Monitoring Of Volcanic Activity Research Articles

Tracing Magma Migration at Mt. Etna Volcano during 2006–2020, Coupling Remote Sensing of Crater Gas Emissions and Ground Measurement of Soil Gases

The geochemical monitoring of volcanic activity today relies largely on remote sensing, but the combination of this approach together with soil gas monitoring, using the appropriate parameters, is still not widely used. The main purpose of this study was to correlate data from crater gas emissions with flank emissions of soil gases at Mt. Etna volcano from June 2006 to December 2020. Crater SO2 fluxes were measured from fixed stations around the volcano using the DOAS technique and applying a modeled clear-sky spectrum. The SO2/HCl ratio in the crater plume was measured with the OP-FTIR technique from a transportable instrument, using the sun as an IR source. Soil CO2 efflux coupled with the 220Rn/222Rn activity ratio in soil gases (named SGDI) were measured at a fixed monitoring site on the east flank of Etna. All signals acquired were subject both to spectral analysis and to filtering of the periodic signals discovered. All filtered signals revealed changes that were nicely correlated both with other geophysical signals and with volcanic eruptions during the study period. Time lags between parameters were explained in terms of different modes of magma migration and storage inside the volcano before eruptions. A comprehensive dynamic degassing model is presented that allows for a better understanding of magma dynamics in an open-conduit volcano.

Satellite derived SO2 emissions from the relatively low-intensity, effusive 2021 eruption of Fagradalsfjall, Iceland

In March 2021 an effusive eruption began at the Fagradalsfjall volcanic system in Iceland, ending nearly 800 years of dormancy on the Reykjanes peninsula. The eruption produced lava flows and moderate gas emissions and, although it did not cause significant disruption, highlighted the need for near real-time monitoring of volcanic activity on the peninsula for future eruptions. The activity passed through several phases, each characterised by a different eruption style, providing a rich testbed for monitoring methodologies.We present measurements of the volcanic sulphur dioxide (SO2) emission rate and injection altitude throughout the eruption, generated by combining satellite SO2 imagery from TROPOMI with PlumeTraj, a back-trajectory analysis toolkit. We compare the results with ground-based measurements of the emission rate and plume altitude, finding excellent agreement in the plume altitude. Reasonable agreement was also found between the measured emission rates, with the best match for stronger and more continuous emissions. This demonstrates the ability for PlumeTraj to monitor SO2 emissions from future effusive eruptions, while highlighting the need for care when analysing results from low altitude plumes or during periods of high cloud cover.

The 2021 Semeru volcano eruption: An insight from visual, seismic, and deformation monitoring data

Semeru is the highest volcano on the island of Java and one of Indonesia’s volcanoes that has a potential threat of pyroclastic flows. The eruption of Semeru often shows a transition pattern between explosive and effusive styles. An increased eruptive activity occurred in 2021 with series of explosions dominated the first two thirds of the year and then transition to series of pyroclastic flows in December 2021. On 4 December 2021, a dome collapse triggered significant pyroclastic flows that reached a maximum distance of 16 km from the crater and resulted in 51 casualties. In this paper, we aimed to study the dynamics of magma movement from depth to the surface and assessing the style transition of the eruptions between explosive and effusive activity from visual, seismic and deformation monitoring data. We analyzed Semeru volcano monitoring data throughout the year 2021. The volcanic activity monitoring system of Semeru volcano consists of 4 seismic stations, 5 deformation stations (2 tiltmeters and 3 GPS stations), and 2 Web Camera/CCTV. Our analysis on seismic data indicates that the series of large pyroclastic flows were triggered by excess pressure at shallow depths a few hours before the events. Deep volcanic earthquakes are relatively increased after the collapse of the lava dome or pyroclastic flows, possibly caused by the sudden decrease in hydrostatic pressure of the rock mass around the magma pocket, thus triggering gas expansion. Deformation monitoring using a tiltmeter at Argosuko and Jawar stations indicates inflation of a deep source since 15 August 2021. Since 7 November 2021, tiltmeter measurement has shown deep source deflation patterns which indicate magma movement from the deep reservoir to a shallower reservoir. After 21 November, inflation of the deep source was observed again, indicating an increase in magma supply from the deep pocket. The results of the pressure source modeling from GPS vector data in the period before the eruption, 1 November – 4 December 2021, showed an anomaly in the form of an increased volume at a depth of > 1.7 km of about 0.84 million/m3. Between 5 December and 31 December 2021, after the 4 December pyroclastic flow, the deformation modeling indicates the transition of the pressure source from a depth of 1.7 km to 8 km. In addition, we also observed a decrease in volume of 5.6 million/m3. The deformation pattern at shallow depths showed a deflationary pattern indicating a decrease in magma overpressure.

