Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey

TL;DR

This survey reviews existing explainable AI methods for time series data, highlighting their types, applications, and impact on trust, addressing a gap compared to other domains like vision and NLP.

Contribution

It provides a comprehensive overview of XAI techniques for time series, emphasizing their importance and current state of research in this specific domain.

Findings

Most XAI methods for time series are adapted from other fields.

Explainability enhances trust and confidence in AI systems.

The survey identifies gaps and future directions in time series XAI.

Abstract

Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations they produce. We also provide a reflection on the impact of these explanation methods to provide confidence and trust in the AI systems.