Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning
Melt ponds are pools of water that form during summer on the surface of the arctic ice. Due to the lower albedo, melt ponds absorb more solar radiation than surrounding ice and hence have higher temperature. This causes more water to melt, creating a feedback loop. This means that melt pond fraction...
Main Authors: | , , |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://elib.dlr.de/203883/ https://elib.dlr.de/203883/1/EGU2024_MeltPond_Poster2.pdf |
id |
ftdlr:oai:elib.dlr.de:203883 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:203883 2024-05-19T07:27:47+00:00 Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning Rösel, Anja Neckel, Niklas Jancauskas, Vytautas 2024-04 application/pdf https://elib.dlr.de/203883/ https://elib.dlr.de/203883/1/EGU2024_MeltPond_Poster2.pdf en eng https://elib.dlr.de/203883/1/EGU2024_MeltPond_Poster2.pdf Rösel, Anja und Neckel, Niklas und Jancauskas, Vytautas (2024) Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning. In: EGU24-16672. EGU General Assembly 2024, 2024-04-14 - 2024-04-19, Vienna, Austria. doi:10.5194/egusphere-egu24-16672 <https://doi.org/10.5194/egusphere-egu24-16672>. EO Data Science Konferenzbeitrag NonPeerReviewed 2024 ftdlr https://doi.org/10.5194/egusphere-egu24-16672 2024-05-01T23:30:12Z Melt ponds are pools of water that form during summer on the surface of the arctic ice. Due to the lower albedo, melt ponds absorb more solar radiation than surrounding ice and hence have higher temperature. This causes more water to melt, creating a feedback loop. This means that melt pond fraction in ice sheets is an important factor to consider in global climate and sea ice models. In situ measurements are difficult and expensive in terms of time and labor. Furthermore, these measurements can only cover limited areas. This makes using Earth Observation methods for this task particularly attractive. Until today, there is no sophisticated global melt pond data set available: Accurate methods may exist for determining melt ponds from Sentinel-2 data. The downside of using Sentinel-2 is that parts of the High Arctic are not covered by this mission. MODIS data covers the whole globe at least once every three days, but the downside of it is that MODIS resolution is much coarser (250m vs. 10m). Since melt ponds are in general much smaller than 250m, it means that accurately capturing melt pond fraction from these data is difficult. We propose to address these issues by employing Deep Learning techniques. Namely, we use Sentinel-2 data to train a model to super-resolve MODIS images to higher resolution and to use all available MODIS bands and their surrounding pixels for information context when predicting melt pond and open water fractions. In addition, a thorough uncertainty quantification (UQ) will be applied by using the UQ Toolbox. Conference Object albedo Arctic Arctic Sea ice German Aerospace Center: elib - DLR electronic library |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
English |
topic |
EO Data Science |
spellingShingle |
EO Data Science Rösel, Anja Neckel, Niklas Jancauskas, Vytautas Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
topic_facet |
EO Data Science |
description |
Melt ponds are pools of water that form during summer on the surface of the arctic ice. Due to the lower albedo, melt ponds absorb more solar radiation than surrounding ice and hence have higher temperature. This causes more water to melt, creating a feedback loop. This means that melt pond fraction in ice sheets is an important factor to consider in global climate and sea ice models. In situ measurements are difficult and expensive in terms of time and labor. Furthermore, these measurements can only cover limited areas. This makes using Earth Observation methods for this task particularly attractive. Until today, there is no sophisticated global melt pond data set available: Accurate methods may exist for determining melt ponds from Sentinel-2 data. The downside of using Sentinel-2 is that parts of the High Arctic are not covered by this mission. MODIS data covers the whole globe at least once every three days, but the downside of it is that MODIS resolution is much coarser (250m vs. 10m). Since melt ponds are in general much smaller than 250m, it means that accurately capturing melt pond fraction from these data is difficult. We propose to address these issues by employing Deep Learning techniques. Namely, we use Sentinel-2 data to train a model to super-resolve MODIS images to higher resolution and to use all available MODIS bands and their surrounding pixels for information context when predicting melt pond and open water fractions. In addition, a thorough uncertainty quantification (UQ) will be applied by using the UQ Toolbox. |
format |
Conference Object |
author |
Rösel, Anja Neckel, Niklas Jancauskas, Vytautas |
author_facet |
Rösel, Anja Neckel, Niklas Jancauskas, Vytautas |
author_sort |
Rösel, Anja |
title |
Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
title_short |
Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
title_full |
Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
title_fullStr |
Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
title_full_unstemmed |
Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning |
title_sort |
arctic meltponds: automated detection algorithm using enhanced machine learning |
publishDate |
2024 |
url |
https://elib.dlr.de/203883/ https://elib.dlr.de/203883/1/EGU2024_MeltPond_Poster2.pdf |
genre |
albedo Arctic Arctic Sea ice |
genre_facet |
albedo Arctic Arctic Sea ice |
op_relation |
https://elib.dlr.de/203883/1/EGU2024_MeltPond_Poster2.pdf Rösel, Anja und Neckel, Niklas und Jancauskas, Vytautas (2024) Arctic Meltponds: Automated Detection Algorithm Using Enhanced Machine Learning. In: EGU24-16672. EGU General Assembly 2024, 2024-04-14 - 2024-04-19, Vienna, Austria. doi:10.5194/egusphere-egu24-16672 <https://doi.org/10.5194/egusphere-egu24-16672>. |
op_doi |
https://doi.org/10.5194/egusphere-egu24-16672 |
_version_ |
1799469049232490496 |