Predicting ice flow using machine learning
Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2019
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.1910.08922 https://arxiv.org/abs/1910.08922 |
id |
ftdatacite:10.48550/arxiv.1910.08922 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.1910.08922 2023-05-15T16:22:28+02:00 Predicting ice flow using machine learning Min, Yimeng Mukkavilli, S. Karthik Bengio, Yoshua 2019 https://dx.doi.org/10.48550/arxiv.1910.08922 https://arxiv.org/abs/1910.08922 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Machine Learning cs.LG Atmospheric and Oceanic Physics physics.ao-ph Geophysics physics.geo-ph Machine Learning stat.ML FOS Computer and information sciences FOS Physical sciences Article CreativeWork article Preprint 2019 ftdatacite https://doi.org/10.48550/arxiv.1910.08922 2022-03-10T16:21:38Z Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future video frame prediction, to increase the accuracy of ice flow tracking in multi-spectral satellite images. As the volume of cryosphere data increases in coming years, this is an interesting and important opportunity for machine learning to address a global challenge for climate change, risk management from floods, and conserving freshwater resources. Future frame prediction of ice melt and tracking the optical flow of ice dynamics presents modeling difficulties, due to uncertainties in global temperature increase, changing precipitation patterns, occlusion from cloud cover, rapid melting and glacier retreat due to black carbon aerosol deposition, from wildfires or human fossil emissions. We show the adversarial learning method helps improve the accuracy of tracking the optical flow of ice dynamics compared to existing methods in climate science. We present a dataset, IceNet, to encourage machine learning research and to help facilitate further applications in the areas of cryospheric science and climate change. : 33rd Conference on Neural Information Processing Systems (NeurIPS), Workshop on Tackling Climate Change with Machine Learning, Vancouver, Canada, 2019 Article in Journal/Newspaper glacier* DataCite Metadata Store (German National Library of Science and Technology) Canada |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Machine Learning cs.LG Atmospheric and Oceanic Physics physics.ao-ph Geophysics physics.geo-ph Machine Learning stat.ML FOS Computer and information sciences FOS Physical sciences |
spellingShingle |
Machine Learning cs.LG Atmospheric and Oceanic Physics physics.ao-ph Geophysics physics.geo-ph Machine Learning stat.ML FOS Computer and information sciences FOS Physical sciences Min, Yimeng Mukkavilli, S. Karthik Bengio, Yoshua Predicting ice flow using machine learning |
topic_facet |
Machine Learning cs.LG Atmospheric and Oceanic Physics physics.ao-ph Geophysics physics.geo-ph Machine Learning stat.ML FOS Computer and information sciences FOS Physical sciences |
description |
Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future video frame prediction, to increase the accuracy of ice flow tracking in multi-spectral satellite images. As the volume of cryosphere data increases in coming years, this is an interesting and important opportunity for machine learning to address a global challenge for climate change, risk management from floods, and conserving freshwater resources. Future frame prediction of ice melt and tracking the optical flow of ice dynamics presents modeling difficulties, due to uncertainties in global temperature increase, changing precipitation patterns, occlusion from cloud cover, rapid melting and glacier retreat due to black carbon aerosol deposition, from wildfires or human fossil emissions. We show the adversarial learning method helps improve the accuracy of tracking the optical flow of ice dynamics compared to existing methods in climate science. We present a dataset, IceNet, to encourage machine learning research and to help facilitate further applications in the areas of cryospheric science and climate change. : 33rd Conference on Neural Information Processing Systems (NeurIPS), Workshop on Tackling Climate Change with Machine Learning, Vancouver, Canada, 2019 |
format |
Article in Journal/Newspaper |
author |
Min, Yimeng Mukkavilli, S. Karthik Bengio, Yoshua |
author_facet |
Min, Yimeng Mukkavilli, S. Karthik Bengio, Yoshua |
author_sort |
Min, Yimeng |
title |
Predicting ice flow using machine learning |
title_short |
Predicting ice flow using machine learning |
title_full |
Predicting ice flow using machine learning |
title_fullStr |
Predicting ice flow using machine learning |
title_full_unstemmed |
Predicting ice flow using machine learning |
title_sort |
predicting ice flow using machine learning |
publisher |
arXiv |
publishDate |
2019 |
url |
https://dx.doi.org/10.48550/arxiv.1910.08922 https://arxiv.org/abs/1910.08922 |
geographic |
Canada |
geographic_facet |
Canada |
genre |
glacier* |
genre_facet |
glacier* |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.1910.08922 |
_version_ |
1766010443516608512 |