This paper introduces recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU) to detect and classify continuous sequences of volcano-seismic events at the Deception Island Volcano, Antarctica. A representative data set containing volcano-tectonic earthquakes, long-period events, volcanic tremors, and hybrid events was used to train these models. Experimental results show that RNN, LSTM, and GRU can exploit temporal and frequency information from continuous seismic data, attaining close to 90%, 94%, and 92% events correctly detected and classified. A second experiment is presented in this paper. The architectures described above, trained with data from campaigns of seismic records obtained in 1995-2002, have been tested with data from the recent seismic survey performed at the Deception Island Volcano in 2016-2017 by the Spanish Antarctic scientific campaign. Despite the variations in the geophysical properties of the seismic events within the volcano across eruptive periods, results provide good generalization accuracy. This result expands the possibilities of RNNs for real-time monitoring of volcanic activity, even if seismic sources change over time.

Deep neural networks (DNNs) could help to identify the internal sources of volcano-seismic events. However, direct applications of DNNs are challenging, given the multiple seismic sources and the small size of available datasets. In this paper, we propose a novel approach in the field of volcano seismology to classify volcano-seismic events based on fully connected DNNs. Two DNN architectures with different weights scheme initialization are studied: stacked denoising autoencoders and deep belief networks. Using a combined feature vector of linear prediction coefficients and statistical properties, we evaluate classification performance on seven different classes of isolated seismic events. These proposed architectures are compared to multilayer perceptron, support vector machine, and random forest. Experimental results show that DNNs can efficiently capture complex relationships of volcano-seismic data and achieve better classification performance with faster convergence when compared to classical models.

After more than a year of unrest, a small effusive eruption commenced in Fagradalsfjall, Iceland, on 19 March 2021. The eruption lasted six months. The first six weeks were characterized by multiple fissure openings, and the remainder was dominated by effusive activity from a single crater. During the eruption, lava and low-level gases propagated over the complex terrain: a hyaloclastite massif with mountain peaks up to about 350 m asl with valleys in between. The area is uninhabited, but easily accessible at about 30 km distance from Reykjavík. While the eruption was ongoing, more than 356,000 tourists visited the eruptive site. To maintain low risk access to the area, it was critical to monitor the eruption (including opening of new fissures) in real-time, forecast the transport of gas and lava flow emplacement, and assess the evolving hazards. In addition to data accessibility and interpretation, managing this volcanic crisis was possible thanks to strong collaboration between the scientific institutions and civil protection agencies. The eruption presented an opportunity to tune, test and validate a variety of numerical models for hazard assessment as well as to refine and improve the delivery of information to the general public, communities living near the eruption site and decision makers. The monitoring team worked long hours during both the pre- and syn-eruptive phases for identifying low risk access areas to the eruption site and to provide a regular flow of information. This paper reviews the eruption and its associated hazards. It also provides an overview of the monitoring setup, the adopted numerical tools and communication materials disseminated to the general public regarding current exclusion zones, hazards and possible future eruptive scenarios.

Domain-specific problems where data collection is an expensive task are often represented by scarce or incomplete data. From a machine learning perspective, this type of problems has been addressed using models trained in different specific domains as the starting point for the final objective-model. The transfer of knowledge between domains, known as transfer learning (TL), helps to speed up training and improve the performance of the models in problems with limited amounts of data. In this letter, we introduce a TL approach to classify isolated volcano-seismic signals at ``Volcán de Fuego'', Colima (Mexico). Using the well-known convolutional architecture (LeNet) as a feature extractor and a representative data set containing regional earthquakes, volcano-tectonic earthquakes, long-period events, volcanic tremors, explosions, and collapses, our proposal compares the generalization capabilities of the models when we only fine-tune the upper layers and fine-tune overall of them. Compared with the other state-of-the-art techniques, classification systems based on TL approaches provide good generalization capabilities (attaining nearly 94% of events correctly classified) and decreasing computational time resources.

Understanding how deep hierarchical models build their knowledge is a key issue in the usage of artificial intelligence to interpret the reality behind data. Depending on the discipline and models used, such knowledge may be represented in ways that are more or less intelligible for humans, limiting further improvements on the performance of the existing models. In order to delve into the characterization and modeling of volcano-seismic signals, this article emphasizes the idea of deciphering what and how recurrent neural networks (RNNs) model, and how this knowledge can be used to improve data interpretation. The key to accomplishing these objectives is both analyzing the hidden state dynamics associated with their hidden units as well as pruning/trimming based on the specialization of neurons. In this article, we process, analyze, and visualize the hidden states activation maps of two RNN architectures when managing different types of volcano-seismic events. As a result, the class-dependent discriminative behavior of most active neurons is analyzed, thereby increasing the comprehension of the detection and classification tasks. A representative dataset from the deception island volcano (Antarctica), containing volcano-tectonic earthquakes, long period events, volcanic tremors, and hybrid events, is used to train the models. Experimental analysis shows how neural activity and its associated specialization skills change depending on the architecture chosen and the type of event analyzed.