Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system
ABSTRACTA deep learning (DL) terrain classification system, the Novelty and Anomaly Hunter – HiRISE (NOAH-H) was used to produce a terrain map of Mawrth Vallis, Mars. With it, we digitised the extent and distribution of transverse aeolian ridges (TARs), a common type of martian aeolian bedform. We p...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Journal of Maps |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17445647.2023.2285480 |
| _version_ | 1827320816689217536 |
|---|---|
| author | Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Jack Wright Mark J. Woods Spyros Karachalios Eleni Bohacek Levin Gerdes Elliot Sefton-Nash Luc Joudrier |
| author_facet | Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Jack Wright Mark J. Woods Spyros Karachalios Eleni Bohacek Levin Gerdes Elliot Sefton-Nash Luc Joudrier |
| author_sort | Alexander M. Barrett |
| collection | DOAJ |
| description | ABSTRACTA deep learning (DL) terrain classification system, the Novelty and Anomaly Hunter – HiRISE (NOAH-H) was used to produce a terrain map of Mawrth Vallis, Mars. With it, we digitised the extent and distribution of transverse aeolian ridges (TARs), a common type of martian aeolian bedform. We present maps of the site, classifying terrain into descriptive classes and interpretive groups. TAR density maps are calculated, and the network output is compared to a manually produced map of TAR density, highlighting the differences in approach and results between these methods. Even when mapping on a small scale, humans must divide the terrain into coherent patches in order to map a large area in a reasonable time frame. Conversely, the speed of DL systems enables mapping on the pixel scale, producing a more detailed product, but one which is also “noisier”, and less immediately informative. There are pros and cons to both approaches. |
| first_indexed | 2024-03-09T14:22:30Z |
| format | Article |
| id | doaj.art-3988af3368c04a44860e21ebcfff5a31 |
| institution | Directory Open Access Journal |
| issn | 1744-5647 |
| language | English |
| last_indexed | 2024-04-25T00:53:40Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Maps |
| spelling | doaj.art-3988af3368c04a44860e21ebcfff5a312024-03-11T14:20:25ZengTaylor & Francis GroupJournal of Maps1744-56472023-12-0119110.1080/17445647.2023.2285480Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification systemAlexander M. Barrett0Peter Fawdon1Elena A. Favaro2Matthew R. Balme3Jack Wright4Mark J. Woods5Spyros Karachalios6Eleni Bohacek7Levin Gerdes8Elliot Sefton-Nash9Luc Joudrier10School of Physical Sciences, The Open University, Milton Keynes, UKSchool of Physical Sciences, The Open University, Milton Keynes, UKSchool of Physical Sciences, The Open University, Milton Keynes, UKSchool of Physical Sciences, The Open University, Milton Keynes, UKSchool of Physical Sciences, The Open University, Milton Keynes, UKSCISYS Ltd, Methuen Park, Chippenham, UKSCISYS Ltd, Methuen Park, Chippenham, UKEuropean Space Agency (ESA), European Space Research and Technology Centre (ESTEC), Noordwijk, NetherlandsEuropean Space Agency (ESA), European Space Research and Technology Centre (ESTEC), Noordwijk, NetherlandsEuropean Space Agency (ESA), European Space Research and Technology Centre (ESTEC), Noordwijk, NetherlandsEuropean Space Agency (ESA), European Space Research and Technology Centre (ESTEC), Noordwijk, NetherlandsABSTRACTA deep learning (DL) terrain classification system, the Novelty and Anomaly Hunter – HiRISE (NOAH-H) was used to produce a terrain map of Mawrth Vallis, Mars. With it, we digitised the extent and distribution of transverse aeolian ridges (TARs), a common type of martian aeolian bedform. We present maps of the site, classifying terrain into descriptive classes and interpretive groups. TAR density maps are calculated, and the network output is compared to a manually produced map of TAR density, highlighting the differences in approach and results between these methods. Even when mapping on a small scale, humans must divide the terrain into coherent patches in order to map a large area in a reasonable time frame. Conversely, the speed of DL systems enables mapping on the pixel scale, producing a more detailed product, but one which is also “noisier”, and less immediately informative. There are pros and cons to both approaches.https://www.tandfonline.com/doi/10.1080/17445647.2023.2285480Marsmachine learningMawrth VallisExoMars |
| spellingShingle | Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Jack Wright Mark J. Woods Spyros Karachalios Eleni Bohacek Levin Gerdes Elliot Sefton-Nash Luc Joudrier Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system Journal of Maps Mars machine learning Mawrth Vallis ExoMars |
| title | Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system |
| title_full | Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system |
| title_fullStr | Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system |
| title_full_unstemmed | Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system |
| title_short | Mawrth Vallis, Mars, classified using the NOAH-H deep-learning terrain classification system |
| title_sort | mawrth vallis mars classified using the noah h deep learning terrain classification system |
| topic | Mars machine learning Mawrth Vallis ExoMars |
| url | https://www.tandfonline.com/doi/10.1080/17445647.2023.2285480 |
| work_keys_str_mv | AT alexandermbarrett mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT peterfawdon mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT elenaafavaro mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT matthewrbalme mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT jackwright mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT markjwoods mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT spyroskarachalios mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT elenibohacek mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT levingerdes mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT elliotseftonnash mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem AT lucjoudrier mawrthvallismarsclassifiedusingthenoahhdeeplearningterrainclassificationsystem |