A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images

Understanding rock hardness on extraterrestrial planets offers valuable insights into planetary geological evolution. Rock hardness correlates with morphological parameters, which can be extracted from navigation images, bypassing the time and cost of rock sampling and return. This research proposes...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuyun Liu, Haifeng Zhao, Zihao Yuan, Liping Xiao, Chengcheng Shen, Xue Wan, Xuhai Tang, Lu Zhang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/12/1/26
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589503711150080
author Shuyun Liu
Haifeng Zhao
Zihao Yuan
Liping Xiao
Chengcheng Shen
Xue Wan
Xuhai Tang
Lu Zhang
author_facet Shuyun Liu
Haifeng Zhao
Zihao Yuan
Liping Xiao
Chengcheng Shen
Xue Wan
Xuhai Tang
Lu Zhang
author_sort Shuyun Liu
collection DOAJ
description Understanding rock hardness on extraterrestrial planets offers valuable insights into planetary geological evolution. Rock hardness correlates with morphological parameters, which can be extracted from navigation images, bypassing the time and cost of rock sampling and return. This research proposes a machine-learning approach to predict extraterrestrial rock hardness using morphological features. A custom dataset of 1496 rock images, including granite, limestone, basalt, and sandstone, was created. Ten features, such as roundness, elongation, convexity, and Lab color values, were extracted for prediction. A foundational model combining Random Forest (RF) and Support Vector Regression (SVR) was trained through cross-validation. The output of this model was used as the input for a meta-model, undergoing linear fitting to predict Mohs hardness, forming the Meta-Random Forest and Support Vector Regression (MRFSVR) model. The model achieved an R<sup>2</sup> of 0.8219, an MSE of 0.2514, and a mean absolute error of 0.2431 during validation. Meteorite samples were used to validate the MRFSVR model’s predictions. The model is used to predict the hardness distribution of extraterrestrial rocks using images from the Tianwen-1 Mars Rover Navigation and Terrain Camera (NaTeCam) and a simulated lunar rock dataset from an open-source website. The results demonstrate the method’s potential for enhancing extraterrestrial exploration.
format Article
id doaj-art-d4b6d54f6a16455b8e2eae8eb2718ddc
institution Kabale University
issn 2226-4310
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-d4b6d54f6a16455b8e2eae8eb2718ddc2025-01-24T13:15:30ZengMDPI AGAerospace2226-43102024-12-011212610.3390/aerospace12010026A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital ImagesShuyun Liu0Haifeng Zhao1Zihao Yuan2Liping Xiao3Chengcheng Shen4Xue Wan5Xuhai Tang6Lu Zhang7University of Chinese Academy of Sciences, Beijing 100039, ChinaUniversity of Chinese Academy of Sciences, Beijing 100039, ChinaTechnology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, ChinaUniversity of Chinese Academy of Sciences, Beijing 100039, ChinaUniversity of Chinese Academy of Sciences, Beijing 100039, ChinaUniversity of Chinese Academy of Sciences, Beijing 100039, ChinaSchool of Civil Engineering, Wuhan University, Wuhan 430072, ChinaTechnology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, ChinaUnderstanding rock hardness on extraterrestrial planets offers valuable insights into planetary geological evolution. Rock hardness correlates with morphological parameters, which can be extracted from navigation images, bypassing the time and cost of rock sampling and return. This research proposes a machine-learning approach to predict extraterrestrial rock hardness using morphological features. A custom dataset of 1496 rock images, including granite, limestone, basalt, and sandstone, was created. Ten features, such as roundness, elongation, convexity, and Lab color values, were extracted for prediction. A foundational model combining Random Forest (RF) and Support Vector Regression (SVR) was trained through cross-validation. The output of this model was used as the input for a meta-model, undergoing linear fitting to predict Mohs hardness, forming the Meta-Random Forest and Support Vector Regression (MRFSVR) model. The model achieved an R<sup>2</sup> of 0.8219, an MSE of 0.2514, and a mean absolute error of 0.2431 during validation. Meteorite samples were used to validate the MRFSVR model’s predictions. The model is used to predict the hardness distribution of extraterrestrial rocks using images from the Tianwen-1 Mars Rover Navigation and Terrain Camera (NaTeCam) and a simulated lunar rock dataset from an open-source website. The results demonstrate the method’s potential for enhancing extraterrestrial exploration.https://www.mdpi.com/2226-4310/12/1/26extraterrestrial explorationrock hardnessmachine learningimage recognitionmeta learningRandom Forest
spellingShingle Shuyun Liu
Haifeng Zhao
Zihao Yuan
Liping Xiao
Chengcheng Shen
Xue Wan
Xuhai Tang
Lu Zhang
A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
Aerospace
extraterrestrial exploration
rock hardness
machine learning
image recognition
meta learning
Random Forest
title A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
title_full A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
title_fullStr A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
title_full_unstemmed A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
title_short A Machine Learning Approach for the Autonomous Identification of Hardness in Extraterrestrial Rocks from Digital Images
title_sort machine learning approach for the autonomous identification of hardness in extraterrestrial rocks from digital images
topic extraterrestrial exploration
rock hardness
machine learning
image recognition
meta learning
Random Forest
url https://www.mdpi.com/2226-4310/12/1/26
work_keys_str_mv AT shuyunliu amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT haifengzhao amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT zihaoyuan amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT lipingxiao amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT chengchengshen amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT xuewan amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT xuhaitang amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT luzhang amachinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT shuyunliu machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT haifengzhao machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT zihaoyuan machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT lipingxiao machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT chengchengshen machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT xuewan machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT xuhaitang machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages
AT luzhang machinelearningapproachfortheautonomousidentificationofhardnessinextraterrestrialrocksfromdigitalimages