Using feature importance as an exploratory data analysis tool on Earth system models
<p>Machine learning (ML) models are commonly used to generate predictions, but these models can also support the discovery of new science. Generating accurate predictions necessitates that a model captures the structure of the underlying data. If the structure is properly extracted, ML could b...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-02-01
|
| Series: | Geoscientific Model Development |
| Online Access: | https://gmd.copernicus.org/articles/18/1041/2025/gmd-18-1041-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849716035959128064 |
|---|---|
| author | D. Ries K. Goode K. McClernon B. Hillman |
| author_facet | D. Ries K. Goode K. McClernon B. Hillman |
| author_sort | D. Ries |
| collection | DOAJ |
| description | <p>Machine learning (ML) models are commonly used to generate predictions, but these models can also support the discovery of new science. Generating accurate predictions necessitates that a model captures the structure of the underlying data. If the structure is properly extracted, ML could be a useful exploratory and evidential tool. In this paper, we present a case study that demonstrates the use of ML for exploratory data analysis (EDA) in the climate space. We apply the ML explainability method of spatiotemporal zeroed feature importance (stZFI) to understand how climate-variable associations evolve over space and time. Our analyses focus on data from ensembles of Earth system models (ESMs) which provide data on different climate states and conditions. We elect to work with ESM ensembles since they allow us to compare feature importance across alternative scenarios not available with observed data. The ensembles also account for natural variability so that we can distinguish between signal and noise due to natural climate variability when computing feature importance. The use of perturbed initial condition ensembles introduces variability mimicking the natural variability in the atmosphere; thus the signals emerging using feature importance (FI) can be evaluated against the natural variability in the climate system. For our analyses, we consider the 1991 volcanic eruption of Mount Pinatubo, which was a large stratospheric aerosol injection. We explore the climate pathway associated with the eruption from aerosols to radiation to temperature at both the near-surface and stratospheric levels. In addition to applying the method to data generated from two different ESMs, we apply stZFI to reanalysis data to compare the associations identified by stZFI. We show how stZFI tracks the importance of aerosol optical depth over time on forecasting temperatures. This case study illustrates usefulness of an ML tool (stZFI) for EDA on a well-studied climate exemplar.</p> |
| format | Article |
| id | doaj-art-c5e73cf7f04f430b8b3f0bd97eeaaa63 |
| institution | DOAJ |
| issn | 1991-959X 1991-9603 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Geoscientific Model Development |
| spelling | doaj-art-c5e73cf7f04f430b8b3f0bd97eeaaa632025-08-20T03:13:08ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032025-02-01181041106510.5194/gmd-18-1041-2025Using feature importance as an exploratory data analysis tool on Earth system modelsD. Ries0K. Goode1K. McClernon2B. Hillman3Sandia National Laboratories, Albuquerque, NM, United States of AmericaSandia National Laboratories, Albuquerque, NM, United States of AmericaSandia National Laboratories, Albuquerque, NM, United States of AmericaSandia National Laboratories, Albuquerque, NM, United States of America<p>Machine learning (ML) models are commonly used to generate predictions, but these models can also support the discovery of new science. Generating accurate predictions necessitates that a model captures the structure of the underlying data. If the structure is properly extracted, ML could be a useful exploratory and evidential tool. In this paper, we present a case study that demonstrates the use of ML for exploratory data analysis (EDA) in the climate space. We apply the ML explainability method of spatiotemporal zeroed feature importance (stZFI) to understand how climate-variable associations evolve over space and time. Our analyses focus on data from ensembles of Earth system models (ESMs) which provide data on different climate states and conditions. We elect to work with ESM ensembles since they allow us to compare feature importance across alternative scenarios not available with observed data. The ensembles also account for natural variability so that we can distinguish between signal and noise due to natural climate variability when computing feature importance. The use of perturbed initial condition ensembles introduces variability mimicking the natural variability in the atmosphere; thus the signals emerging using feature importance (FI) can be evaluated against the natural variability in the climate system. For our analyses, we consider the 1991 volcanic eruption of Mount Pinatubo, which was a large stratospheric aerosol injection. We explore the climate pathway associated with the eruption from aerosols to radiation to temperature at both the near-surface and stratospheric levels. In addition to applying the method to data generated from two different ESMs, we apply stZFI to reanalysis data to compare the associations identified by stZFI. We show how stZFI tracks the importance of aerosol optical depth over time on forecasting temperatures. This case study illustrates usefulness of an ML tool (stZFI) for EDA on a well-studied climate exemplar.</p>https://gmd.copernicus.org/articles/18/1041/2025/gmd-18-1041-2025.pdf |
| spellingShingle | D. Ries K. Goode K. McClernon B. Hillman Using feature importance as an exploratory data analysis tool on Earth system models Geoscientific Model Development |
| title | Using feature importance as an exploratory data analysis tool on Earth system models |
| title_full | Using feature importance as an exploratory data analysis tool on Earth system models |
| title_fullStr | Using feature importance as an exploratory data analysis tool on Earth system models |
| title_full_unstemmed | Using feature importance as an exploratory data analysis tool on Earth system models |
| title_short | Using feature importance as an exploratory data analysis tool on Earth system models |
| title_sort | using feature importance as an exploratory data analysis tool on earth system models |
| url | https://gmd.copernicus.org/articles/18/1041/2025/gmd-18-1041-2025.pdf |
| work_keys_str_mv | AT dries usingfeatureimportanceasanexploratorydataanalysistoolonearthsystemmodels AT kgoode usingfeatureimportanceasanexploratorydataanalysistoolonearthsystemmodels AT kmcclernon usingfeatureimportanceasanexploratorydataanalysistoolonearthsystemmodels AT bhillman usingfeatureimportanceasanexploratorydataanalysistoolonearthsystemmodels |