Planet Four: A Neural Network’s search for polar spring-time fans on Mars
Dark deposits visible from orbit appear in the Martian south polar region during the springtime. These are thought to form from explosive jets of carbon dioxide gas breaking through the thawing seasonal ice cap, carrying dust and dirt which is then deposited onto the ice as dark ‘blotches’, or blown...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://refubium.fu-berlin.de/handle/fub188/37999 https://doi.org/10.17169/refubium-37715 https://doi.org/10.1016/j.icarus.2022.115308 |
id |
ftfuberlin:oai:refubium.fu-berlin.de:fub188/37999 |
---|---|
record_format |
openpolar |
spelling |
ftfuberlin:oai:refubium.fu-berlin.de:fub188/37999 2023-05-15T16:38:18+02:00 Planet Four: A Neural Network’s search for polar spring-time fans on Mars McDonnell, Mark D. Jones, Eriita Schwamb, Megan E. Aye, K.-Michael Portyankina, Ganna Hansen, Candice J. 2023 20 Seiten application/pdf https://refubium.fu-berlin.de/handle/fub188/37999 https://doi.org/10.17169/refubium-37715 https://doi.org/10.1016/j.icarus.2022.115308 eng eng https://refubium.fu-berlin.de/handle/fub188/37999 http://dx.doi.org/10.17169/refubium-37715 doi:10.1016/j.icarus.2022.115308 https://creativecommons.org/licenses/by/4.0/ CC-BY Mars Machine learning Classification Surface ddc:520 doc-type:article 2023 ftfuberlin https://doi.org/10.17169/refubium-37715 https://doi.org/10.1016/j.icarus.2022.115308 2023-02-26T23:24:42Z Dark deposits visible from orbit appear in the Martian south polar region during the springtime. These are thought to form from explosive jets of carbon dioxide gas breaking through the thawing seasonal ice cap, carrying dust and dirt which is then deposited onto the ice as dark ‘blotches’, or blown by the surface winds into streaks or ‘fans’. We investigate machine learning (ML) methods for automatically identifying these seasonal features in High Resolution Imaging Science Experiment (HiRISE) satellite imagery. We designed deep Convolutional Neural Networks (CNNs) that were trained and tested using the catalog generated by Planet Four, an online citizen science project mapping the south polar seasonal deposits. We validated the CNNs by comparing their results with those of ISODATA (Iterative Self-Organizing Data Analysis Technique) clustering and as expected, the CNNs were significantly better at predicting the results found by Planet Four, in both the area of predicted seasonal deposits and in delineating their boundaries. We found neither the CNNs or ISODATA were suited to predicting the source point and directions of seasonal fans, which is a strength of the citizen science approach. The CNNs showed good agreement with Planet Four in cross-validation metrics and detected some seasonal deposits in the HiRISE images missed in the Planet Four catalog; the total area of seasonal deposits predicted by the CNNs was 27% larger than that of the Planet Four catalog, but this aspect varied considerably on a per-image basis. Article in Journal/Newspaper Ice cap Freie Universität Berlin: Refubium (FU Berlin) |
institution |
Open Polar |
collection |
Freie Universität Berlin: Refubium (FU Berlin) |
op_collection_id |
ftfuberlin |
language |
English |
topic |
Mars Machine learning Classification Surface ddc:520 |
spellingShingle |
Mars Machine learning Classification Surface ddc:520 McDonnell, Mark D. Jones, Eriita Schwamb, Megan E. Aye, K.-Michael Portyankina, Ganna Hansen, Candice J. Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
topic_facet |
Mars Machine learning Classification Surface ddc:520 |
description |
Dark deposits visible from orbit appear in the Martian south polar region during the springtime. These are thought to form from explosive jets of carbon dioxide gas breaking through the thawing seasonal ice cap, carrying dust and dirt which is then deposited onto the ice as dark ‘blotches’, or blown by the surface winds into streaks or ‘fans’. We investigate machine learning (ML) methods for automatically identifying these seasonal features in High Resolution Imaging Science Experiment (HiRISE) satellite imagery. We designed deep Convolutional Neural Networks (CNNs) that were trained and tested using the catalog generated by Planet Four, an online citizen science project mapping the south polar seasonal deposits. We validated the CNNs by comparing their results with those of ISODATA (Iterative Self-Organizing Data Analysis Technique) clustering and as expected, the CNNs were significantly better at predicting the results found by Planet Four, in both the area of predicted seasonal deposits and in delineating their boundaries. We found neither the CNNs or ISODATA were suited to predicting the source point and directions of seasonal fans, which is a strength of the citizen science approach. The CNNs showed good agreement with Planet Four in cross-validation metrics and detected some seasonal deposits in the HiRISE images missed in the Planet Four catalog; the total area of seasonal deposits predicted by the CNNs was 27% larger than that of the Planet Four catalog, but this aspect varied considerably on a per-image basis. |
format |
Article in Journal/Newspaper |
author |
McDonnell, Mark D. Jones, Eriita Schwamb, Megan E. Aye, K.-Michael Portyankina, Ganna Hansen, Candice J. |
author_facet |
McDonnell, Mark D. Jones, Eriita Schwamb, Megan E. Aye, K.-Michael Portyankina, Ganna Hansen, Candice J. |
author_sort |
McDonnell, Mark D. |
title |
Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
title_short |
Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
title_full |
Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
title_fullStr |
Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
title_full_unstemmed |
Planet Four: A Neural Network’s search for polar spring-time fans on Mars |
title_sort |
planet four: a neural network’s search for polar spring-time fans on mars |
publishDate |
2023 |
url |
https://refubium.fu-berlin.de/handle/fub188/37999 https://doi.org/10.17169/refubium-37715 https://doi.org/10.1016/j.icarus.2022.115308 |
genre |
Ice cap |
genre_facet |
Ice cap |
op_relation |
https://refubium.fu-berlin.de/handle/fub188/37999 http://dx.doi.org/10.17169/refubium-37715 doi:10.1016/j.icarus.2022.115308 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.17169/refubium-37715 https://doi.org/10.1016/j.icarus.2022.115308 |
_version_ |
1766028580287938560 |