Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Granulation-based LSTM-RF combination model for hourly sea surface temperature predictionopen access

Authors
Cao, MengmengMao, KebiaoBateni, Sayed M.Jun, ChanghyunShi, JianchengDu, YongmingDu, Guoming
Issue Date
Dec-2023
Publisher
Taylor and Francis Ltd.
Keywords
adaptive granulation method; error reciprocal method; LSTM; RF; SST prediction
Citation
International Journal of Digital Earth, v.16, no.1, pp 3838 - 3859
Pages
22
Journal Title
International Journal of Digital Earth
Volume
16
Number
1
Start Page
3838
End Page
3859
URI
https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/70169
DOI
10.1080/17538947.2023.2260779
ISSN
1753-8947
1753-8955
Abstract
Accurate predictions of sea surface temperature (SST) are crucial due to the significant impact of SST on the global ocean-atmospheric system and its potential to trigger extreme weather events. Many existing machine-learning-based SST predictions adapt the traditional iterative point-wise prediction mechanism, whose predicting horizons and accuracy are limited owing to the high sensitivity to cumulative errors during iterative predictions. Therefore, this paper proposes a novel granulation-based long short-term memory (LSTM)-random forest (RF) combination model that can fully capture the feature dependencies involved in the fluctuation of SST sequences, reduce the cumulative error in the iteration process, and extend the prediction horizons, which includes two sub-models (adaptive granulation model and hybrid prediction model). They can restack the one-dimensional SST time-series into multidimensional feature variables, and achieve a strong forecasting ability. The analysis shows that the proposed model can achieve more accurate prediction-hours in nearly all prediction ranges from 1 to 125 h. The average prediction error of the proposed model in 25–125 h is 0.07 K, similar to that (0.067 K) in the first 24 h, which exhibits a high generalization performance and robustness and isthus a promising platform for the medium- and long-term forecasting of hourly SSTs. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Files in This Item
Appears in
Collections
ETC > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Jun, Changhyun photo

Jun, Changhyun
공과대학 (건설환경플랜트공학)
Read more

Altmetrics

Total Views & Downloads

BROWSE