Mauna Loa awakens

On 27 November 2022, Hawaii’s Mauna Loa volcano on the Big Island began erupting for the first time in 38 years. A day later, a flight over the eruption captured this photo. It clearly shows a line of fissures, at an elevation of 3 km, from which lava flowed across the volcano’s northeast rift zone. The eruption continued for about two weeks, with lava traveling some 20 km from the summit. The US Geological Survey observed an increase in the number of earthquakes beneath the volcano’s cauldron-shaped summit and to the northwest roughly two months before the eruption began. The island’s nearby Kīlauea volcano has been erupting since September 2021.PPT|High resolutionThe two volcanoes appear to be connected underground by a deep, widespread network of pathways, according to a recently published paper by researchers from Caltech. Although previous studies have hypothesized that such a network may exist, the large data set the Caltech team analyzed showed enough seismic activity to map out a detailed plumbing system that connects Mauna Loa to Kīlauea, 34 km away. Future monitoring of volcanic activity may benefit from considering both volcanoes as part of a larger, interconnected system. (J. D. Wilding et al., Science 379, 462, 2023, doi:10.1126/science.ade5755; image courtesy of the US Geological Survey.) Section:ChooseTop of page <<© 2023 American Institute of Physics.

The FastVRP automatic platform for the thermal monitoring of volcanic activity using VIIRS and SLSTR sensors: FastFRP to monitor volcanic radiative power

Satellite thermal remote sensing is widely used to detect and quantify the high-temperature vol- canic features produced during an eruption, e.g. released radiative power. Some space agencies provide Fire Radiative Power (FRP) Products to characterize any thermal anomaly around the world. In particular, Level-2 FRP Products of the Visible Infrared Imaging Radiometer Suite (VIIRS) and the Sea and Land Surface Temperature Radiometer (SLSTR) are freely available online and they allow to monitor high-temperature volcanic features related to the dynamics of volcanic activity. Here, we propose the FastVRP platform developed in Google Colab to process automatically the FRP Products provided by the National Aeronautics and Space Administration (NASA) and the European Space Agency (ESA) space agencies. FastVRP was designed to monitor the volcanic radiative power (VRP) related to eruptive activity of Mt. Etna (Sicily, Italy). We compared the quality of these FRP Products during a number of recent paroxysmal lava fountains occurred at Etna volcano between February and March 2021. We highlighted the advantages and the limits of each sensor in monitor- ing intense volcanic eruptions lasting a few hours. Furthermore, we combine the mid-high spatial/ low temporal resolution VIIRS and SLSTR with the low spatial-high temporal resolution SEVIRI (Spinning Enhanced Visible and Infrared Radiometer Imager) to improve estimates of the energies released from each paroxysmal episode. In particular, we propose a fitting approach to enhance the accuracy of SEVIRI low spatial-high temporal resolution measurements exploiting the few acqui- sitions from VIIRS and SLSTR high spatial-low temporal resolution during lava fountain cooling phase. We validated the radiative power values forecasted from VIIRS and SLSTR with the radiative power values retrieved using MODIS (Moderate Resolution Imaging Spectroradiometer) sensor.

CNES-ESA satellite contribution to the operational monitoring of volcanic activity: The 2021 Icelandic eruption of Mt. Fagradalsfjall

