Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory
The well-documented decrease in the annual minimum Arctic sea ice extent over the past few decades is an alarming indicator of current climate change. However, much less is known about the thickness of the Arctic sea ice. Developing accurate forecasting models is critical to better predict its chang...
Published in: | Geosciences |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/geosciences13120370 https://doaj.org/article/5f6a0241f1c64dd6a7afd35dd7d60cb6 |
id |
ftdoajarticles:oai:doaj.org/article:5f6a0241f1c64dd6a7afd35dd7d60cb6 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:5f6a0241f1c64dd6a7afd35dd7d60cb6 2024-01-21T10:03:02+01:00 Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory Aymane Ahajjam Jaakko Putkonen Timothy J. Pasch Xun Zhu 2023-11-01T00:00:00Z https://doi.org/10.3390/geosciences13120370 https://doaj.org/article/5f6a0241f1c64dd6a7afd35dd7d60cb6 EN eng MDPI AG https://www.mdpi.com/2076-3263/13/12/370 https://doaj.org/toc/2076-3263 doi:10.3390/geosciences13120370 2076-3263 https://doaj.org/article/5f6a0241f1c64dd6a7afd35dd7d60cb6 Geosciences, Vol 13, Iss 12, p 370 (2023) pan-Arctic sea ice volume forecasting multi-horizon forecasting time-series forecasting short-term forecasting mid-term forecasting deep learning Geology QE1-996.5 article 2023 ftdoajarticles https://doi.org/10.3390/geosciences13120370 2023-12-24T01:37:15Z The well-documented decrease in the annual minimum Arctic sea ice extent over the past few decades is an alarming indicator of current climate change. However, much less is known about the thickness of the Arctic sea ice. Developing accurate forecasting models is critical to better predict its changes and monitor the impacts of global warming on the total Arctic sea ice volume (SIV). Significant improvements in forecasting performance are possible with the advances in signal processing and deep learning. Accordingly, here, we set out to utilize the recent advances in machine learning to develop non-physics-based techniques for forecasting the sea ice volume with low computational costs. In particular, this paper aims to provide a step-wise decision process required to develop a more accurate forecasting model over short- and mid-term horizons. This work integrates variational mode decomposition (VMD) and bidirectional long short-term memory (BiLSTM) for multi-input multi-output pan-Arctic SIV forecasting. Different experiments are conducted to identify the impact of several aspects, including multivariate inputs, signal decomposition, and deep learning, on forecasting performance. The empirical results indicate that (i) the proposed hybrid model is consistently effective in time-series processing and forecasting, with average improvements of up to 60% compared with the case of no decomposition and over 40% compared with other deep learning models in both forecasting horizons and seasons; (ii) the optimization of the VMD level is essential for optimal performance; and (iii) the use of the proposed technique with a divide-and-conquer strategy demonstrates superior forecasting performance. Article in Journal/Newspaper Arctic Climate change Global warming Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Geosciences 13 12 370 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
pan-Arctic sea ice volume forecasting multi-horizon forecasting time-series forecasting short-term forecasting mid-term forecasting deep learning Geology QE1-996.5 |
spellingShingle |
pan-Arctic sea ice volume forecasting multi-horizon forecasting time-series forecasting short-term forecasting mid-term forecasting deep learning Geology QE1-996.5 Aymane Ahajjam Jaakko Putkonen Timothy J. Pasch Xun Zhu Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
topic_facet |
pan-Arctic sea ice volume forecasting multi-horizon forecasting time-series forecasting short-term forecasting mid-term forecasting deep learning Geology QE1-996.5 |
description |
The well-documented decrease in the annual minimum Arctic sea ice extent over the past few decades is an alarming indicator of current climate change. However, much less is known about the thickness of the Arctic sea ice. Developing accurate forecasting models is critical to better predict its changes and monitor the impacts of global warming on the total Arctic sea ice volume (SIV). Significant improvements in forecasting performance are possible with the advances in signal processing and deep learning. Accordingly, here, we set out to utilize the recent advances in machine learning to develop non-physics-based techniques for forecasting the sea ice volume with low computational costs. In particular, this paper aims to provide a step-wise decision process required to develop a more accurate forecasting model over short- and mid-term horizons. This work integrates variational mode decomposition (VMD) and bidirectional long short-term memory (BiLSTM) for multi-input multi-output pan-Arctic SIV forecasting. Different experiments are conducted to identify the impact of several aspects, including multivariate inputs, signal decomposition, and deep learning, on forecasting performance. The empirical results indicate that (i) the proposed hybrid model is consistently effective in time-series processing and forecasting, with average improvements of up to 60% compared with the case of no decomposition and over 40% compared with other deep learning models in both forecasting horizons and seasons; (ii) the optimization of the VMD level is essential for optimal performance; and (iii) the use of the proposed technique with a divide-and-conquer strategy demonstrates superior forecasting performance. |
format |
Article in Journal/Newspaper |
author |
Aymane Ahajjam Jaakko Putkonen Timothy J. Pasch Xun Zhu |
author_facet |
Aymane Ahajjam Jaakko Putkonen Timothy J. Pasch Xun Zhu |
author_sort |
Aymane Ahajjam |
title |
Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
title_short |
Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
title_full |
Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
title_fullStr |
Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
title_full_unstemmed |
Short- and Mid-Term Forecasting of Pan-Arctic Sea Ice Volume Using Variational Mode Decomposition and Bidirectional Long Short-Term Memory |
title_sort |
short- and mid-term forecasting of pan-arctic sea ice volume using variational mode decomposition and bidirectional long short-term memory |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/geosciences13120370 https://doaj.org/article/5f6a0241f1c64dd6a7afd35dd7d60cb6 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Global warming Sea ice |
genre_facet |
Arctic Climate change Global warming Sea ice |
op_source |
Geosciences, Vol 13, Iss 12, p 370 (2023) |
op_relation |
https://www.mdpi.com/2076-3263/13/12/370 https://doaj.org/toc/2076-3263 doi:10.3390/geosciences13120370 2076-3263 https://doaj.org/article/5f6a0241f1c64dd6a7afd35dd7d60cb6 |
op_doi |
https://doi.org/10.3390/geosciences13120370 |
container_title |
Geosciences |
container_volume |
13 |
container_issue |
12 |
container_start_page |
370 |
_version_ |
1788693299514572800 |