science_cases:gmap_science_cases:landforms
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
science_cases:gmap_science_cases:landforms [2022/02/28 11:29] – admin | science_cases:gmap_science_cases:landforms [2022/10/20 14:02] (current) – admin | ||
---|---|---|---|
Line 5: | Line 5: | ||
This science case is focused on the detection and mapping of sinkhole-like depressions on Mars and the Moon through Deep Learning Object Detection and Instance Segmentation. | This science case is focused on the detection and mapping of sinkhole-like depressions on Mars and the Moon through Deep Learning Object Detection and Instance Segmentation. | ||
- | The term sinkhole refers to different morphologies that have a in common the processes of depleting materials of different type into an area within the morphology itself (Waltham, 2005). On Earth the formation of sinkholes is related to a cluster of processes, and could occur in various type of grounds, furthermore presence of water has a key-role. On other terrestrial planets, although the mechanisms for the origin of these landforms are similar, if not the same, with the main difference that as far as we know there is no liquid water that can be involved in the formation of these landforms, and therefore the mechanisms and processes are still debated. Several authors suggested the hypothesis of formation from lava tube collapses (Greeley, 1971; Cruikshank and , 1972; Carr et al., 1977), others imply different volcanic and tectonic processes involved (Wyrick et al., 2004). In karst environment, | + | The term sinkhole refers to different morphologies that have a in common the processes of depleting materials of different type into an area within the morphology itself (Waltham, 2005). On Earth the formation of sinkholes is related to a cluster of processes, and could occur in various type of grounds, furthermore presence of water has a key-role. On other terrestrial planets, although the mechanisms for the origin of these landforms are similar, if not the same, with the main difference that as far as we know there is no liquid water that can be involved in the formation of these landforms, and therefore the mechanisms and processes are still debated. Several authors suggested the hypothesis of formation from lava tube collapses (Greeley, 1971; Cruikshank and Wood, 1972; Carr et al., 1977), others imply different volcanic and tectonic processes involved (Wyrick et al., 2004). In karst environment, |
- | Doline, pit craters, pit chains and lava tubes are well-known morphologies on Earth (Lauterbach et al., 2019; Díaz Michelena et al., 2020), Mars (Carr, | + | Doline, pit craters, pit chains and lava tubes are well-known morphologies on Earth (Lauterbach et al., 2019; Díaz Michelena et al., 2020), Mars (Carr, |
- | In the framework of geological exploration of terrestrial planets like Earth, those landforms - being a potential direct access to subsurface - are one of the most promising environments where to focus the research of valuable data of different kind, from planet' | + | In the framework of geological exploration of terrestrial planets like Earth, those landforms - being a potential direct access to subsurface - are one of the most promising environments where to focus the research of valuable data of different kind, from planet' |
Detecting, mapping, and describing sinkhole-like landform is a challenging process since a set of tedious tasks must be conducted manually, from data collection to manual analysis, mapping using Geographic Information Systems (GIS) software and extracting morphometric parameters. | Detecting, mapping, and describing sinkhole-like landform is a challenging process since a set of tedious tasks must be conducted manually, from data collection to manual analysis, mapping using Geographic Information Systems (GIS) software and extracting morphometric parameters. | ||
- | For Mars, there exists a downloadable database of more than 1000 cave candidates (Cushing, | + | For Mars, there exists a downloadable database of more than 1000 cave candidates (Cushing, |
* Type-1: Skylight with possible cave entrance, flat rim, no ejecta blankets, almost perfect circular shape and no visible bottom. | * Type-1: Skylight with possible cave entrance, flat rim, no ejecta blankets, almost perfect circular shape and no visible bottom. | ||
Line 34: | Line 34: | ||
===== Details about the data ===== | ===== Details about the data ===== | ||
- | Mars optical images are provided by the MRO spacecraft, and are composed of: | + | Mars optical images are provided by the Martian Reconnaissance Orbiter (MRO), and are composed of: |
* HiRISE images: a very high spatial resolution instrument with 0.3 m/pixel and a swath of approximately 30 km-wide. This instrument provides the highest quality images captured of Mars, designed for retrieving fine details from surface. The dataset used for preliminary tests consist of approx. 900 images. | * HiRISE images: a very high spatial resolution instrument with 0.3 m/pixel and a swath of approximately 30 km-wide. This instrument provides the highest quality images captured of Mars, designed for retrieving fine details from surface. The dataset used for preliminary tests consist of approx. 900 images. | ||