Within the framework of the CIEST2 (Cellule d'Intervention d'Expertise Scientifique et Technique new generation) and thanks to the support of CNES, the French space agency, the first phase of the Fagradalsfjall eruption was exceptionally well covered by high resolution optical satellite data, through daily acquisitions of Pléiades images in stereo mode. In this study, we show how Pléiades data provided real-time information useful for the operational monitoring of the ongoing eruption. An estimation of the volume of lava emitted as well as the corresponding effusion rate could be derived and delivered to the civil protection less than 6 h after the data acquisition. This information is complementary to and consistent with estimates obtained through the HOTVOLC service using SEVIRI (Spinning Enhanced Visible and Infrared Imager) sensor on-board Meteosat Second Generation (MGS) geostationary satellites, operated by the European Space Agency (ESA), characterized by a lower spatial resolution and a higher temporal one. In addition to the information provided on the lava emission, Pléiades data also helped characterize the intensity of the eruption by providing insight into the elevation and the velocity of the volcanic plume. The survey of this effusive eruption, well anticipated by a series of precursors, is a proof of concept of the efficiency of optical/thermal satellite data for volcanic crisis real-time monitoring.

Monitoring of Volcanic Activity Based on Geomagnetic Field Observations

Monitoring of Volcanic Activity Based on Geomagnetic Field Observations

The Hydrothermal Vent Field at the Eastern Edge of the Hellenic Volcanic Arc: The Avyssos Caldera (Nisyros)

Almost three-quarters of known volcanic activity on Earth occurs in underwater locations. The presence of active hydrothermal vent fields in such environments is a potential natural hazard for the environment, society, and economy. Despite its importance for risk assessment and risk mitigation, the monitoring of volcanic activity is impeded by the remoteness and the extreme conditions of many underwater volcanoes. The morphology and the activity of the submarine caldera, Avyssos, at the northern part of Nisyros volcano in the South Aegean Sea (Greece), were studied using a remotely operated underwater vehicle. The recorded time series of temperature and conductivity over the submarine volcano have been analyzed in terms of the Generalized Moments Method. This type of analysis can be used as an indicator for the state of activity of a submarine volcano. Here, we expand the work conducted for the first time in 2018. We present the findings of the geological exploration and the mathematical analysis, obtained from the data collected in October 2010. The temperature and conductivity time series show minor fluctuations in a rather stable environment. Based on these results, the impact of developing appropriate mechanisms and policies to avoid the associated natural hazard is expected to be important.

Validation of a New UAV Magnetic Prospecting Tool for Volcano Monitoring and Geohazard Assessment

The use of unmanned aircraft vehicles (UAVs) in volcanological contexts is a key challenge in studying volcanoes and improving efficiency in the monitoring of volcanic activity. The coupling of ground and satellite measurements has been reinforced at an intermediate scale thanks to UAV measurements. Along with carrying out visible and infrared measurements, UAVs can conduct geophysical measurements for more in-depth studies. Magnetic field measurements are a powerful tool in volcanic contexts for (i) mapping structural contacts between formations of different ages or type, and (ii) imaging deep thermal anomalies and intrusive systems. Here, we focus on magnetic sensors, which are becoming operational, and in particular on a scalar system recently implemented on a light drone that can be deployed quickly and efficiently in the field. This paper presents several flight test results in order to discuss any artifacts of the UAV or environmental conditions in the magnetic measurements. The results of the comparison between simultaneous UAV and ground surveys are presented. We demonstrate that low altitude measurements are particularly relevant to well-imaged magnetic anomalies and their variation through time in a volcanic context. Some potential uses for this technology and associated applications are also discussed in the fields of exploring and monitoring active volcanoes, for the 4D imaging of volcanoes.

Hydrogeological and Geochemical Characteristics of the Coastal Aquifer of Stromboli Volcanic Island (Italy)

Although groundwater is a strategic source in volcanic islands, most hydrogeochemical research on this topic has been focused on volcanic activity monitoring, overlooking general hydrogeological aspects. The same applies to one of the most studied volcanoes in the world, Stromboli Island (Italy). Here, we provide a hydrogeological scheme of its coastal aquifer, retrieving inferences about its potential use as a water supply source and for optimizing monitoring protocols for volcanic surveillance. Starting from the hydrogeochemical literature background, we analyzed new data, acquired both for volcano monitoring purposes and during specific surveys. Among these, there were saturated hydraulic conductivity measurements of selected rock samples and precise determinations of water table elevations based on GNSS surveys of wells. We identified a ubiquitous thin lens of brackish water floating on seawater and composed of a variable mixing of marine and meteoric components; inlets of hydrothermal fluids to the aquifer are basically gases, mainly CO2. Based on its hydrogeochemical character, the coastal aquifer of Stromboli could be used as a water supply source after desalinization by reverse osmosis, while the wells located far from the seashore are the most interesting for volcano monitoring, because they are less disturbed by the shallow geochemical noise.

