MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES
Today, radar imaging from space allows continuous and wide-area sea ice monitoring under nearly all weather conditions. To this end, we applied modern machine learning techniques to produce ice-describing semantic maps of the polar regions of the Earth. Time series of these maps can then be exploite...
Published in: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
---|---|
Main Authors: | , , , |
Format: | Conference Object |
Language: | unknown |
Published: |
Zenodo
2019
|
Subjects: | |
Online Access: | https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 |
id |
ftzenodo:oai:zenodo.org:3941579 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:3941579 2024-09-15T18:34:46+00:00 MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES C.O. Dumitru V. Andrei G. Schwarz M. Datcu 2019-09-17 https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 unknown Zenodo https://zenodo.org/communities/eu https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 oai:zenodo.org:3941579 info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode info:eu-repo/semantics/conferencePaper 2019 ftzenodo https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 2024-07-26T23:26:22Z Today, radar imaging from space allows continuous and wide-area sea ice monitoring under nearly all weather conditions. To this end, we applied modern machine learning techniques to produce ice-describing semantic maps of the polar regions of the Earth. Time series of these maps can then be exploited for local and regional change maps of selected areas. What we expect, however, are fullyautomated unsupervised routine classifications of sea ice regions that are needed for the rapid and reliable monitoring of shipping routes, drifting and disintegrating icebergs, snowfall and melting on ice, and other dynamic climate change indicators. Therefore, we designed and implemented an automated processing chain that analyses and interprets the specific ice-related content of highresolution synthetic aperture radar (SAR) images. We trained this system with selected images covering various use cases allowing us to interpret these images with modern machine learning approaches. In the following, we describe a system comprising representation learning, variational inference, and auto-encoders. Test runs have already demonstrated its usefulness and stability that can pave the way towards future artificial intelligence systems extending, for instance, the current capabilities of traditional image analysis by including content-related image understanding. Conference Object Sea ice Zenodo The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W16 83 89 |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
description |
Today, radar imaging from space allows continuous and wide-area sea ice monitoring under nearly all weather conditions. To this end, we applied modern machine learning techniques to produce ice-describing semantic maps of the polar regions of the Earth. Time series of these maps can then be exploited for local and regional change maps of selected areas. What we expect, however, are fullyautomated unsupervised routine classifications of sea ice regions that are needed for the rapid and reliable monitoring of shipping routes, drifting and disintegrating icebergs, snowfall and melting on ice, and other dynamic climate change indicators. Therefore, we designed and implemented an automated processing chain that analyses and interprets the specific ice-related content of highresolution synthetic aperture radar (SAR) images. We trained this system with selected images covering various use cases allowing us to interpret these images with modern machine learning approaches. In the following, we describe a system comprising representation learning, variational inference, and auto-encoders. Test runs have already demonstrated its usefulness and stability that can pave the way towards future artificial intelligence systems extending, for instance, the current capabilities of traditional image analysis by including content-related image understanding. |
format |
Conference Object |
author |
C.O. Dumitru V. Andrei G. Schwarz M. Datcu |
spellingShingle |
C.O. Dumitru V. Andrei G. Schwarz M. Datcu MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
author_facet |
C.O. Dumitru V. Andrei G. Schwarz M. Datcu |
author_sort |
C.O. Dumitru |
title |
MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
title_short |
MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
title_full |
MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
title_fullStr |
MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
title_full_unstemmed |
MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES |
title_sort |
machine learning for sea ice monitoring from satellites |
publisher |
Zenodo |
publishDate |
2019 |
url |
https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
https://zenodo.org/communities/eu https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 oai:zenodo.org:3941579 |
op_rights |
info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 |
container_title |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
container_volume |
XLII-2/W16 |
container_start_page |
83 |
op_container_end_page |
89 |
_version_ |
1810476733483188224 |