167,-82.467,-82.467) ENVELOPE(77.968,77.968,-68.576,-68.576) ENVELOPE(77.968,77.968,-68.576,-68.576) |
geographic |
Christchurch Davis Station Davis-Station New Zealand |
geographic_facet |
Christchurch Davis Station Davis-Station New Zealand |
genre |
Antarc* Antarctica |
genre_facet |
Antarc* Antarctica |
op_source |
eISSN: |
op_relation |
doi:10.5194/egusphere-2023-1085 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-1085/ |
op_doi |
https://doi.org/10.5194/egusphere-2023-1085 |
_version_ |
1772821149913186304 |