Development of IoT-Based Volcano Early Warning System

Monitoring volcanic activity this is indispensable for both research and disaster mitigation strategies. Therefore, the presence of volcano monitoring allows the monitoring, data recording and early warning system of volcanic activity from a distance that is real time. Volcanic monitoring system aims to detect any changes in volcanic status. Temperature and humidity become parameters of increased magma activity. Concentration of gasses includes SO2 and CO2, indicates of the depth of magma in volcanic conduit. Magma movement also triggers the earthquake.The instrument that used in this research are temperature and humidity sensor DHT11, SO2 sensor TGS2602, CO2 sensor MG811, and vibration sensor ADXL345. Temperature and humidity sensors used DHT11 sensors that serve to detect temperature and humidity in the air. DHT11 sensors can detect temperature between 0-50°C and humidity between 20-90% RH. SO2 emissions were detected using TGS 2602 sensors that detects SO2 gas between 0-100 ppm. While CO2 gas emissions used MG811 sensors that detect the presence of CO2 gas between 350-10000 ppm. Furthermore, the vibrations were detected using a digital accelerometer ADXL345 that detects vibrations between 0.1-3200 Hz.Data from all sensors processed using arduino promini microcontroller and then sent to ESP8266. ESP8266 is a wifi module that serves as a microcontroller enhancement to connect to wifi and create TCP / IP protocol. This module is also used to create an IoT project so that it can be accessed at any time on the web service page. This system will be assembled solar cells as a source of power supply.

Episodic ground deformation associated with geothermal energy production at the Guayabo Caldera, Costa Rica

The ground response to the production of energy in geothermal fields can be observed in the form of ground displacement and seismic activity. Changes in the temperature, volume, pressure of the reservoir can culminate in surface deformation and in seismicity at the reservoir edges and/or near the production wells. Identifying the origin of the ground response enables controlled management of the reservoir and can help prevent damage to structures. Satellite remote sensing (InSAR) permits the study of the deformation at these sites with high spatial and temporal resolution. However, Central America has a dynamic atmosphere with considerable water vapour and constant growth of vegetation all year long, which leads to decorrelation between SAR images. Here we study the Dr. Alfredo Mainieri Protti geothermal field, located near Miravalles Volcano in the Northern Costa Rica volcanic arc. We measure the deformation associated with geothermal energy production using data from two satellites (ALOS-2 and Sentinel-1) between January 2015 and January 2017. The ALOS-2 data was used to obtain the extent of the affected area, and two StaMPS multi-temporal methods (Persistent Scatter (PS) InSAR, and Small Baselines(SB)) were applied to the Sentinel-1 data, to obtain the temporal pattern of the ground displacements. Results show a direct response of the ground to the extraction of fluids. The pattern of deformation obtained with ALOS-2 is spatially correlated with the geothermal field, and with the recorded seismicity. Between April 2015 to October 2016, periods of uplift and subsidence were observed with values between ~2.0 to 3.0 cm every 120 days, linked to changes in the amount of fluids extracted from the reservoir. The results also show the ability of the reservoir to recover rapidly following a decrease in extraction rate. This work has shown that even in this tropical region it is possible to monitor anthropogenic ground motion using InSAR. This is beneficial for the Central American region, as satellite images are becoming more frequently acquired and available, and can be used to boost the monitoring of seismic regions, volcanic activity and anthropogenic activities.

Volcanic activity monitoring by unique LIDAR based on a diode laser

For the first time, we monitored the Elbrus volcano activity detecting volcanic gases emanating through pores using an unique eye-safe LIDAR system. A highly sensitive eye-safe LIDAR system was developed for monitoring the fracture-emitted aerosol, which is transported by volcanic gases inside a hot tunnel near the Elbrus Mountain. The developed LIDAR is based on a diode laser (transmitter, 910 nm, 3 ns, <1 µJ cm−2) and a single-photon avalanche photodiode (detector). From August to October 2019, within the first months of the LIDAR monitoring, we have detected a two-fold decrease in the fracture-emitted aerosol emanation, while other parameters in the tunnel remained relatively stable (radon concentration, air temperature and humidity changed less than by 1%). A significant correlation between the LIDAR signal of volcanic aerosol and the Earth’s crust deformation measured by the laser strainmeter located nearby was found. Based on our preliminary experiments we consider the new LIDAR system as a sensitive, economical and robust instrument for Earth’s crust deformation and volcanic activity monitoring and eruption precursor observation.

