Deep Convolutional Autoencoders as Generic Feature Extractors in Seismological Applications

TL;DR

This paper evaluates the effectiveness of deep autoencoders as feature extractors in seismological applications, finding they perform well under specific conditions like limited data and certain model structures.

Contribution

It systematically tests autoencoders as generic feature extractors for seismic event classification, highlighting conditions where they outperform traditional models.

Findings

Autoencoder features improve classification when data is limited.

Overcomplete autoencoders with convolutional layers perform best.

Performance depends on model structure and training strategies.

Abstract

The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms, and phase picking). These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only perform well under certain conditions such as when the target problems require features to be similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.