English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning (DL) has emerged as a promising tool to downscale climateprojections at regional-to-local scales from large-scale atmospheric fieldsfollowing the perfect-prognosis (PP) approach. Given their complexity, it iscrucial to properly evaluate these methods, especially when applied to changingclimatic conditions where the ability to extrapolate/generalise is key. In thiswork, we intercompare several DL models extracted from the literature for thesame challenging use-case (downscaling temperature in the CORDEX North Americadomain) and expand standard evaluation methods building on eXplainableartifical intelligence (XAI) techniques. We show how these techniques can beused to unravel the internal behaviour of these models, providing newevaluation dimensions and aiding in their diagnostic and design. These resultsshow the usefulness of incorporating XAI techniques into statisticaldownscaling evaluation frameworks, especially when working with large regionsand/or under climate change conditions.

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