Forecasting, Detecting, and Tracking Volcanic Eruptions from Space

Satellite monitoring of volcanic activity typically includes four primary observations: (1) deformation and surface change, (2) gas emissions, (3) thermal anomalies, and (4) ash plumes. These phenomena are imaged by remote sensing data that span the electromagnetic spectrum, from microwave to ultraviolet energy and including visible and infrared wavelengths. The primary uses of satellite data in volcanology are forecasting, detecting, and tracking eruptive activity. Eruptions are often preceded by a number of indicators that are detectable from space, including surface deformation, subtle increases in surface temperature, and elevated gas emissions. The first indications of eruption, especially at remote volcanoes, are often identified in satellite data by strong thermal anomalies and/or the presence of ash and gas in the atmosphere, the recognition of which can be automated for rapid eruption detection. Once an eruption is in progress, space-based imagery of all types can track activity over time, providing information on the emplacement of volcanic deposits, the presence and character of ash plumes, and potential changes in the character of the eruption, all of which aid hazards assessment. Activity at Agung volcano, Indonesia, during 2017–2019, offers an excellent example of the importance of remote sensing datasets for forecasting, detecting, and tracking eruptions. Challenges to exploiting current and future satellite data include ensuring regular acquisitions over active volcanoes and developing tools for automated analysis of the massive volume of imagery for volcano-related signals.

Detection of Thermal Anomalies in the Images of Volcanoes Taken at Night

The problem of revealing the appearance and development of thermal anomalies in the images of volcanoes taken at night in the visible and near-infrared ranges is discussed. An algorithm for detecting and classifying such anomalies is proposed and is tested on the data from the archive of the video monitoring of volcanoes on Kamchatka. The results obtained suggest the possible use of the developed solution in the tasks of real-time monitoring of volcanic activity in the Russian Far East.

A Signal Processing Perspective of Monitoring Active Volcanoes [Applications Corner

A volcano is a rupture in Earth's crust that unleashes lava, volcanic ash, and gases from a cavity beneath the surface. Monitoring volcanoes is crucial for getting an insight into the dynamics of the different events taking place, modeling their behavior, and establishing mechanisms to efficiently deal with eruptions. The seismic signals coming from volcanoes are a great source of information about what happens inside their structure and thus are helpful in forecasting their activity. Their study is important to ensure the safety of people who live in the vicinity of different volcanoes around the world. This is why volcanicactivity monitoring is being supported by applying modern signal processing and machine-learning methods.

High-sensitivity microseismic monitoring: Automatic detection and localization of subsurface noise sources using matched-field processing and dense patch arrays

Recent advancements in seismic data acquisition and computational power have enhanced the deployment of dense seismic monitoring networks. The growing volume of recorded data requires the development of automated techniques to monitor and image zones of seismicity. We have developed an automatic detection and localization method that demands minimal a priori information for retrieval of the spatial distribution of subsurface noise sources (including, but not limited to, microseismic activity), in a reservoir and in the near vicinity during a hydraulic fracturing treatment. This method is based on matched-field processing (MFP), which takes advantage of the phase coherence that is recorded at dense arrays of sensors to localize noise sources. MFP is applied with a distributed set of patch arrays in the context of geophysics exploration. The MFP approach is applied to ambient noise recordings, and it provides results that are consistent with the classic localization methods applied to high-amplitude microseismic signals (in particular, using the relative template-based method). Furthermore, MFP provides enhanced sensitivity of detection and spatially extended information about structural heterogeneities. MFP opens a route to continuous, automatic, statistics-based, and high-sensitivity reservoir monitoring and imaging for geophysics exploration. Potential applications can also be envisaged for seismic monitoring of volcanic and geyser activities, and for other types of hydrothermal activity.

