Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model
This article proposes a combined prediction model based on a bidirectional long short-term memory (BiLSTM) neural network optimized by the snake optimizer (SO) under complete ensemble empirical mode decomposition with adaptive noise. First, complete ensemble empirical mode decomposition with adaptiv...
Published in: | PeerJ |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
PeerJ
2023
|
Subjects: | |
Online Access: | http://dx.doi.org/10.7717/peerj.15748 https://peerj.com/articles/15748.pdf https://peerj.com/articles/15748.xml https://peerj.com/articles/15748.html |
id |
crpeerj:10.7717/peerj.15748 |
---|---|
record_format |
openpolar |
spelling |
crpeerj:10.7717/peerj.15748 2024-06-02T08:14:17+00:00 Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model Guo, Qiao Zhang, Haoyu Zhang, Yuhao Jiang, Xuchu 2023 http://dx.doi.org/10.7717/peerj.15748 https://peerj.com/articles/15748.pdf https://peerj.com/articles/15748.xml https://peerj.com/articles/15748.html en eng PeerJ https://creativecommons.org/licenses/by/4.0/ PeerJ volume 11, page e15748 ISSN 2167-8359 journal-article 2023 crpeerj https://doi.org/10.7717/peerj.15748 2024-05-07T14:14:21Z This article proposes a combined prediction model based on a bidirectional long short-term memory (BiLSTM) neural network optimized by the snake optimizer (SO) under complete ensemble empirical mode decomposition with adaptive noise. First, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was used to decompose the sea ice area time series data into a series of eigenmodes and perform noise reduction to enhance the stationarity and smoothness of the time series. Second, this article used a bidirectional long short-term memory neural network optimized by the snake optimizer to fully exploit the characteristics of each eigenmode of the time series to achieve the prediction of each. Finally, the predicted values of each mode are superimposed and reconstructed as the final prediction values. Our model achieves a good score of RMSE: 1.047, MAE: 0.815, and SMAPE: 3.938 on the test set. Article in Journal/Newspaper Sea ice PeerJ Publishing PeerJ 11 e15748 |
institution |
Open Polar |
collection |
PeerJ Publishing |
op_collection_id |
crpeerj |
language |
English |
description |
This article proposes a combined prediction model based on a bidirectional long short-term memory (BiLSTM) neural network optimized by the snake optimizer (SO) under complete ensemble empirical mode decomposition with adaptive noise. First, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was used to decompose the sea ice area time series data into a series of eigenmodes and perform noise reduction to enhance the stationarity and smoothness of the time series. Second, this article used a bidirectional long short-term memory neural network optimized by the snake optimizer to fully exploit the characteristics of each eigenmode of the time series to achieve the prediction of each. Finally, the predicted values of each mode are superimposed and reconstructed as the final prediction values. Our model achieves a good score of RMSE: 1.047, MAE: 0.815, and SMAPE: 3.938 on the test set. |
format |
Article in Journal/Newspaper |
author |
Guo, Qiao Zhang, Haoyu Zhang, Yuhao Jiang, Xuchu |
spellingShingle |
Guo, Qiao Zhang, Haoyu Zhang, Yuhao Jiang, Xuchu Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
author_facet |
Guo, Qiao Zhang, Haoyu Zhang, Yuhao Jiang, Xuchu |
author_sort |
Guo, Qiao |
title |
Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
title_short |
Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
title_full |
Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
title_fullStr |
Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
title_full_unstemmed |
Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model |
title_sort |
prediction of sea ice area based on the ceemdan-so-bilstm model |
publisher |
PeerJ |
publishDate |
2023 |
url |
http://dx.doi.org/10.7717/peerj.15748 https://peerj.com/articles/15748.pdf https://peerj.com/articles/15748.xml https://peerj.com/articles/15748.html |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
PeerJ volume 11, page e15748 ISSN 2167-8359 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.7717/peerj.15748 |
container_title |
PeerJ |
container_volume |
11 |
container_start_page |
e15748 |
_version_ |
1800738082480193536 |