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.

Continuous global monitoring of volcanic activity from space requires balancing spatial and temporal resolution, a long-standing trade-off between polar-orbiting and geostationary satellites. Polar sensors such as MODIS, VIIRS, and SLSTR provide high spatial resolution (375 m–1 km) but with limited temporal coverage. In contrast, geostationary sensors like SEVIRI offer high temporal resolution (5–15 min) but with coarser spatial detail (~3 km), often missing lower-intensity thermal events. The recently launched Flexible Combined Imager (FCI) aboard the geostationary Meteosat Third Generation (MTG-I) satellite represents a major improvement, providing images every 10 min with a spatial resolution of 1–2 km, comparable to that of polar orbiters. Here, we adapted the established Remote Sensing Data Fusion (RSDF) algorithm to exploit the enhanced capabilities of FCI for detecting volcanic thermal anomalies and estimating Volcanic Radiative Power (VRP). The algorithm was applied to Mount Etna during three different eruptive phases that occurred in 2025. The VRP derived from FCI data was compared with that obtained from the geostationary SEVIRI and the polar-orbiting MODIS, SLSTR, and VIIRS sensors. The results show that FCI provides a more detailed and continuous characterization of volcanic thermal output than SEVIRI, while maintaining close agreement with polar sensors. These findings confirm the capability of FCI to deliver high-frequency, high-resolution thermal monitoring, representing a major step toward operational, near-real-time volcanic surveillance from space.

Earth Observations (EO) play a crucial role in global monitoring of volcanic activity worldwide. Satellite data are continuously acquired by multispectralsensors on board of polar and geostationary satellites orbiting the Earth. EO allows to track ongoing volcanic activity by retrieving eruptive parameters such as the amount of lava erupted in near real time. The heterogeneity of satellite sensors in terms of spatial and temporal resolution requires advanced techniques to automatically estimate volcanic features and combine their outcomes. Here, the potential of integrating Artificial Intelligence (AI) techniques has been demonstrated in processing large amounts of heterogeneous satellite data used to monitor the effusive activity in near real time at Mount Etna from November 2022 to February 2023. Data provided by satellite sensors, including 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), enable reliable estimates of Volcanic Radiative Power (VRP), areal coverage of lava flows, Time Averaged Discharge Rate (TADR) and the lava volume erupted, and areal coverage of lava flows thanks to Sentinel-2 MSI.

Effusive volcanic eruptions pose significant hazards to populated areas, making the accurate dating of lava flows essential for reconstructing eruptive histories and assessing volcanic risk. Traditional dating techniques, such as radiometric, paleomagnetic and lichenometric methods, are highly reliable but require direct sampling, complex analytical procedures, and substantial financial resources. Satellite remote sensing provides a non-invasive and spatially extensive approach that can complement conventional methods in the regional investigation of exposed volcanic surfaces. This study presents a two-stage hybrid classification–regression framework for empirical age estimation and chronological mapping of historical lava surfaces on Mount Etna, spanning the 17th to the 21st centuries. In the first stage, a Random Forest Classifier distinguishes background, pre-1600 lava surfaces, and post-1600 historical lava surfaces, thereby defining the spatial applicability domain of the chronological model. In the second stage, a Random Forest Regressor estimates age only for pixels classified as post-1600 lava by integrating ten Sentinel-2 surface-reflectance bands, elevation derived from the Digital Elevation Model (DEM), and a binary north-flank spatial indicator. On the balanced pixel-level test dataset, the RFR achieved an $R^2$ of 0.549, a Mean Absolute Error of 66.2 years, and a Root Mean Squared Error of 89.0 years. Using the median prediction for each test eruption, the corresponding eruption-level values were $R^2=0.701$, MAE $=51.6$ years, and RMSE $=67.2$ years. Prediction errors were larger for the oldest evaluated surfaces, indicating reduced empirical discrimination near the lower boundary of the calibrated chronological domain. This pattern may reflect calibration-boundary effects, sparse chronological coverage, eruption-specific variability, and possible convergence of surface spectral properties. Comparison with an RBF-SVR showed comparable but metric-dependent performance, without establishing the overall superiority of either regression architecture. Permutation analysis indicated that most predictive information within this dataset was associated with the Sentinel-2 spectral component, particularly the Red Edge bands. The proposed method should therefore be interpreted as a complementary fast empirical lava age-estimation and regional screening framework for exposed historical lava surfaces, rather than as a substitute for radiometric, paleomagnetic, or field-based dating.