Segmentation of PMSE Data Using Random Forests
EISCAT VHF radar data are used for observing, monitoring, and understanding Earth’s upper atmosphere. This paper presents an approach to segment Polar Mesospheric Summer Echoes (PMSE) from datasets obtained from EISCAT VHF radar data. The data consist of 30 observations days, corresponding to 56,250...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14132976 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/14/13/2976/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/14/13/2976/ 2023-10-09T21:51:08+02:00 Segmentation of PMSE Data Using Random Forests Dorota Jozwicki Puneet Sharma Ingrid Mann Ulf-Peter Hoppe agris 2022-06-22 application/pdf https://doi.org/10.3390/rs14132976 eng eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs14132976 https://creativecommons.org/licenses/by/4.0/ Remote Sensing Volume 14 Issue 13 Pages: 2976 space physics upper atmosphere random forests segmentation Text 2022 ftmdpi https://doi.org/10.3390/rs14132976 2023-09-10T23:55:41Z EISCAT VHF radar data are used for observing, monitoring, and understanding Earth’s upper atmosphere. This paper presents an approach to segment Polar Mesospheric Summer Echoes (PMSE) from datasets obtained from EISCAT VHF radar data. The data consist of 30 observations days, corresponding to 56,250 data samples. We manually labeled the data into three different categories: PMSE, Ionospheric background, and Background noise. For segmentation, we employed random forests on a set of simple features. These features include: altitude derivative, time derivative, mean, median, standard deviation, minimum, and maximum values corresponding to neighborhood sizes ranging from 3 by 3 to 11 by 11 pixels. Next, in order to reduce the model bias and variance, we employed a method that decreases the weight applied to pixel labels with large uncertainty. Our results indicate that, first, it is possible to segment PMSE from the data using random forests. Second, the weighted-down labels technique improves the performance of the random forests method. Text EISCAT MDPI Open Access Publishing Remote Sensing 14 13 2976 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
space physics upper atmosphere random forests segmentation |
spellingShingle |
space physics upper atmosphere random forests segmentation Dorota Jozwicki Puneet Sharma Ingrid Mann Ulf-Peter Hoppe Segmentation of PMSE Data Using Random Forests |
topic_facet |
space physics upper atmosphere random forests segmentation |
description |
EISCAT VHF radar data are used for observing, monitoring, and understanding Earth’s upper atmosphere. This paper presents an approach to segment Polar Mesospheric Summer Echoes (PMSE) from datasets obtained from EISCAT VHF radar data. The data consist of 30 observations days, corresponding to 56,250 data samples. We manually labeled the data into three different categories: PMSE, Ionospheric background, and Background noise. For segmentation, we employed random forests on a set of simple features. These features include: altitude derivative, time derivative, mean, median, standard deviation, minimum, and maximum values corresponding to neighborhood sizes ranging from 3 by 3 to 11 by 11 pixels. Next, in order to reduce the model bias and variance, we employed a method that decreases the weight applied to pixel labels with large uncertainty. Our results indicate that, first, it is possible to segment PMSE from the data using random forests. Second, the weighted-down labels technique improves the performance of the random forests method. |
format |
Text |
author |
Dorota Jozwicki Puneet Sharma Ingrid Mann Ulf-Peter Hoppe |
author_facet |
Dorota Jozwicki Puneet Sharma Ingrid Mann Ulf-Peter Hoppe |
author_sort |
Dorota Jozwicki |
title |
Segmentation of PMSE Data Using Random Forests |
title_short |
Segmentation of PMSE Data Using Random Forests |
title_full |
Segmentation of PMSE Data Using Random Forests |
title_fullStr |
Segmentation of PMSE Data Using Random Forests |
title_full_unstemmed |
Segmentation of PMSE Data Using Random Forests |
title_sort |
segmentation of pmse data using random forests |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14132976 |
op_coverage |
agris |
genre |
EISCAT |
genre_facet |
EISCAT |
op_source |
Remote Sensing Volume 14 Issue 13 Pages: 2976 |
op_relation |
https://dx.doi.org/10.3390/rs14132976 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs14132976 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
13 |
container_start_page |
2976 |
_version_ |
1779314219048501248 |