Mechanism of Gd3+ uptake in gypsum (CaSO4·2H2O): Implications for EPR dating, REE recovery and REE behavior

Rare earth elements (REE) in gypsum have long attracted interest for geochemical applications from the reconstruction of paleoclimate, paleoenvironment and paleohydrology to the monitoring of volcanic and seismic activities. Resurgent interests in REE in gypsum stem from the potential recovery of these high-tech metals from gypsum-rich tailings. Development of new geochemical applications and invention of effective recovery technologies all require knowledge about the mechanism of REE uptake in gypsum. In this contribution, we have investigated Gd-doped gypsum from the gel diffusion technique at ambient conditions in the pH range from 6.5 to 9.5. Inductively coupled plasma mass spectrometry analyses of Gd-doped gypsum yielded 752 ppm Gd at pH = 6.5 down to 2.8 ppm Gd at pH = 9.5. Synchrotron Gd L3-edge X-ray absorption spectra show that Gd3+ has a local environment similar to that of Ca2+ in gypsum. Single-crystal electron paramagnetic resonance (EPR, also known as electron spin resonance or ESR) spectra reveal a dominant Gd3+ center with weak satellites. The dominant Gd3+ center arises from a substitutional Gd3+ ion at the Ca site retaining its C2 local symmetry, which is also confirmed by pulsed electron nuclear double resonance (ENDOR) data for proton hyperfine structures up to 5.2 Å away from Gd3+. The satellites are attributable to a Gd3+-Gd3+ pair (dimer) along the crystallographic a-axis with a dipolar coupling constant Dd/geβe = −13 G, which corresponds to a distance of 12.6 Å between the two Gd3+ ions and provides the first experimental confirmation for the substitution 2Gd3+ + □ = 3Ca2+ in gypsum. Hole trapping at cation vacancies associated with the incorporation of Gd3+ (and other trivalent REE) in gypsum offers a new class of radiation-induced paramagnetic defects in this mineral for EPR/ESR dating. These results also have implications for developing new technologies for effective recovery of REE from gypsum-rich tailings and for understanding the behavior of REE in evaporites and aqueous solutions.

Volcano-tectonic dynamics of Deception Island (Antarctica): 27 years of GPS observations (1991–2018)

Deception Island (South Shetland Islands) is one of the most active volcanoes in Antarctica. In the 1988–1989 austral summer, after the most recent eruptive process on the island (1967–1970), monitoring of volcanic activity through geophysical and geodetic techniques was resumed by Spanish and Argentinean scientists. In order to monitor the island's tectonic and volcanic behavior, a geodetic network was deployed. Currently, this network consists of 15 geodetic benchmarks located around Port Foster, Deception's inner bay open to the sea. Two additional geodetic benchmarks were installed outside Deception Island to be used as reference benchmarks for the differential positioning strategy. Since 1991–1992, geodetic ground-displacement velocities between the successive austral summer Antarctic campaigns have been computed and analyzed.The overall geodynamic behavior of Deception Island within the South Shetland Islands, Antarctic Peninsula and Bransfield Basin regional environment has been analyzed from geodetic ground-displacements. Results obtained demonstrate that Deception and Livingston island have a similar behavior derived from the Bransfield Basin extension and the Phoenix micro-plate subsidence processes. However, Deception Island is also highly influenced by its volcanic activity.Deception Island's volcanic behavior between 1991 and 2018 is shown by the velocity field, strain tensors and pressure source evolution obtained from the ground-displacements at the geodetic benchmarks. During this time period, it is possible to identify different inflation and deflation phases separated by transitional (or mixed) stages of extension without uplift and compression without subsidence. The most representative inflation and deflation periods were analyzed in detail, to show how they correlate with high and low seismic activity, respectively. The transitional or mixed stages, seem to be the precursors of the next inflation or deflation phase being the Bransfield basin rifting and NW-SE extension the potential related process.Finally, we have analyzed the processes that occurred prior to the volcanic unrests of 1999–2000 and 2012–2013. In both cases, an increase in detected seismic activity and/or soil and seawater temperature was observed and a mixed phase of extension without uplift seems to be precursory to the volcanic unrest. The correlation between the inflation processes, identified by ground-displacement of the network geodetic benchmarks, the increase in seismicity and the increment of soil and seawater temperature makes these transitional mixed phases potential precursors of Deception Island's volcanic unrest periods.

Detection and Classification of Continuous Volcano-Seismic Signals With Recurrent Neural Networks

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.