Line 46: | Line 46: | ||
All data can be accessed through NASA PDS Geoscience Node ODE Portal. | All data can be accessed through NASA PDS Geoscience Node ODE Portal. | ||
- | ===== Description of the machine learning problem ===== | + | ===== Description of the machine learning problem |
- | Considering the five classes that have been identified and taking into account their similarities within each other, the problem could be described as a multi-label multi-class object detection problem. The data consist of all images, the best suitable approach is Deep Learning since it is widely applied on Earth for similar problems and could be adapted easily to different targets. | + | Considering the five classes that have been identified and taking into account their similarities within each other, the problem could be described as a multi-label multi-class object detection problem. The data consist of all images, the best suitable approach is Deep Learning since it is widely applied on Earth for similar problems and could be adapted easily to different targets. \\ Several Deep Learning object detection algorithms exits, in addition to open source framework based on Python and C/C++ programming language. |
- | \\ Several | + | Without entering in the depth of Deep Learning, |
- | \\ Without entering in the depth of Deep Learning, abstraction problem | + | Training results are strictly related to data set dimension and labeling quality, and this is the major problematic |
- | \\ Training results are strictly related | + | As a first step, a **deep learning object detection algorithm YOLO** |
+ | |||
+ | To improve the results obtained by this first tool for automated mapping of pits, a change of architecture was necessary. The results obtained by that tool, despite their high quality, | ||
+ | |||
+ | Since this is a highly time-consuming | ||
+ | |||
+ | {{: | ||
+ | |||
+ | **References: | ||
+ | |||
+ | * Barlow, N. G., Ferguson, S. N., Horstman, R. M., Maine, A. (2017) ' | ||
+ | * Baioni, D. and Tramontana, M. (2015) ‘Evaporite karst in three interior layered deposits in Iani Chaos, Mars’, Geomorphology 245, 15–22. doi: 10.1016/ | ||
+ | * Baioni, D. and Tramontana, M. (2016) Possible karst landforms in two unnamed craters in Tyrrhena Terra, Mars, Planetary and Space Science. doi: 10.1016/ | ||
+ | * Blamont, J. (2014) ‘A roadmap | ||
+ | * Carr, M. H. et al. (1977) ‘Some Martian volcanic features as viewed from the Viking orbiters’, | ||
+ | * Carrer, L., Gerekos, C. and Bruzzone, L. (2018) ‘A multi-frequency radar sounder for lava tubes detection on the Moon: Design, performance assessment and simulations’, | ||
+ | * Chappaz, L. et al. (2017) ‘Evidence of large empty lava tubes on the Moon using GRAIL gravity’, Geophysical Research Letters 44(1), 105–112. doi: 10.1002/ | ||
+ | * Cruikshank, D. P. and Wodd, C. A. (1972) ‘Lunar Rilles and Hawaiian Volcanic Features: Possible Analogues’, | ||
+ | * Cushing, G. E. et al. (2007) ‘THEMIS observes possible cave skylights on Mars’, Geophysical Research Letters. doi: 10.1029/ | ||
+ | * Cushing, G. E. (2012) ‘Candidate cave entrances on Mars’, Journal of Cave and Karst Studies, 74(1), 33– 47. doi: 10.4311/ | ||
+ | * Cushing, G. E. (2017) ‘MARS GLOBAL CAVE CANDIDATE CATALOG (MGC3)’, 2017(1965), 86001. | ||
+ | * Cushing, G. E., Okubo, C. H. and Titus, T. N. (2015) ‘Atypical pit craters on Mars: New insights from THEMIS, CTX, and HiRISE observations’, | ||
+ | * Díaz Michelena, M. et al. (2020) ‘The formation of a giant collapse caprock sinkhole on the Barda Negra plateau basalts (Argentina): | ||
+ | * Sawford, W .C., Ernst, R. E., Samson, C. and Davey, S. (2015) ‘Pit Crater Chains in the Nyx Mons Region, Venus’, pp. 1283, 46th Annual Lunar and Planetary Science Conference. | ||
+ | * Gillis-Davis, | ||
+ | * Greeley, R. (1971) ‘Lava tubes and channels in the lunar Marius Hills’, The Moon 3(3), 289–314. doi: 10.1007/ | ||
+ | * Hare, T. M. et al. (2018) ‘Interoperability in planetary research for geospatial data analysis’, | ||
+ | * Lauterbach, H. A. et al. (2019) ‘MOBILE MAPPING of the la CORONA LAVATUBE on LANZAROTE’, | ||
+ | * PDS Geosciences Nodes (2020) PDS Geosciences Node Orbital Data Explorer (ODE). Available at: [[https:// | ||
+ | * Sauro, F. et al. (2020a) ‘Lava tubes on Earth, Moon and Mars: A review on their size and morphology revealed by comparative planetology’, | ||
+ | * Léveillé, R. J., and S. Datta (2010) 'Lava tubes and basaltic caves as astrobiological targets on Earth and Mars: A review', | ||
+ | * Wyrick, D. et al. (2004) ‘Distribution, | ||
+ | * Waltham, T. (2005) ‘Sinkhole classification and nomenclature’, | ||
+ | * Wagner, R. V. and Robinson, M. S. (2014) ' | ||
+ | * Nodjoumi, G., DeepLandforms-YOLOv5. Available online: [[https:// | ||
science_cases/gmap_science_cases/landforms.1646044175.txt.gz · Last modified: 2022/02/28 11:29 by admin