Prototype-Based Methods in Explainable AI and Emerging Opportunities in the Geosciences

TL;DR

This paper reviews the development and application of prototype-based explainable AI methods, emphasizing their potential and challenges in geosciences, and discusses how these methods can be adapted for scientific learning tasks.

Contribution

It provides a structured overview of prototype-based XAI methods, highlighting their applications, limitations, and opportunities specifically within geosciences.

Findings

Prototype-based XAI methods enhance interpretability in geosciences.

Differences between geoscientific data and standard benchmarks affect method adaptation.

Challenges include data heterogeneity and visualization of prototypes.

Abstract

Prototype-based methods are intrinsically interpretable XAI methods that produce predictions and explanations by comparing input data with a set of learned prototypical examples that are representative of the training data. In this work, we discuss a series of developments in the field of prototype-based XAI that show potential for scientific learning tasks, with a focus on the geosciences. We organize the prototype-based XAI literature into three themes: the development and visualization of prototypes, types of prototypes, and the use of prototypes in various learning tasks. We discuss how the authors use prototype-based methods, their novel contributions, and any limitations or challenges that may arise when adapting these methods for geoscientific learning tasks. We highlight differences between geoscientific data sets and the standard benchmarks used to develop XAI methods, and discuss how specific geoscientific applications may benefit from using or modifying existing prototype-based XAI techniques.