Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system
We applied a deep learning terrain classification system, the ‘Novelty or Anomaly Hunter – HiRISE’ (NOAH-H), originally developed for the ExoMars landing sites in Oxia Planum and Mawrth Vallis, to the Mars 2020 Perseverance rover landing site in Jezero crater. NOAH-H successfully classified the terr...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-08-01
|
| Series: | Journal of Maps |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17445647.2022.2095935 |
| _version_ | 1818496236356894720 |
|---|---|
| author | Jack Wright Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Mark J. Woods Spyros Karachalios |
| author_facet | Jack Wright Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Mark J. Woods Spyros Karachalios |
| author_sort | Jack Wright |
| collection | DOAJ |
| description | We applied a deep learning terrain classification system, the ‘Novelty or Anomaly Hunter – HiRISE’ (NOAH-H), originally developed for the ExoMars landing sites in Oxia Planum and Mawrth Vallis, to the Mars 2020 Perseverance rover landing site in Jezero crater. NOAH-H successfully classified the terrain in four HiRISE images of Jezero even though the landforms in the Jezero study area were slightly different from those in the training dataset. We mosaicked the NOAH-H classified rasters and compared them with a manually generated photogeological map, and with Perseverance rover and Ingenuity helicopter images. We find that grouped NOAH-H classes correspond well with the humanmade map and that individual classes are corroborated by the available ground-truth images. We conclude that our NOAH-H products can be refined for feeding into traversability analysis of the ExoMars Rosalind Franklin rover landing site at Oxia Planum and that they can also be used to aid the photogeological mapping process. |
| first_indexed | 2024-12-10T18:30:48Z |
| format | Article |
| id | doaj.art-bc74cfe2e30e403d8110e165f06b0be3 |
| institution | Directory Open Access Journal |
| issn | 1744-5647 |
| language | English |
| last_indexed | 2024-12-10T18:30:48Z |
| publishDate | 2022-08-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Maps |
| spelling | doaj.art-bc74cfe2e30e403d8110e165f06b0be32022-12-22T01:37:57ZengTaylor & Francis GroupJournal of Maps1744-56472022-08-0111310.1080/17445647.2022.2095935Jezero crater, Mars: application of the deep learning NOAH-H terrain classification systemJack Wright0Alexander M. Barrett1Peter Fawdon2Elena A. Favaro3Matthew R. Balme4Mark J. Woods5Spyros Karachalios6European Space Agency (ESA), European Space Astronomy Centre (ESAC), Madrid, SpainSchool 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, Chippenham, UKSCISYS Ltd, Chippenham, UKWe applied a deep learning terrain classification system, the ‘Novelty or Anomaly Hunter – HiRISE’ (NOAH-H), originally developed for the ExoMars landing sites in Oxia Planum and Mawrth Vallis, to the Mars 2020 Perseverance rover landing site in Jezero crater. NOAH-H successfully classified the terrain in four HiRISE images of Jezero even though the landforms in the Jezero study area were slightly different from those in the training dataset. We mosaicked the NOAH-H classified rasters and compared them with a manually generated photogeological map, and with Perseverance rover and Ingenuity helicopter images. We find that grouped NOAH-H classes correspond well with the humanmade map and that individual classes are corroborated by the available ground-truth images. We conclude that our NOAH-H products can be refined for feeding into traversability analysis of the ExoMars Rosalind Franklin rover landing site at Oxia Planum and that they can also be used to aid the photogeological mapping process.https://www.tandfonline.com/doi/10.1080/17445647.2022.2095935Mars’ surfacegeomorphologyJezero cratermachine learningdeep learningrover planning |
| spellingShingle | Jack Wright Alexander M. Barrett Peter Fawdon Elena A. Favaro Matthew R. Balme Mark J. Woods Spyros Karachalios Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system Journal of Maps Mars’ surface geomorphology Jezero crater machine learning deep learning rover planning |
| title | Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system |
| title_full | Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system |
| title_fullStr | Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system |
| title_full_unstemmed | Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system |
| title_short | Jezero crater, Mars: application of the deep learning NOAH-H terrain classification system |
| title_sort | jezero crater mars application of the deep learning noah h terrain classification system |
| topic | Mars’ surface geomorphology Jezero crater machine learning deep learning rover planning |
| url | https://www.tandfonline.com/doi/10.1080/17445647.2022.2095935 |
| work_keys_str_mv | AT jackwright jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT alexandermbarrett jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT peterfawdon jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT elenaafavaro jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT matthewrbalme jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT markjwoods jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem AT spyroskarachalios jezerocratermarsapplicationofthedeeplearningnoahhterrainclassificationsystem |