Layer-wise Relevance Propagation for Echo State Networks applied to Earth System Variability

TL;DR

This paper demonstrates how layer-wise relevance propagation (LRP) can be applied to echo state networks (ESNs) to improve their interpretability, especially in climate-related time series prediction like El Nino detection.

Contribution

It introduces a method to apply LRP to ESNs, making their decision processes more transparent in time series and image classification tasks.

Findings

LRP effectively explains ESN decisions in climate data

ESNs can be used for both time series prediction and image classification

Enhanced interpretability of ESNs in Earth system variability analysis

Abstract

Artificial neural networks (ANNs) are known to be powerful methods for many hard problems (e.g. image classification, speech recognition or time series prediction). However, these models tend to produce black-box results and are often difficult to interpret. Layer-wise relevance propagation (LRP) is a widely used technique to understand how ANN models come to their conclusion and to understand what a model has learned. Here, we focus on Echo State Networks (ESNs) as a certain type of recurrent neural networks, also known as reservoir computing. ESNs are easy to train and only require a small number of trainable parameters, but are still black-box models. We show how LRP can be applied to ESNs in order to open the black-box. We also show how ESNs can be used not only for time series prediction but also for image classification: Our ESN model serves as a detector for El Nino Southern Oscillation (ENSO) from sea surface temperature anomalies. ENSO is actually a well-known problem and has been extensively discussed before. But here we use this simple problem to demonstrate how LRP can significantly enhance the explainablility of ESNs.