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.

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.

Physical phenomena evolve in space and time following governing laws with a high level of complexity and mathematical models can help to make accurate predictions of their behavior, describing complex fluids with a good balance between accuracy and computational costs. We have long used detailed Computational Fluid Dynamics (CFD) models to simulate complex dynamics with high accuracy, but these simulations typically entail high computational costs, resulting in long execution times and the use of expensive computational resources. To overcome these limitations, we have recently integrated CFD with Artificial Intelligence (AI), in the so-called Emulators, to expand the scope of fluid modeling, improving its performance. Here, we present an AI-based CFD emulator for Smoothed Particle Hydrodynamics (SPH) simulations, which uses an Artificial Neural Network (ANN) to enhance simulations of complex fluids with viscous and thermal components. We show the model capability to reproduce the spatio-temporal evolution of natural visco-thermal fluids. In addition, we demonstrate the emulator capacity to generalize its applicability to problems not encountered during the training phase. We also conduct a detailed error evaluation, showing that the minimal observed discrepancies do not compromise model accuracy and robustness, especially given the theoretical and computational advantages. These key points open this emulator to practical applications for natural fluids, e.g., oil, honey, or geophysical fluids such as lava, enhancing fluidmodeling performance and extending functionalities. The innovation of this method improves studies in the field of numerical simulations, for example in its use as a digital Twin of a physical phenomenon, for the study of the dynamics of the system without the need of large costs for field analysis or laboratory experiments.