Deep Learning Investigation of Mercury’s Explosive Volcanism
The remnants of explosive volcanism on Mercury have been observed in the form of vents and pyroclastic deposits, termed faculae, using data from the Mercury Atmospheric and Surface Composition Spectrometer (MASCS) onboard the Mercury surface, space environment, geochemistry, and ranging (MESSENGER)...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/18/4560 |
_version_ | 1797577197120126976 |
---|---|
author | Mireia Leon-Dasi Sebastien Besse Alain Doressoundiram |
author_facet | Mireia Leon-Dasi Sebastien Besse Alain Doressoundiram |
author_sort | Mireia Leon-Dasi |
collection | DOAJ |
description | The remnants of explosive volcanism on Mercury have been observed in the form of vents and pyroclastic deposits, termed faculae, using data from the Mercury Atmospheric and Surface Composition Spectrometer (MASCS) onboard the Mercury surface, space environment, geochemistry, and ranging (MESSENGER) spacecraft. Although these features present a wide variety of sizes, shapes, and spectral properties, the large number of observations and the lack of high-resolution hyperspectral images complicates their detailed characterisation. We investigate the application of unsupervised deep learning to explore the diversity and constrain the extent of the Hermean pyroclastic deposits. We use a three-dimensional convolutional autoencoder (3DCAE) to extract the spectral and spatial attributes that characterise these features and to create cluster maps constructing a unique framework to compare different deposits. From the cluster maps we define the boundaries of 55 irregular deposits covering 110 vents and compare the results with previous radius and surface estimates. We find that the network is capable of extracting spatial information such as the border of the faculae, and spectral information to altogether highlight the pyroclastic deposits from the background terrain. Overall, we find the 3DCAE an effective technique to analyse sparse observations in planetary sciences. |
first_indexed | 2024-03-10T22:05:41Z |
format | Article |
id | doaj.art-b4b4517a905d409aa46afcc719cf83d4 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T22:05:41Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-b4b4517a905d409aa46afcc719cf83d42023-11-19T12:49:25ZengMDPI AGRemote Sensing2072-42922023-09-011518456010.3390/rs15184560Deep Learning Investigation of Mercury’s Explosive VolcanismMireia Leon-Dasi0Sebastien Besse1Alain Doressoundiram2LESIA, Observatoire de Paris, Université PSL, CNRS, 5 Place Jules Janssen, 92195 Meudon, FranceEuropean Space Agency (ESA), European Space Astronomy Centre (ESAC), Camino Bajo del Castillo s/n, Villanueva de la Cañada, 28692 Madrid, SpainLESIA, Observatoire de Paris, Université PSL, CNRS, 5 Place Jules Janssen, 92195 Meudon, FranceThe remnants of explosive volcanism on Mercury have been observed in the form of vents and pyroclastic deposits, termed faculae, using data from the Mercury Atmospheric and Surface Composition Spectrometer (MASCS) onboard the Mercury surface, space environment, geochemistry, and ranging (MESSENGER) spacecraft. Although these features present a wide variety of sizes, shapes, and spectral properties, the large number of observations and the lack of high-resolution hyperspectral images complicates their detailed characterisation. We investigate the application of unsupervised deep learning to explore the diversity and constrain the extent of the Hermean pyroclastic deposits. We use a three-dimensional convolutional autoencoder (3DCAE) to extract the spectral and spatial attributes that characterise these features and to create cluster maps constructing a unique framework to compare different deposits. From the cluster maps we define the boundaries of 55 irregular deposits covering 110 vents and compare the results with previous radius and surface estimates. We find that the network is capable of extracting spatial information such as the border of the faculae, and spectral information to altogether highlight the pyroclastic deposits from the background terrain. Overall, we find the 3DCAE an effective technique to analyse sparse observations in planetary sciences.https://www.mdpi.com/2072-4292/15/18/4560mercuryvolcanismpyroclasticdeep learningautoencoderhyperspectral image |
spellingShingle | Mireia Leon-Dasi Sebastien Besse Alain Doressoundiram Deep Learning Investigation of Mercury’s Explosive Volcanism Remote Sensing mercury volcanism pyroclastic deep learning autoencoder hyperspectral image |
title | Deep Learning Investigation of Mercury’s Explosive Volcanism |
title_full | Deep Learning Investigation of Mercury’s Explosive Volcanism |
title_fullStr | Deep Learning Investigation of Mercury’s Explosive Volcanism |
title_full_unstemmed | Deep Learning Investigation of Mercury’s Explosive Volcanism |
title_short | Deep Learning Investigation of Mercury’s Explosive Volcanism |
title_sort | deep learning investigation of mercury s explosive volcanism |
topic | mercury volcanism pyroclastic deep learning autoencoder hyperspectral image |
url | https://www.mdpi.com/2072-4292/15/18/4560 |
work_keys_str_mv | AT mireialeondasi deeplearninginvestigationofmercurysexplosivevolcanism AT sebastienbesse deeplearninginvestigationofmercurysexplosivevolcanism AT alaindoressoundiram deeplearninginvestigationofmercurysexplosivevolcanism |