An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula

Tianliang Xu; Zhiquan Zhou; Shanqiang Yang; Chenxu Wang; Ying Liu

doi:10.1109/ICPICS58376.2023.10235655

An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula

Tianliang Xu
, Zhiquan Zhou
, Shanqiang Yang
, Chenxu Wang^*
, Ying Liu^*

^*Corresponding author for this work

School of Information Science and Engineering

School of Electronics and Information Engineering, Harbin Institute of Technology
Harbin Institute of Technology
Disaster Reduction Center

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Ocean temperature has an important influence on the distribution and migration of marine fishes, and with the improvement of modern remote sensing information acquisition technology, ocean data are constantly being improved. Sea surface temperature (SST) around the Korean Peninsula is influenced by several complex factors. In this paper, an improved long short-term memory network (LSTM) model with attention mechanism is proposed to predict the SST for the next 5 days, which extracts more temporal and spatial information by assigning new weights through the attention mechanism. The experimental results show that the root mean square error (RMSE) of the proposed model on day 1 is 0.2181°C and the prediction accuracy (PACC) is 99.14%, which is a 20% reduction in RMSE compared to the existing similar networks.

Original language	English
Title of host publication	2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	192-196
Number of pages	5
ISBN (Electronic)	9798350333442
DOIs	https://doi.org/10.1109/ICPICS58376.2023.10235655
State	Published - 2023
Event	5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023 - Shenyang, China Duration: 14 Jul 2023 → 16 Jul 2023

Publication series

Name	2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

Conference

Conference	5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023
Country/Territory	China
City	Shenyang
Period	14/07/23 → 16/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

LSTM network
SST
attention mechanism
prediction

Access to Document

10.1109/ICPICS58376.2023.10235655

Cite this

Xu, T., Zhou, Z., Yang, S., Wang, C., & Liu, Y. (2023). An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula. In 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023 (pp. 192-196). (2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPICS58376.2023.10235655

Xu, Tianliang ; Zhou, Zhiquan ; Yang, Shanqiang et al. / An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula. 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 192-196 (2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023).

@inproceedings{29373c3d66ff4d74b1d4ec3a37b7f4e7,

title = "An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula",

abstract = "Ocean temperature has an important influence on the distribution and migration of marine fishes, and with the improvement of modern remote sensing information acquisition technology, ocean data are constantly being improved. Sea surface temperature (SST) around the Korean Peninsula is influenced by several complex factors. In this paper, an improved long short-term memory network (LSTM) model with attention mechanism is proposed to predict the SST for the next 5 days, which extracts more temporal and spatial information by assigning new weights through the attention mechanism. The experimental results show that the root mean square error (RMSE) of the proposed model on day 1 is 0.2181°C and the prediction accuracy (PACC) is 99.14\%, which is a 20\% reduction in RMSE compared to the existing similar networks.",

keywords = "LSTM network, SST, attention mechanism, prediction",

author = "Tianliang Xu and Zhiquan Zhou and Shanqiang Yang and Chenxu Wang and Ying Liu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023 ; Conference date: 14-07-2023 Through 16-07-2023",

year = "2023",

doi = "10.1109/ICPICS58376.2023.10235655",

language = "英语",

series = "2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "192--196",

booktitle = "2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023",

address = "美国",

}

Xu, T, Zhou, Z, Yang, S, Wang, C & Liu, Y 2023, An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula. in 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023. 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023, Institute of Electrical and Electronics Engineers Inc., pp. 192-196, 5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023, Shenyang, China, 14/07/23. https://doi.org/10.1109/ICPICS58376.2023.10235655

An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula. / Xu, Tianliang; Zhou, Zhiquan; Yang, Shanqiang et al.
2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 192-196 (2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula

AU - Xu, Tianliang

AU - Zhou, Zhiquan

AU - Yang, Shanqiang

AU - Wang, Chenxu

AU - Liu, Ying

PY - 2023

Y1 - 2023

N2 - Ocean temperature has an important influence on the distribution and migration of marine fishes, and with the improvement of modern remote sensing information acquisition technology, ocean data are constantly being improved. Sea surface temperature (SST) around the Korean Peninsula is influenced by several complex factors. In this paper, an improved long short-term memory network (LSTM) model with attention mechanism is proposed to predict the SST for the next 5 days, which extracts more temporal and spatial information by assigning new weights through the attention mechanism. The experimental results show that the root mean square error (RMSE) of the proposed model on day 1 is 0.2181°C and the prediction accuracy (PACC) is 99.14%, which is a 20% reduction in RMSE compared to the existing similar networks.

AB - Ocean temperature has an important influence on the distribution and migration of marine fishes, and with the improvement of modern remote sensing information acquisition technology, ocean data are constantly being improved. Sea surface temperature (SST) around the Korean Peninsula is influenced by several complex factors. In this paper, an improved long short-term memory network (LSTM) model with attention mechanism is proposed to predict the SST for the next 5 days, which extracts more temporal and spatial information by assigning new weights through the attention mechanism. The experimental results show that the root mean square error (RMSE) of the proposed model on day 1 is 0.2181°C and the prediction accuracy (PACC) is 99.14%, which is a 20% reduction in RMSE compared to the existing similar networks.

KW - LSTM network

KW - SST

KW - attention mechanism

KW - prediction

UR - https://www.scopus.com/pages/publications/85172927942

U2 - 10.1109/ICPICS58376.2023.10235655

DO - 10.1109/ICPICS58376.2023.10235655

M3 - 会议稿件

AN - SCOPUS:85172927942

T3 - 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

SP - 192

EP - 196

BT - 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2023

Y2 - 14 July 2023 through 16 July 2023

ER -

Xu T, Zhou Z, Yang S, Wang C, Liu Y. An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula. In 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 192-196. (2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023). doi: 10.1109/ICPICS58376.2023.10235655

An Improved LSTM Model with Attention Mechanism for Sea Surface Temperature Prediction Around the Korean Peninsula

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this