Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere
The Arctic sea ice has retreated rapidly in the past few decades, which is believed to be driven by various dynamic and thermodynamic processes in the atmosphere. The newly open water resulted from sea ice decline in turn exerts large influence on the atmosphere. Therefore, this study aims to invest...
Published in: | Frontiers in Big Data |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Frontiers Media S.A.
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3389/fdata.2021.642182 https://doaj.org/article/a3fdc26b53f34223b8d8672dcf28a1b2 |
id |
ftdoajarticles:oai:doaj.org/article:a3fdc26b53f34223b8d8672dcf28a1b2 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:a3fdc26b53f34223b8d8672dcf28a1b2 2023-05-15T14:52:59+02:00 Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere Yiyi Huang Matthäus Kleindessner Alexey Munishkin Debvrat Varshney Pei Guo Jianwu Wang 2021-08-01T00:00:00Z https://doi.org/10.3389/fdata.2021.642182 https://doaj.org/article/a3fdc26b53f34223b8d8672dcf28a1b2 EN eng Frontiers Media S.A. https://www.frontiersin.org/articles/10.3389/fdata.2021.642182/full https://doaj.org/toc/2624-909X 2624-909X doi:10.3389/fdata.2021.642182 https://doaj.org/article/a3fdc26b53f34223b8d8672dcf28a1b2 Frontiers in Big Data, Vol 4 (2021) causality discovery time series arctic sea ice temporal causality discovery framework non-combinatorial optimization via trace exponential and augmented lagrangian for structure learning directed acyclic graph-graph neural networks Information technology T58.5-58.64 article 2021 ftdoajarticles https://doi.org/10.3389/fdata.2021.642182 2022-12-31T13:02:06Z The Arctic sea ice has retreated rapidly in the past few decades, which is believed to be driven by various dynamic and thermodynamic processes in the atmosphere. The newly open water resulted from sea ice decline in turn exerts large influence on the atmosphere. Therefore, this study aims to investigate the causality between multiple atmospheric processes and sea ice variations using three distinct data-driven causality approaches that have been proposed recently: Temporal Causality Discovery Framework Non-combinatorial Optimization via Trace Exponential and Augmented lagrangian for Structure learning (NOTEARS) and Directed Acyclic Graph-Graph Neural Networks (DAG-GNN). We apply these three algorithms to 39 years of historical time-series data sets, which include 11 atmospheric variables from ERA-5 reanalysis product and passive microwave satellite retrieved sea ice extent. By comparing the causality graph results of these approaches with what we summarized from the literature, it shows that the static graphs produced by NOTEARS and DAG-GNN are relatively reasonable. The results from NOTEARS indicate that relative humidity and precipitation dominate sea ice changes among all variables, while the results from DAG-GNN suggest that the horizontal and meridional wind are more important for driving sea ice variations. However, both approaches produce some unrealistic cause-effect relationships. Additionally, these three methods cannot well detect the delayed impact of one variable on another in the Arctic. It also turns out that the results are rather sensitive to the choice of hyperparameters of the three methods. As a pioneer study, this work paves the way to disentangle the complex causal relationships in the Earth system, by taking the advantage of cutting-edge Artificial Intelligence technologies. Article in Journal/Newspaper Arctic Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Frontiers in Big Data 4 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
causality discovery time series arctic sea ice temporal causality discovery framework non-combinatorial optimization via trace exponential and augmented lagrangian for structure learning directed acyclic graph-graph neural networks Information technology T58.5-58.64 |
spellingShingle |
causality discovery time series arctic sea ice temporal causality discovery framework non-combinatorial optimization via trace exponential and augmented lagrangian for structure learning directed acyclic graph-graph neural networks Information technology T58.5-58.64 Yiyi Huang Matthäus Kleindessner Alexey Munishkin Debvrat Varshney Pei Guo Jianwu Wang Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
topic_facet |
causality discovery time series arctic sea ice temporal causality discovery framework non-combinatorial optimization via trace exponential and augmented lagrangian for structure learning directed acyclic graph-graph neural networks Information technology T58.5-58.64 |
description |
The Arctic sea ice has retreated rapidly in the past few decades, which is believed to be driven by various dynamic and thermodynamic processes in the atmosphere. The newly open water resulted from sea ice decline in turn exerts large influence on the atmosphere. Therefore, this study aims to investigate the causality between multiple atmospheric processes and sea ice variations using three distinct data-driven causality approaches that have been proposed recently: Temporal Causality Discovery Framework Non-combinatorial Optimization via Trace Exponential and Augmented lagrangian for Structure learning (NOTEARS) and Directed Acyclic Graph-Graph Neural Networks (DAG-GNN). We apply these three algorithms to 39 years of historical time-series data sets, which include 11 atmospheric variables from ERA-5 reanalysis product and passive microwave satellite retrieved sea ice extent. By comparing the causality graph results of these approaches with what we summarized from the literature, it shows that the static graphs produced by NOTEARS and DAG-GNN are relatively reasonable. The results from NOTEARS indicate that relative humidity and precipitation dominate sea ice changes among all variables, while the results from DAG-GNN suggest that the horizontal and meridional wind are more important for driving sea ice variations. However, both approaches produce some unrealistic cause-effect relationships. Additionally, these three methods cannot well detect the delayed impact of one variable on another in the Arctic. It also turns out that the results are rather sensitive to the choice of hyperparameters of the three methods. As a pioneer study, this work paves the way to disentangle the complex causal relationships in the Earth system, by taking the advantage of cutting-edge Artificial Intelligence technologies. |
format |
Article in Journal/Newspaper |
author |
Yiyi Huang Matthäus Kleindessner Alexey Munishkin Debvrat Varshney Pei Guo Jianwu Wang |
author_facet |
Yiyi Huang Matthäus Kleindessner Alexey Munishkin Debvrat Varshney Pei Guo Jianwu Wang |
author_sort |
Yiyi Huang |
title |
Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
title_short |
Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
title_full |
Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
title_fullStr |
Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
title_full_unstemmed |
Benchmarking of Data-Driven Causality Discovery Approaches in the Interactions of Arctic Sea Ice and Atmosphere |
title_sort |
benchmarking of data-driven causality discovery approaches in the interactions of arctic sea ice and atmosphere |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doi.org/10.3389/fdata.2021.642182 https://doaj.org/article/a3fdc26b53f34223b8d8672dcf28a1b2 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Frontiers in Big Data, Vol 4 (2021) |
op_relation |
https://www.frontiersin.org/articles/10.3389/fdata.2021.642182/full https://doaj.org/toc/2624-909X 2624-909X doi:10.3389/fdata.2021.642182 https://doaj.org/article/a3fdc26b53f34223b8d8672dcf28a1b2 |
op_doi |
https://doi.org/10.3389/fdata.2021.642182 |
container_title |
Frontiers in Big Data |
container_volume |
4 |
_version_ |
1766324394405134336 |