KOPRI Repository

Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction

Cited 0 time in wos
Cited 0 time in scopus
Title
Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction
Other Titles
인지기반 최적화 함수와 이미지 및 시계열 인공지능 결합 모델을 통한 북극 해빙 예측 연구
Authors
Chi, Junhwa
Bae, Jihyun
Kwon, Young-Joo
Subject
Environmental Sciences & EcologyGeologyRemote SensingImaging Science & Photographic Technology
Keywords
Arctic sea iceconvolutional neural networkdeep learningfuture predictionlong- and short-term memoryloss functionvisual geometry group (VGG)
Issue Date
2021-09
Citation
Chi, Junhwa, 배지현, Kwon, Young-Joo. 2021. "Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction". REMOTE SENSING, 13(17): 3413-3432.
Abstract
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 have 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.
URI
https://repository.kopri.re.kr/handle/201206/12988
DOI
http://dx.doi.org/10.3390/rs13173413
Type
Article
Station
해당사항없음
Indexed
SCIE
Appears in Collections  
2021-2021, Preliminary research on Arctic sea ice prediction using artificial intelligence for the extension of Arctic research (21-21) / Chi, Junhwa (PE21420)
Files in This Item

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse