Volcanic thermal anomalies are monitored with an increased application of optical satellite sensors to improve the ability to identify renewed volcanic activity. Hotspot detection algorithms adopting a fixed threshold are widely used to detect thermal anomalies with a minimal occurrence of false alerts. However, when used on a global scale, these algorithms miss some subtle thermal anomalies that occur. Analyzing satellite data sources with machine learning (ML) algorithms has been shown to be efficient in extracting volcanic thermal features. Here, a data-driven algorithm is developed in Google Earth Engine (GEE) to map thermal anomalies associated with lava flows that erupted recently at different volcanoes around the world (e.g., Etna, Cumbre Vieja, Geldingadalir, Pacaya, and Stromboli). We used high spatial resolution images acquired by a Sentinel-2 MultiSpectral Instrument (MSI) and a random forest model, which avoids the setting of fixed a priori thresholds. The results indicate that the model achieves better performance than traditional approaches with good generalization capabilities and high sensitivity to less intense volcanic thermal anomalies. We found that this model is sufficiently robust to be successfully used with new eruptive scenes never seen before on a global scale.

The latest generation of high-spatial-resolution satellites produces measurements of high-temperature volcanic features at global scale, which are valuable to monitor volcanic activity. Recent advances in technology and increased computational resources have resulted in an extraordinary amount of monitoring data, which can no longer be so readily examined. Here, we present an automatic detection algorithm based on a deep convolutional neural network (CNN) that uses infrared satellite data to automatically determine the presence of volcanic thermal activity. We exploit the potentiality of the transfer learning technique to retrain a pre-trained SqueezeNet CNN to a new domain. We fine-tune the weights of the network over a new dataset opportunely created with images related to thermal anomalies of different active volcanoes around the world. Furthermore, an ensemble approach is employed to enhance accuracy and robustness when compared to using individual models. We chose a balanced training dataset with two classes, one containing volcanic thermal anomalies (erupting volcanoes) and the other containing no thermal anomalies (non-erupting volcanoes), to differentiate between volcanic scenes with eruptive and non-eruptive activity. We used satellite images acquired in the infrared bands by ESA Sentinel-2 Multispectral Instrument (MSI) and NASA & USGS Landsat 8 Operational Land Imager and Thermal InfraRed Sensor (OLI/TIRS). This deep learning approach makes the model capable of identifying the appearance of a volcanic thermal anomaly in the images belonging to the volcanic domain with an overall accuracy of 98.3%, recognizing the scene with active flows and erupting vents (i.e., eruptive activity) and the volcanoes at rest. This model is generalizable, and has the capability to analyze every image captured by these satellites over volcanoes around the world.

Volcanic explosive eruptions inject several different types of particles and gasses into the atmosphere, giving rise to the formation and propagation of volcanic clouds. These can pose a serious threat to the health of people living near an active volcano and cause damage to air traffic. Many efforts have been devoted to monitor and characterize volcanic clouds. Satellite infrared (IR) sensors have been shown to be well suitable for volcanic cloud monitoring tasks. Here, a machine learning (ML) approach was developed in Google Earth Engine (GEE) to detect a volcanic cloud and to classify its main components using satellite infrared images. We implemented a supervised support vector machine (SVM) algorithm to segment a combination of thermal infrared (TIR) bands acquired by the geostationary MSG-SEVIRI (Meteosat Second Generation—Spinning Enhanced Visible and Infrared Imager). This ML algorithm was applied to some of the paroxysmal explosive events that occurred at Mt. Etna between 2020 and 2022. We found that the ML approach using a combination of TIR bands from the geostationary satellite is very efficient, achieving an accuracy of 0.86, being able to properly detect, track and map automatically volcanic ash clouds in near real-time.

Stromboli volcano has a persistent activity that is almost exclusively explosive. Predominated by low intensity events, this activity is occasionally interspersed with more powerful episodes, known as major explosions and paroxysms, which represent the main hazards for the inhabitants of the island. Here, we propose a machine learning approach to distinguish between paroxysms and major explosions by using satellite-derived measurements. We investigated the high energy explosive events occurring in the period January 2018–April 2021. Three distinguishing features are taken into account, namely (i) the temporal variations of surface temperature over the summit area, (ii) the magnitude of the explosive volcanic deposits emplaced during each explosion, and (iii) the height of the volcanic ash plume produced by the explosive events. We use optical satellite imagery to compute the land surface temperature (LST) and the ash plume height (PH). The magnitude of the explosive volcanic deposits (EVD) is estimated by using multi-temporal Synthetic Aperture Radar (SAR) intensity images. Once the input feature vectors were identified, we designed a k-means unsupervised classifier to group the explosive events at Stromboli volcano based on their similarities in two clusters: (1) paroxysms and (2) major explosions. The major explosions are identified by low/medium thermal content, i.e., LSTI around 1.4 °C, low plume height, i.e., PH around 420 m, and low production of explosive deposits, i.e., EVD around 2.5. The paroxysms are extreme events mainly characterized by medium/high thermal content, i.e., LSTI around 2.3 °C, medium/high plume height, i.e., PH around 3330 m, and high production of explosive deposits, i.e., EVD around 10.17. The centroids with coordinates (PH, EVD, LSTI) are: C_p (3330, 10.7, 2.3) for the paroxysms, and C_me (420, 2.5, 1.4) for the major explosions.

The global, near-real-time monitoring of volcano thermal activity has become feasible through thermal infrared sensors on various satellite platforms, which enable accurate estimations of volcanic emissions. Specifically, these sensors facilitate reliable estimation of Volcanic Radiative Power (VRP), representing the heat radiated during volcanic activity. A critical factor influencing VRP estimates is the identification of hotspots in satellite imagery, typically based on intensity. Different satellite sensors employ unique algorithms due to their distinct characteristics. Integrating data from multiple satellite sources, each with different spatial and spectral resolutions, offers a more comprehensive analysis than using individual data sources alone. We introduce an innovative Remote Sensing Data Fusion (RSDF) algorithm, developed within a Cloud Computing environment that provides scalable, on-demand computing resources and services via the internet, to monitor VRP locally using data from various multispectral satellite sensors: the polar-orbiting Moderate Resolution Imaging Spectroradiometer (MODIS), the Sea and Land Surface Temperature Radiometer (SLSTR), and the Visible Infrared Imaging Radiometer Suite (VIIRS), along with the geostationary Spinning Enhanced Visible and InfraRed Imager (SEVIRI). We describe and demonstrate the operation of this algorithm through the analysis of recent eruptive activities at the Etna and Stromboli volcanoes. The RSDF algorithm, leveraging both spatial and intensity features, demonstrates heightened sensitivity in detecting high-temperature volcanic features, thereby improving VRP monitoring compared to conventional pre-processed products available online. The overall accuracy increased significantly, with the omission rate dropping from 75.5% to 3.7% and the false detection rate decreasing from 11.0% to 4.3%. The proposed multi-sensor approach markedly enhances the ability to monitor and analyze volcanic activity.

Several satellite missions are currently available to provide thermal infrared data at different spatial resolutions and revisit time. Furthermore, new missions are planned thus enabling to keep a nearly continuous ‘eye’ on thermal volcanic activity around the world. This massive volume of data requires the development of artificial intelligence (AI) techniques for the automatic processing of satellite data in order to extract significant information about volcano conditions in a short time. Here, we propose a robust machine learning approach to accurately detect, recognize and quantify high-temperature volcanic features using Sentinel-2 MultiSpectral Instrument (S2-MSI) imagery. We use the entire archive of high spatial resolution satellite data containing more than 6000 S2-MSI scenes at ten different volcanoes around the world. Combining a ‘top-down’ cascading architecture, two different machine learning models, a scene classifier (SqueezeNet) and a pixel-based segmentation model (random forest), we achieved a very high accuracy, namely 95%. These results show that the cascading approach can be applied in near-real time to any available satellite image, providing a full description of the scene, with an important contribution to the monitoring, mapping and characterization of volcanic thermal features.