Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches

González-Abad, Jose; Baño‐Medina, Jorge; Gutiérrez, José

doi:10.48550/arxiv.2302.01771

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 Let's examine how XAI methods yield statistical understanding in a detailed example. González-Abad et al (2023) use the saliency method to examine input-output mappings in three different convolutional neural nets (CNNs) which were trained and used to downscale climate data. They computed and produced accumulated saliency maps which account for "the overall importance of the different elements" of the input data for the model's prediction (p. 8).…”

Section: Post-hoc Xai In Climate Science and Statistical Understandingmentioning

confidence: 99%

Moving beyond post-hoc XAI: Lessons learned from dynamical climate modeling

O'Loughlin,

Li,

O'Brien

2024

Preprint

View full text Add to dashboard Cite

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 Perspective, 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 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, which is obtained when researchers can make sense of the modelling 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 of 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 behaviour. 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.

show abstract

Section: Post-hoc Xai In Climate Science and Statistical Understandingmentioning

confidence: 99%