Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data
Surface albedo is a necessary parameter for climate studies and modeling. There is a need for a full spatial coverage of albedo data, but clouds and high solar zenith angle cause missing values to the optical satellite products, especially around the polar areas. Therefore, our motivation is to deve...
Published in: | International Journal of Applied Earth Observation and Geoinformation |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1016/j.jag.2022.102701 https://doaj.org/article/4b0682e951f348cba29589c1fb2573e7 |
id |
fttriple:oai:gotriple.eu:oai:doaj.org/article:4b0682e951f348cba29589c1fb2573e7 |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:oai:doaj.org/article:4b0682e951f348cba29589c1fb2573e7 2023-05-15T13:10:33+02:00 Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data Emmihenna Jääskeläinen Terhikki Manninen Janne Hakkarainen Johanna Tamminen 2022-03-01 https://doi.org/10.1016/j.jag.2022.102701 https://doaj.org/article/4b0682e951f348cba29589c1fb2573e7 en eng Elsevier 1569-8432 doi:10.1016/j.jag.2022.102701 https://doaj.org/article/4b0682e951f348cba29589c1fb2573e7 undefined International Journal of Applied Earth Observations and Geoinformation, Vol 107, Iss , Pp 102701- (2022) Surface albedo Machine learning Gradient boosting Gap filling geo envir Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2022 fttriple https://doi.org/10.1016/j.jag.2022.102701 2023-01-22T19:14:53Z Surface albedo is a necessary parameter for climate studies and modeling. There is a need for a full spatial coverage of albedo data, but clouds and high solar zenith angle cause missing values to the optical satellite products, especially around the polar areas. Therefore, our motivation is to develop gap filling models. For that purpose, we will apply monthly gradient boosting (GB) based models to the Arctic sea ice area of the 34 years long albedo time series of the Satellite Application Facility on Climate Monitoring (CM SAF) project. We demonstrate the ability of the GB models to accurately fill missing data using albedo monthly mean, brightness temperature, and sea ice concentration as model inputs. Monthly GB models produce the most unbiased, precise, and robust estimates when compared to alternative estimates presented, such as monthly mean albedo values or estimates from monthly linear regression (LR) models. The mean relative differences between GB based estimates and original pentad values vary from −20% to 20% with RMSE being 0.048, compared to relative differences varying from −20% to over 60% with RMSE varying from 0.054 to 0.074 between other estimates and original pentad values. Pixelwise mean differences and standard deviations (std) over the whole Arctic sea ice area show that GB based estimates are more accurate (mean differences from −0.02 to 0.02) and more precise (std from 0.02 to 0.08) than other estimates (mean differences varying between −0.05 to over 0.05, and std varying from around 0.03 to over 0.1). Also, albedo of the melting sea ice is predicted better by the GB model, with negligible mean differences, compared to the LR model. Based on these results, we show that GB method is a useful technique to fill missing data, and the brightness temperature and sea ice concentration are useful additional model input data sources. Article in Journal/Newspaper albedo Arctic Sea ice Unknown Arctic The Gib ENVELOPE(-57.531,-57.531,51.817,51.817) International Journal of Applied Earth Observation and Geoinformation 107 102701 |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English |
topic |
Surface albedo Machine learning Gradient boosting Gap filling geo envir |
spellingShingle |
Surface albedo Machine learning Gradient boosting Gap filling geo envir Emmihenna Jääskeläinen Terhikki Manninen Janne Hakkarainen Johanna Tamminen Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
topic_facet |
Surface albedo Machine learning Gradient boosting Gap filling geo envir |
description |
Surface albedo is a necessary parameter for climate studies and modeling. There is a need for a full spatial coverage of albedo data, but clouds and high solar zenith angle cause missing values to the optical satellite products, especially around the polar areas. Therefore, our motivation is to develop gap filling models. For that purpose, we will apply monthly gradient boosting (GB) based models to the Arctic sea ice area of the 34 years long albedo time series of the Satellite Application Facility on Climate Monitoring (CM SAF) project. We demonstrate the ability of the GB models to accurately fill missing data using albedo monthly mean, brightness temperature, and sea ice concentration as model inputs. Monthly GB models produce the most unbiased, precise, and robust estimates when compared to alternative estimates presented, such as monthly mean albedo values or estimates from monthly linear regression (LR) models. The mean relative differences between GB based estimates and original pentad values vary from −20% to 20% with RMSE being 0.048, compared to relative differences varying from −20% to over 60% with RMSE varying from 0.054 to 0.074 between other estimates and original pentad values. Pixelwise mean differences and standard deviations (std) over the whole Arctic sea ice area show that GB based estimates are more accurate (mean differences from −0.02 to 0.02) and more precise (std from 0.02 to 0.08) than other estimates (mean differences varying between −0.05 to over 0.05, and std varying from around 0.03 to over 0.1). Also, albedo of the melting sea ice is predicted better by the GB model, with negligible mean differences, compared to the LR model. Based on these results, we show that GB method is a useful technique to fill missing data, and the brightness temperature and sea ice concentration are useful additional model input data sources. |
format |
Article in Journal/Newspaper |
author |
Emmihenna Jääskeläinen Terhikki Manninen Janne Hakkarainen Johanna Tamminen |
author_facet |
Emmihenna Jääskeläinen Terhikki Manninen Janne Hakkarainen Johanna Tamminen |
author_sort |
Emmihenna Jääskeläinen |
title |
Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
title_short |
Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
title_full |
Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
title_fullStr |
Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
title_full_unstemmed |
Filling gaps of black-sky surface albedo of the Arctic sea ice using gradient boosting and brightness temperature data |
title_sort |
filling gaps of black-sky surface albedo of the arctic sea ice using gradient boosting and brightness temperature data |
publisher |
Elsevier |
publishDate |
2022 |
url |
https://doi.org/10.1016/j.jag.2022.102701 https://doaj.org/article/4b0682e951f348cba29589c1fb2573e7 |
long_lat |
ENVELOPE(-57.531,-57.531,51.817,51.817) |
geographic |
Arctic The Gib |
geographic_facet |
Arctic The Gib |
genre |
albedo Arctic Sea ice |
genre_facet |
albedo Arctic Sea ice |
op_source |
International Journal of Applied Earth Observations and Geoinformation, Vol 107, Iss , Pp 102701- (2022) |
op_relation |
1569-8432 doi:10.1016/j.jag.2022.102701 https://doaj.org/article/4b0682e951f348cba29589c1fb2573e7 |
op_rights |
undefined |
op_doi |
https://doi.org/10.1016/j.jag.2022.102701 |
container_title |
International Journal of Applied Earth Observation and Geoinformation |
container_volume |
107 |
container_start_page |
102701 |
_version_ |
1766233856423231488 |