Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches
-
Published:2023-11
Issue:11
Volume:15
Page:
-
ISSN:1942-2466
-
Container-title:Journal of Advances in Modeling Earth Systems
-
language:en
-
Short-container-title:J Adv Model Earth Syst
Author:
González‐Abad Jose1ORCID,
Baño‐Medina Jorge1ORCID,
Gutiérrez José Manuel1
Affiliation:
1. Instituto de Física de Cantabria (IFCA) CSIC—Universidad de Cantabria Santander Spain
Abstract
AbstractDeep learning (DL) has emerged as a promising tool to downscale climate projections at regional‐to‐local scales from large‐scale atmospheric fields following the perfect‐prognosis approach. Given their complexity, it is crucial to properly evaluate these methods, especially when applied to changing climatic conditions where the ability to extrapolate/generalize is key. In this work, we intercompare several DL models extracted from the literature for the same challenging use‐case (downscaling temperature in the CORDEX North America domain) and expand standard evaluation methods building on eXplainable Artificial Intelligence (XAI) techniques. Specifically, we introduce two novel XAI‐based diagnostics—Aggregated Saliency Map and Saliency Dispersion Maps—and show how they can be used to unravel the internal behavior of these models, aiding in their design and evaluation. This work advocates for the introduction of XAI techniques into deep downscaling evaluation frameworks, especially when working with large regions and/or under climate change conditions.
Funder
Agencia Estatal de Investigación
Consejo Superior de Investigaciones Científicas
Universidad de Cantabria
Publisher
American Geophysical Union (AGU)
Subject
General Earth and Planetary Sciences,Environmental Chemistry,Global and Planetary Change
Reference58 articles.
1. Abadi M. Agarwal A. Barham P. Brevdo E. Chen Z. Citro C. et al. (2015).TensorFlow: Large‐scale machine learning on heterogeneous systems. (Software available from tensorflow.org) Retrieved fromhttps://www.tensorflow.org/
2. Innvestigate neural networks;Alber M.;Journal of Machine Learning Research,2019
3. Understanding Deep Learning Decisions in Statistical Downscaling Models
4. Downscaling multi‐model climate projection ensembles with deep learning (DeepESD): Contribution to CORDEX EUR‐44;Baño‐Medina J.;Geoscientific Model Development Discussions,2022
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献