Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars
Martian chaos terrains are fractured depressions consisting of block landforms that are often located in source areas of outflow channels. Numerous chaos and chaos-like features have been found on Mars; however, a global-scale classification has not been pursued. Here, we perform recognition and cla...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/3883 |
| _version_ | 1797431757708984320 |
|---|---|
| author | Hiroki Shozaki Yasuhito Sekine Nicholas Guttenberg Goro Komatsu |
| author_facet | Hiroki Shozaki Yasuhito Sekine Nicholas Guttenberg Goro Komatsu |
| author_sort | Hiroki Shozaki |
| collection | DOAJ |
| description | Martian chaos terrains are fractured depressions consisting of block landforms that are often located in source areas of outflow channels. Numerous chaos and chaos-like features have been found on Mars; however, a global-scale classification has not been pursued. Here, we perform recognition and classification of Martian chaos using imagery machine learning. We developed neural network models to classify block landforms commonly found in chaos terrains—which are associated with outflow channels formed by water activity (referred to as Aromatum-Hydraotes-Oxia-like (or AHO) chaos blocks) or with geological features suggesting volcanic activity (Arsinoes-Pyrrhae-like (or AP) chaos blocks)—and also non-chaos surface features, based on >1400 surface images. Our models can recognize chaos and non-chaos features with 93.9% ± 0.3% test accuracy, and they can be used to classify both AHO and AP chaos blocks with >89 ± 4% test accuracy. By applying our models to ~3150 images of block landforms of chaos-like features, we identified 2 types of chaos terrain. These include hybrid chaos terrain, where AHO and AP chaos blocks co-exist in one basin, and AHO-dominant chaos terrain. Hybrid chaos terrains are predominantly found in the circum-Chryse outflow channels region. AHO-dominant chaos terrains are widely distributed across Aeolis, Cydonia, and Nepenthes Mensae along the dichotomy boundary. Their locations coincide with regions suggested to exhibit upwelling groundwater on Hesperian Mars. |
| first_indexed | 2024-03-09T09:49:56Z |
| format | Article |
| id | doaj.art-5d480a71a58b42a0a7da3346da9569de |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T09:49:56Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5d480a71a58b42a0a7da3346da9569de2023-12-02T00:14:45ZengMDPI AGRemote Sensing2072-42922022-08-011416388310.3390/rs14163883Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on MarsHiroki Shozaki0Yasuhito Sekine1Nicholas Guttenberg2Goro Komatsu3Earth-Life Science Institute (ELSI), Tokyo Institute of Technology, Meguro, Tokyo 152-8550, JapanEarth-Life Science Institute (ELSI), Tokyo Institute of Technology, Meguro, Tokyo 152-8550, JapanEarth-Life Science Institute (ELSI), Tokyo Institute of Technology, Meguro, Tokyo 152-8550, JapanInternational Research School of Planetary Sciences, Università d’Annunzio, 65127 Pescara, ItalyMartian chaos terrains are fractured depressions consisting of block landforms that are often located in source areas of outflow channels. Numerous chaos and chaos-like features have been found on Mars; however, a global-scale classification has not been pursued. Here, we perform recognition and classification of Martian chaos using imagery machine learning. We developed neural network models to classify block landforms commonly found in chaos terrains—which are associated with outflow channels formed by water activity (referred to as Aromatum-Hydraotes-Oxia-like (or AHO) chaos blocks) or with geological features suggesting volcanic activity (Arsinoes-Pyrrhae-like (or AP) chaos blocks)—and also non-chaos surface features, based on >1400 surface images. Our models can recognize chaos and non-chaos features with 93.9% ± 0.3% test accuracy, and they can be used to classify both AHO and AP chaos blocks with >89 ± 4% test accuracy. By applying our models to ~3150 images of block landforms of chaos-like features, we identified 2 types of chaos terrain. These include hybrid chaos terrain, where AHO and AP chaos blocks co-exist in one basin, and AHO-dominant chaos terrain. Hybrid chaos terrains are predominantly found in the circum-Chryse outflow channels region. AHO-dominant chaos terrains are widely distributed across Aeolis, Cydonia, and Nepenthes Mensae along the dichotomy boundary. Their locations coincide with regions suggested to exhibit upwelling groundwater on Hesperian Mars.https://www.mdpi.com/2072-4292/14/16/3883Marsmachine learningchaosground iceoutflow channelclassification |
| spellingShingle | Hiroki Shozaki Yasuhito Sekine Nicholas Guttenberg Goro Komatsu Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars Remote Sensing Mars machine learning chaos ground ice outflow channel classification |
| title | Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars |
| title_full | Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars |
| title_fullStr | Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars |
| title_full_unstemmed | Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars |
| title_short | Recognition and Classification of Martian Chaos Terrains Using Imagery Machine Learning: A Global Distribution of Chaos Linked to Groundwater Circulation, Catastrophic Flooding, and Magmatism on Mars |
| title_sort | recognition and classification of martian chaos terrains using imagery machine learning a global distribution of chaos linked to groundwater circulation catastrophic flooding and magmatism on mars |
| topic | Mars machine learning chaos ground ice outflow channel classification |
| url | https://www.mdpi.com/2072-4292/14/16/3883 |
| work_keys_str_mv | AT hirokishozaki recognitionandclassificationofmartianchaosterrainsusingimagerymachinelearningaglobaldistributionofchaoslinkedtogroundwatercirculationcatastrophicfloodingandmagmatismonmars AT yasuhitosekine recognitionandclassificationofmartianchaosterrainsusingimagerymachinelearningaglobaldistributionofchaoslinkedtogroundwatercirculationcatastrophicfloodingandmagmatismonmars AT nicholasguttenberg recognitionandclassificationofmartianchaosterrainsusingimagerymachinelearningaglobaldistributionofchaoslinkedtogroundwatercirculationcatastrophicfloodingandmagmatismonmars AT gorokomatsu recognitionandclassificationofmartianchaosterrainsusingimagerymachinelearningaglobaldistributionofchaoslinkedtogroundwatercirculationcatastrophicfloodingandmagmatismonmars |