Two-pathway spatiotemporal representation learning for extreme water temperature prediction SCIE SCOPUS

Cited 0 time in WEB OF SCIENCE Cited 0 time in Scopus
Title
Two-pathway spatiotemporal representation learning for extreme water temperature prediction
Author(s)
Kim, Jinah; Kim, Taekyung; Kim, Jaeil
KIOST Author(s)
Kim, Jinah(김진아)Kim, Taekyung(김태경)
Alternative Author(s)
김진아; 김태경
Publication Year
2024-05
Abstract
Accurate predictions of extreme water temperatures are criticalto understanding the variability of the marine environment and reducing marine disasters maximized by global warming. In this study, we propose a two-pathway framework with separated spatial and temporal encoders for accurate prediction of water temperature, especially extremely high water temperature, through effective spatiotemporal representation learning. The spatial and temporal encoder networks based on the Transformer’s self-attention mechanism performs the task of predicting the water temperature time series at the 16 coastal locations around the Korean Peninsula for the seven consecutive days ahead at daily intervals with various combinations of patch embedding methods, positional embedding for spatial features. Comparative experiments with conventional deep convolutional and recurrent networks are also conducted for comparison. By comparing and assessing these results, the proposed two-pathway framework can improve the predictability of extremely high coastal water temperature by better capturing spatiotemporal interrelationships and long-range dependencies from open ocean and regional sea, and further determines the optimal architectural details of self-attention-based spatial and temporal encoders. Furthermore, to examine the explainability of the proposed model and its consistency with domain knowledge, spatial and temporal attention maps are visualized and analyzed that represents weights for spatiotemporal input sequences that are more relevant to predict for future predictions.
ISSN
0952-1976
URI
https://sciwatch.kiost.ac.kr/handle/2020.kiost/45373
DOI
10.1016/j.engappai.2023.107718
Bibliographic Citation
Engineering Applications of Artificial Intelligence, v.131, 2024
Publisher
Pergamon Press Ltd.
Keywords
Marine heatwaves; Multi-step-ahead prediction; Sea surface temperature; Self-attention mechanism; Spatiotemporal representation learning; Two-pathway representation learning
Type
Article
Language
English
Document Type
Article
Files in This Item:
There are no files associated with this item.

qrcode

Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse