Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network
The Arctic sea ice is an important indicator of the progress of global warming and climate change. Prediction of Arctic sea ice concentration has been investigated by many disciplines and predictions have been made using a variety of methods. Deep learning (DL) using large training datasets, also kn...
Published in: | Remote Sensing |
---|---|
Main Authors: | , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2017
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs9121305 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/9/12/1305/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/9/12/1305/ 2023-08-20T04:03:26+02:00 Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network Junhwa Chi Hyun-choel Kim agris 2017-12-12 application/pdf https://doi.org/10.3390/rs9121305 EN eng Multidisciplinary Digital Publishing Institute Ocean Remote Sensing https://dx.doi.org/10.3390/rs9121305 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 9; Issue 12; Pages: 1305 arctic sea ice autoregressive model deep learning global warming long and short-term memory machine learning multilayer perceptron neural network sea ice concentration sea ice extent Text 2017 ftmdpi https://doi.org/10.3390/rs9121305 2023-07-31T21:18:50Z The Arctic sea ice is an important indicator of the progress of global warming and climate change. Prediction of Arctic sea ice concentration has been investigated by many disciplines and predictions have been made using a variety of methods. Deep learning (DL) using large training datasets, also known as deep neural network, is a fast-growing area in machine learning that promises improved results when compared to traditional neural network methods. Arctic sea ice data, gathered since 1978 by passive microwave sensors, may be an appropriate input for training DL models. In this study, a large Arctic sea ice dataset was employed to train a deep neural network and this was then used to predict Arctic sea ice concentration, without incorporating any physical data. We compared the results of our methods quantitatively and qualitatively to results obtained using a traditional autoregressive (AR) model, and to a compilation of results from the Sea Ice Prediction Network, collected using a diverse set of approaches. Our DL-based prediction methods outperformed the AR model and yielded results comparable to those obtained with other models. Text Arctic Climate change Global warming Sea ice MDPI Open Access Publishing Arctic Remote Sensing 9 12 1305 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
arctic sea ice autoregressive model deep learning global warming long and short-term memory machine learning multilayer perceptron neural network sea ice concentration sea ice extent |
spellingShingle |
arctic sea ice autoregressive model deep learning global warming long and short-term memory machine learning multilayer perceptron neural network sea ice concentration sea ice extent Junhwa Chi Hyun-choel Kim Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
topic_facet |
arctic sea ice autoregressive model deep learning global warming long and short-term memory machine learning multilayer perceptron neural network sea ice concentration sea ice extent |
description |
The Arctic sea ice is an important indicator of the progress of global warming and climate change. Prediction of Arctic sea ice concentration has been investigated by many disciplines and predictions have been made using a variety of methods. Deep learning (DL) using large training datasets, also known as deep neural network, is a fast-growing area in machine learning that promises improved results when compared to traditional neural network methods. Arctic sea ice data, gathered since 1978 by passive microwave sensors, may be an appropriate input for training DL models. In this study, a large Arctic sea ice dataset was employed to train a deep neural network and this was then used to predict Arctic sea ice concentration, without incorporating any physical data. We compared the results of our methods quantitatively and qualitatively to results obtained using a traditional autoregressive (AR) model, and to a compilation of results from the Sea Ice Prediction Network, collected using a diverse set of approaches. Our DL-based prediction methods outperformed the AR model and yielded results comparable to those obtained with other models. |
format |
Text |
author |
Junhwa Chi Hyun-choel Kim |
author_facet |
Junhwa Chi Hyun-choel Kim |
author_sort |
Junhwa Chi |
title |
Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
title_short |
Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
title_full |
Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
title_fullStr |
Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
title_full_unstemmed |
Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network |
title_sort |
prediction of arctic sea ice concentration using a fully data driven deep neural network |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2017 |
url |
https://doi.org/10.3390/rs9121305 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Global warming Sea ice |
genre_facet |
Arctic Climate change Global warming Sea ice |
op_source |
Remote Sensing; Volume 9; Issue 12; Pages: 1305 |
op_relation |
Ocean Remote Sensing https://dx.doi.org/10.3390/rs9121305 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs9121305 |
container_title |
Remote Sensing |
container_volume |
9 |
container_issue |
12 |
container_start_page |
1305 |
_version_ |
1774713802499031040 |