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: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/25561 https://doi.org/10.3390/rs14132976 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/25561 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/25561 2023-05-15T16:04:30+02:00 Segmentation of PMSE data using random forests Jozwicki, Dorota Sharma, Puneet Mann, Ingrid Hoppe, Ulf-Peter Jürgen 2022-06-22 https://hdl.handle.net/10037/25561 https://doi.org/10.3390/rs14132976 eng eng MDPI Remote Sensing FRIDAID 2032781 https://doi.org/10.3390/rs14132976 2072-4292 https://hdl.handle.net/10037/25561 openAccess Copyright 2022 The Author(s) Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2022 ftunivtroemsoe https://doi.org/10.3390/rs14132976 2022-06-29T22:58:55Z 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. Article in Journal/Newspaper EISCAT University of Tromsø: Munin Open Research Archive Remote Sensing 14 13 2976 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
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 |
Article in Journal/Newspaper |
author |
Jozwicki, Dorota Sharma, Puneet Mann, Ingrid Hoppe, Ulf-Peter Jürgen |
spellingShingle |
Jozwicki, Dorota Sharma, Puneet Mann, Ingrid Hoppe, Ulf-Peter Jürgen Segmentation of PMSE data using random forests |
author_facet |
Jozwicki, Dorota Sharma, Puneet Mann, Ingrid Hoppe, Ulf-Peter Jürgen |
author_sort |
Jozwicki, Dorota |
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 |
MDPI |
publishDate |
2022 |
url |
https://hdl.handle.net/10037/25561 https://doi.org/10.3390/rs14132976 |
genre |
EISCAT |
genre_facet |
EISCAT |
op_relation |
Remote Sensing FRIDAID 2032781 https://doi.org/10.3390/rs14132976 2072-4292 https://hdl.handle.net/10037/25561 |
op_rights |
openAccess Copyright 2022 The Author(s) |
op_doi |
https://doi.org/10.3390/rs14132976 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
13 |
container_start_page |
2976 |
_version_ |
1766400077688995840 |