Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series

Satellite imagery provides a rich source of information that serves as a comprehensive and synoptic tool for the continuous monitoring of active volcanoes, including those in remote and inaccessible areas. The huge influx of such data requires the development of automated systems for efficient proce...

Full description

Saved in:
Bibliographic Details
Main Authors: Francesco Spina, Giuseppe Bilotta, Annalisa Cappello, Marco Spina, Francesco Zuccarello, Gaetana Ganci
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/10/1679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719151501770752
author Francesco Spina
Giuseppe Bilotta
Annalisa Cappello
Marco Spina
Francesco Zuccarello
Gaetana Ganci
author_facet Francesco Spina
Giuseppe Bilotta
Annalisa Cappello
Marco Spina
Francesco Zuccarello
Gaetana Ganci
author_sort Francesco Spina
collection DOAJ
description Satellite imagery provides a rich source of information that serves as a comprehensive and synoptic tool for the continuous monitoring of active volcanoes, including those in remote and inaccessible areas. The huge influx of such data requires the development of automated systems for efficient processing and interpretation. Early warning systems, designed to process satellite imagery to identify signs of impending eruptions and monitor eruptive activity in near real-time, are essential for hazard assessment and risk mitigation. Here, we propose a machine learning approach for the automatic classification of pixels in SEVIRI images to detect and characterize the eruptive activity of a volcano. In particular, we exploit a semi-supervised GAN (SGAN) model that retrieves the presence of thermal anomalies, volcanic ash plumes, and meteorological clouds in each SEVIRI pixel, allowing time series plots to be obtained showing the evolution of volcanic activity. The SGAN model was trained and tested using the huge amount of data available on Mount Etna (Italy). Then, it was applied to other volcanoes, specifically, Stromboli (Italy), Tajogaite (Spain), and Nyiragongo (Democratic Republic of the Congo), to assess the model’s ability to generalize. The validation of the model was performed through a visual comparison between the classification results and the corresponding SEVIRI images. Moreover, we evaluate the model performance by calculating three different metrics, namely the precision (correctness of positive predictions), the recall (ability to find all the positive instances), and the F1-score (general model’s accuracy), finding an average accuracy of 0.9. Our approach can be extended to other geostationary satellite data and applied worldwide to characterize volcanic activity, allowing the monitoring of even remote volcanoes that are difficult to reach from the ground.
format Article
id doaj-art-6d42a94deb2a45179689456430ae76ee
institution DOAJ
issn 2072-4292
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6d42a94deb2a45179689456430ae76ee2025-08-20T03:12:12ZengMDPI AGRemote Sensing2072-42922025-05-011710167910.3390/rs17101679Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time SeriesFrancesco Spina0Giuseppe Bilotta1Annalisa Cappello2Marco Spina3Francesco Zuccarello4Gaetana Ganci5Istituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalyIstituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalyIstituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalyIstituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalyIstituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalyIstituto Nazionale di Geofisica e Vulcanologia, Piazza Roma 2, 95125 Catania, ItalySatellite imagery provides a rich source of information that serves as a comprehensive and synoptic tool for the continuous monitoring of active volcanoes, including those in remote and inaccessible areas. The huge influx of such data requires the development of automated systems for efficient processing and interpretation. Early warning systems, designed to process satellite imagery to identify signs of impending eruptions and monitor eruptive activity in near real-time, are essential for hazard assessment and risk mitigation. Here, we propose a machine learning approach for the automatic classification of pixels in SEVIRI images to detect and characterize the eruptive activity of a volcano. In particular, we exploit a semi-supervised GAN (SGAN) model that retrieves the presence of thermal anomalies, volcanic ash plumes, and meteorological clouds in each SEVIRI pixel, allowing time series plots to be obtained showing the evolution of volcanic activity. The SGAN model was trained and tested using the huge amount of data available on Mount Etna (Italy). Then, it was applied to other volcanoes, specifically, Stromboli (Italy), Tajogaite (Spain), and Nyiragongo (Democratic Republic of the Congo), to assess the model’s ability to generalize. The validation of the model was performed through a visual comparison between the classification results and the corresponding SEVIRI images. Moreover, we evaluate the model performance by calculating three different metrics, namely the precision (correctness of positive predictions), the recall (ability to find all the positive instances), and the F1-score (general model’s accuracy), finding an average accuracy of 0.9. Our approach can be extended to other geostationary satellite data and applied worldwide to characterize volcanic activity, allowing the monitoring of even remote volcanoes that are difficult to reach from the ground.https://www.mdpi.com/2072-4292/17/10/1679classification algorithmsdeep learninggenerative adversarial networksremote sensingvolcanic ash
spellingShingle Francesco Spina
Giuseppe Bilotta
Annalisa Cappello
Marco Spina
Francesco Zuccarello
Gaetana Ganci
Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
Remote Sensing
classification algorithms
deep learning
generative adversarial networks
remote sensing
volcanic ash
title Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
title_full Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
title_fullStr Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
title_full_unstemmed Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
title_short Volcanic Activity Classification Through Semi-Supervised Learning Applied to Satellite Radiance Time Series
title_sort volcanic activity classification through semi supervised learning applied to satellite radiance time series
topic classification algorithms
deep learning
generative adversarial networks
remote sensing
volcanic ash
url https://www.mdpi.com/2072-4292/17/10/1679
work_keys_str_mv AT francescospina volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries
AT giuseppebilotta volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries
AT annalisacappello volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries
AT marcospina volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries
AT francescozuccarello volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries
AT gaetanaganci volcanicactivityclassificationthroughsemisupervisedlearningappliedtosatelliteradiancetimeseries