Identification

Title

Moving beyond post hoc explainable artificial intelligence: A perspective paper on lessons learned from dynamical climate modeling

Abstract

AI models are criticized as being black boxes, potentially subjecting climate science to greater uncertainty. Explainable artificial intelligence (XAI) has been proposed to probe AI models and increase trust. In this review and perspective paper, we suggest that, in addition to using XAI methods, AI researchers in climate science can learn from past successes in the development of physics-based dynamical climate models. Dynamical models are complex but have gained trust because their successes and failures can sometimes be attributed to specific components or sub-models, such as when model bias is explained by pointing to a particular parameterization. We propose three types of understanding as a basis to evaluate trust in dynamical and AI models alike: (1) instrumental understanding, which is obtained when a model has passed a functional test; (2) statistical understanding, obtained when researchers can make sense of the modeling results using statistical techniques to identify input–output relationships; and (3) component-level understanding, which refers to modelers' ability to point to specific model components or parts in the model architecture as the culprit for erratic model behaviors or as the crucial reason why the model functions well. We demonstrate how component-level understanding has been sought and achieved via climate model intercomparison projects over the past several decades. Such component-level understanding routinely leads to model improvements and may also serve as a template for thinking about AI-driven climate science. Currently, XAI methods can help explain the behaviors of AI models by focusing on the mapping between input and output, thereby increasing the statistical understanding of AI models. Yet, to further increase our understanding of AI models, we will have to build AI models that have interpretable components amenable to component-level understanding. We give recent examples from the AI climate science literature to highlight some recent, albeit limited, successes in achieving component-level understanding and thereby explaining model behavior. The merit of such interpretable AI models is that they serve as a stronger basis for trust in climate modeling and, by extension, downstream uses of climate model data.

Resource type

document

Resource locator

Unique resource identifier

code

https://n2t.net/ark:/85065/d7v410k8

codeSpace

Dataset language

eng

Spatial reference system

code identifying the spatial reference system

Classification of spatial data and services

Topic category

geoscientificInformation

Keywords

Keyword set

keyword value

Text

originating controlled vocabulary

title

Resource Type

reference date

date type

publication

effective date

2016-01-01T00:00:00Z

Geographic location

West bounding longitude

East bounding longitude

North bounding latitude

South bounding latitude

Temporal reference

Temporal extent

Begin position

End position

Dataset reference date

date type

publication

effective date

2025-02-11T00:00:00Z

Frequency of update

Quality and validity

Lineage

Conformity

Data format

name of format

version of format

Constraints related to access and use

Constraint set

Use constraints

<span style="font-family:Arial;font-size:10pt;font-style:normal;" data-sheets-root="1">Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</span>

Limitations on public access

None

Responsible organisations

Responsible party

contact position

OpenSky Support

organisation name

UCAR/NCAR - Library

full postal address

PO Box 3000

Boulder

80307-3000

email address

opensky@ucar.edu

web address

http://opensky.ucar.edu/

name: homepage

responsible party role

pointOfContact

Metadata on metadata

Metadata point of contact