Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction
Arctic sea ice plays a significant role in climate systems, and its prediction is important for coping with global warming. Artificial intelligence (AI) has gained recent attention in various disciplines with the increasing use of big data. In recent years, the use of AI-based sea ice prediction, al...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13173413 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/17/3413/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/17/3413/ 2023-08-20T04:03:28+02:00 Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction Junhwa Chi Jihyun Bae Young-Joo Kwon agris 2021-08-27 application/pdf https://doi.org/10.3390/rs13173413 EN eng Multidisciplinary Digital Publishing Institute Remote Sensing in Geology, Geomorphology and Hydrology https://dx.doi.org/10.3390/rs13173413 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 17; Pages: 3413 Arctic sea ice convolutional neural network long- and short-term memory visual geometry group (VGG) loss function deep learning future prediction Text 2021 ftmdpi https://doi.org/10.3390/rs13173413 2023-08-01T02:32:57Z Arctic sea ice plays a significant role in climate systems, and its prediction is important for coping with global warming. Artificial intelligence (AI) has gained recent attention in various disciplines with the increasing use of big data. In recent years, the use of AI-based sea ice prediction, along with conventional prediction models, has drawn attention. This study proposes a new deep learning (DL)-based Arctic sea ice prediction model with a new perceptual loss function to improve both statistical and visual accuracy. The proposed DL model learned spatiotemporal characteristics of Arctic sea ice for sequence-to-sequence predictions. The convolutional neural network-based perceptual loss function successfully captured unique sea ice patterns, and the widely used loss functions could not use various feature maps. Furthermore, the input variables that are essential to accurately predict Arctic sea ice using various combinations of input variables were identified. The proposed approaches produced statistical outcomes with better accuracy and qualitative agreements with the observed data. Text Arctic Global warming Sea ice MDPI Open Access Publishing Arctic Remote Sensing 13 17 3413 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
Arctic sea ice convolutional neural network long- and short-term memory visual geometry group (VGG) loss function deep learning future prediction |
spellingShingle |
Arctic sea ice convolutional neural network long- and short-term memory visual geometry group (VGG) loss function deep learning future prediction Junhwa Chi Jihyun Bae Young-Joo Kwon Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
topic_facet |
Arctic sea ice convolutional neural network long- and short-term memory visual geometry group (VGG) loss function deep learning future prediction |
description |
Arctic sea ice plays a significant role in climate systems, and its prediction is important for coping with global warming. Artificial intelligence (AI) has gained recent attention in various disciplines with the increasing use of big data. In recent years, the use of AI-based sea ice prediction, along with conventional prediction models, has drawn attention. This study proposes a new deep learning (DL)-based Arctic sea ice prediction model with a new perceptual loss function to improve both statistical and visual accuracy. The proposed DL model learned spatiotemporal characteristics of Arctic sea ice for sequence-to-sequence predictions. The convolutional neural network-based perceptual loss function successfully captured unique sea ice patterns, and the widely used loss functions could not use various feature maps. Furthermore, the input variables that are essential to accurately predict Arctic sea ice using various combinations of input variables were identified. The proposed approaches produced statistical outcomes with better accuracy and qualitative agreements with the observed data. |
format |
Text |
author |
Junhwa Chi Jihyun Bae Young-Joo Kwon |
author_facet |
Junhwa Chi Jihyun Bae Young-Joo Kwon |
author_sort |
Junhwa Chi |
title |
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
title_short |
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
title_full |
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
title_fullStr |
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
title_full_unstemmed |
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction |
title_sort |
two-stream convolutional long- and short-term memory model using perceptual loss for sequence-to-sequence arctic sea ice prediction |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13173413 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Global warming Sea ice |
genre_facet |
Arctic Global warming Sea ice |
op_source |
Remote Sensing; Volume 13; Issue 17; Pages: 3413 |
op_relation |
Remote Sensing in Geology, Geomorphology and Hydrology https://dx.doi.org/10.3390/rs13173413 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13173413 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
17 |
container_start_page |
3413 |
_version_ |
1774713842406785024 |