Layer-wise Relevance Propagation for Echo State Networks applied to Earth System Variability
This work addresses the interpretability issue in ESNs for researchers and practitioners in Earth system science, but it is incremental as it adapts an existing method (LRP) to a specific network type.
The authors tackled the problem of interpreting black-box Echo State Networks (ESNs) by applying Layer-wise Relevance Propagation (LRP) to enhance explainability, demonstrating its effectiveness on time series prediction and image classification tasks, specifically for detecting El Nino Southern Oscillation (ENSO) from sea surface temperature anomalies.
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.