Abstract

Monitoring continuous volcano-seismic signals is often performed by systems trained on scarce or incomplete datasets. From a machine learning perspective, these types of systems are typically built by learning from seismic records containing information not only on the volcanic dynamics, but also on the complex inner structure of the volcanic edifice. The dual nature of the information content presents a challenge when it comes to modeling events temporally. Here, we show that while existing recurrent-neural-network-based monitoring systems recognize almost 90% of events annotated in seismic catalogs, the long-range temporal dependencies are still hard to model. We found that dilated recurrent neural networks based on multiresolution dilated recurrent skip connections between layers have the remarkable capability to simultaneously enhance the efficiency of the model, reducing the number of training parameters, while increasing the performance of the model when compared with classical recurrent neural networks in sequence modeling tasks involving very long-term seismic records. Our results offer the potential to increase the reliability of monitoring tools despite the variations in the geophysical properties of the seismic events within the volcano across eruptive periods.