Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice
Accurate and fast prediction of sea ice conditions is the foundation of safety guarantee for Arctic navigation. Aiming at the imperious demand of short-term prediction for sea ice, we develop a new data-driven prediction technique for the sea ice concentration (SIC) combined with causal analysis. Th...
Published in: | Frontiers in Marine Science |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Frontiers Media S.A.
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3389/fmars.2021.649378 https://doaj.org/article/3ff3f8cd65b44c039dd4de82166a9dd0 |
id |
ftdoajarticles:oai:doaj.org/article:3ff3f8cd65b44c039dd4de82166a9dd0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:3ff3f8cd65b44c039dd4de82166a9dd0 2023-05-15T14:54:20+02:00 Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice Ming Li Ren Zhang Kefeng Liu 2021-05-01T00:00:00Z https://doi.org/10.3389/fmars.2021.649378 https://doaj.org/article/3ff3f8cd65b44c039dd4de82166a9dd0 EN eng Frontiers Media S.A. https://www.frontiersin.org/articles/10.3389/fmars.2021.649378/full https://doaj.org/toc/2296-7745 2296-7745 doi:10.3389/fmars.2021.649378 https://doaj.org/article/3ff3f8cd65b44c039dd4de82166a9dd0 Frontiers in Marine Science, Vol 8 (2021) Arctic sea ice machine learning causal analysis prediction short-term variation Science Q General. Including nature conservation geographical distribution QH1-199.5 article 2021 ftdoajarticles https://doi.org/10.3389/fmars.2021.649378 2022-12-31T12:29:43Z Accurate and fast prediction of sea ice conditions is the foundation of safety guarantee for Arctic navigation. Aiming at the imperious demand of short-term prediction for sea ice, we develop a new data-driven prediction technique for the sea ice concentration (SIC) combined with causal analysis. Through the causal analysis based on kernel Granger causality (KGC) test, key environmental factors affecting SIC are selected. Then multiple popular machine learning (ML) algorithms, namely self-adaptive differential extreme learning machine (SaD-ELM), classification and regression tree (CART), random forest (RF) and support vector regression (SVR), are employed to predict daily SIC, respectively. The experimental results in the Barents-Kara (B-K) sea show: (1) compared with correlation analysis, the input variables of ML models screened out by causal analysis achieve better prediction; (2) when lead time is short (<3 d), the four ML algorithms are all suitable for short-term prediction of daily SIC, while RF and SaD-ELM have better prediction performance with long lead time (>3 d); (3) RF has the best prediction accuracy and generalization ability but hugely time consuming, while SaD-ELM achieves more favorable performance when taking computational complexity into consideration. In summary, ML is applicable to short-term prediction of daily SIC, which develops a new way of sea ice prediction and provides technical support for Arctic navigation. Article in Journal/Newspaper Arctic Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Frontiers in Marine Science 8 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Arctic sea ice machine learning causal analysis prediction short-term variation Science Q General. Including nature conservation geographical distribution QH1-199.5 |
spellingShingle |
Arctic sea ice machine learning causal analysis prediction short-term variation Science Q General. Including nature conservation geographical distribution QH1-199.5 Ming Li Ren Zhang Kefeng Liu Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
topic_facet |
Arctic sea ice machine learning causal analysis prediction short-term variation Science Q General. Including nature conservation geographical distribution QH1-199.5 |
description |
Accurate and fast prediction of sea ice conditions is the foundation of safety guarantee for Arctic navigation. Aiming at the imperious demand of short-term prediction for sea ice, we develop a new data-driven prediction technique for the sea ice concentration (SIC) combined with causal analysis. Through the causal analysis based on kernel Granger causality (KGC) test, key environmental factors affecting SIC are selected. Then multiple popular machine learning (ML) algorithms, namely self-adaptive differential extreme learning machine (SaD-ELM), classification and regression tree (CART), random forest (RF) and support vector regression (SVR), are employed to predict daily SIC, respectively. The experimental results in the Barents-Kara (B-K) sea show: (1) compared with correlation analysis, the input variables of ML models screened out by causal analysis achieve better prediction; (2) when lead time is short (<3 d), the four ML algorithms are all suitable for short-term prediction of daily SIC, while RF and SaD-ELM have better prediction performance with long lead time (>3 d); (3) RF has the best prediction accuracy and generalization ability but hugely time consuming, while SaD-ELM achieves more favorable performance when taking computational complexity into consideration. In summary, ML is applicable to short-term prediction of daily SIC, which develops a new way of sea ice prediction and provides technical support for Arctic navigation. |
format |
Article in Journal/Newspaper |
author |
Ming Li Ren Zhang Kefeng Liu |
author_facet |
Ming Li Ren Zhang Kefeng Liu |
author_sort |
Ming Li |
title |
Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
title_short |
Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
title_full |
Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
title_fullStr |
Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
title_full_unstemmed |
Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice |
title_sort |
machine learning incorporated with causal analysis for short-term prediction of sea ice |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doi.org/10.3389/fmars.2021.649378 https://doaj.org/article/3ff3f8cd65b44c039dd4de82166a9dd0 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Frontiers in Marine Science, Vol 8 (2021) |
op_relation |
https://www.frontiersin.org/articles/10.3389/fmars.2021.649378/full https://doaj.org/toc/2296-7745 2296-7745 doi:10.3389/fmars.2021.649378 https://doaj.org/article/3ff3f8cd65b44c039dd4de82166a9dd0 |
op_doi |
https://doi.org/10.3389/fmars.2021.649378 |
container_title |
Frontiers in Marine Science |
container_volume |
8 |
_version_ |
1766326051765485568 |