月球撞击坑形态特征的多维度聚类方法研究

doi:10.11871/jfdc.issn.2096-742X.2025.04.008

数据与计算发展前沿 ›› 2025, Vol. 7 ›› Issue (4): 89-100.

CSTR: 32002.14.jfdc.CN10-1649/TP.2025.04.008

doi: 10.11871/jfdc.issn.2096-742X.2025.04.008

• 专刊：空间科学大数据智能算法模型与工具 • 上一篇下一篇

月球撞击坑形态特征的多维度聚类方法研究

刘方超¹(),张立²,郭弟均³,陈剑¹,吕英波^1,^*(),凌宗成¹,李博然²,李心语²,马云龙¹

1.山东大学，空间科学与技术学院, 山东威海 264209
2.山东大学，机电与信息工程学院, 山东威海 264209
3.中国科学院空间科学中心，北京 100190

收稿日期:2023-12-29 出版日期:2025-08-20 发布日期:2025-08-21
通讯作者: 吕英波
作者简介:刘方超，山东大学空间科学与技术学院，博士研究生，主要研究方向为行星科学与大数据。
本文中主要负责方法研究、实验设计与论文撰写。
LIU Fangchao, is a Ph.D. candidate at the School of Space Science and Technology, Shandong University, with main research interests in planetary science and big data.
In this paper, he is mainly responsible for methodological research, experimental design, and paper writing.
E-mail: liufc@mail.sdu.edu.cn|吕英波，山东大学空间科学与技术学院，博士生导师，教授，博士。主要研究方向为空间科学数据分析、深度学习与数据挖掘、深空资源勘探与利用、空间太阳能利用、材料模拟与工程仿真等相关的科学研究与技术攻关工作。
本文中主要负责方法设计、实验指导和论文撰写。
LYU Yingbo, Ph.D., is a doctoral supervisor amd professor in the School of Space Science and Technology, Shandong University, with main research interests in planetary science and big data.
In this paper, he is mainly responsible for method design, experimental guidance, and paper writing.
E-mail: lyb@sdu.edu.cn
基金资助:
国家重点研发计划(2022YFF0711400);中国科学院国家空间科学中心开放课题(NSSDC2302001)

A Multi-Dimensional Clustering Method for Morphological Characterization of Lunar Impact Craters

LIU Fangchao¹(),ZHANG Li²,GUO Dijun³,CHEN Jian¹,LYU Yingbo^1,^*(),LING Zongcheng¹,LI Boran²,LI Xinyu²,MA Yunlong¹

1. School of space scicence and technology, Shandong University, Weihai, Shandong 264209, China
2. School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, Shandong 264209, China
3. National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China

Received:2023-12-29 Online:2025-08-20 Published:2025-08-21
Contact: LYU Yingbo

摘要/Abstract

摘要：

【目的】月球撞击坑是研究月球表面地质演化的重要标志，但是在高分辨率影像数据的支持下系统地对撞击坑进行分类和形态分析仍是一个重要的研究课题。【方法】本研究基于嫦娥三号着陆区的LROC NAC影像数据，提出了一种无需训练的k-means聚类方法，用于对形态特征相似的撞击坑进行自动分类。首先，从每张影像中提取均值、方差、熵、对比度和尺度五个维度的特征信息；其次，通过肘部法、轮廓系数法、Gap统计量和层次聚类四种方法确定了最佳的聚类数k=8；然后，将特征信息和k输入k-means算法，对撞击坑影像进行聚类；最后，通过绘制簇特征散点图和示例图像等方式对聚类结果进行可视化分析。【结果】基于聚类结果，对不同类型的撞击坑形态特征进行了详细分析，揭示了不同形态类别的撞击坑在月球表面地质演化中的潜在意义。【结论】本研究为月球撞击坑的自动化分类和形态特征分析提供了一种新的方法，为深入理解月球表面地质过程提供了重要支持。

关键词: 月球撞击坑, 聚类, k-means, 多维特征, 可视化

Abstract:

[Purpose] Lunar impact craters are important landmarks for studying the geologic evolution of the lunar surface, while systematically classifying and morphologically analyzing impact craters with the support of high-resolution image data is still an important research topic. [Method] In this study, based on the LROC NAC image data near the Chang'e-3 landing site, a k-means clustering method without training is proposed for automatic classification of impact craters with similar morphological features. Firstly, feature information in five dimensions, including mean, variance, entropy, contrast, and scale, is extracted from each image. Secondly, the optimal number of clusters, k=8, is determined by four methods, namely, the elbow method, the silhouette coefficient method, the Gap statistic, and hierarchical clustering. Thirdly, the feature information and the k are input into the k-means algorithm for clustering of the impact crater images. Finally, the images are clustered by drawing a cluster feature scatter plot and example images, etc. to visualize and analyze the clustering results. [Results] Based on the clustering results, the morphological features of different types of impact craters are analyzed in detail, revealing the potential significance of different morphological categories of impact craters in the geological evolution of the lunar surface. [Conclusion] This study provides a new method for the automated classification and morphological characterization of lunar impact craters, which provides important support for an in-depth understanding of lunar surface geological processes.

Key words: lunar impact crater, clustering, k-means, multidimensional features, visualization

刘方超, 张立, 郭弟均, 陈剑, 吕英波, 凌宗成, 李博然, 李心语, 马云龙. 月球撞击坑形态特征的多维度聚类方法研究[J]. 数据与计算发展前沿, 2025, 7(4): 89-100.

LIU Fangchao, ZHANG Li, GUO Dijun, CHEN Jian, LYU Yingbo, LING Zongcheng, LI Boran, LI Xinyu, MA Yunlong. A Multi-Dimensional Clustering Method for Morphological Characterization of Lunar Impact Craters[J]. Frontiers of Data and Computing, 2025, 7(4): 89-100, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2025.04.008.

图/表 12

图1

图2

图3

图4

图5

图6

表1

图7

表2

图8

表3

图9

参考文献 39

[1]	LIU J, ZENG X, LI C, et al. Landing site selection and overview of China’s lunar landing missions[J]. Space Science Reviews, 2021, 217(1): 6.
[2]	LIU J, REN X, YAN W, et al. Descent trajectory reconstruction and landing site positioning of chang’E-4 on the lunar farside[J]. Nature Communications, 2019, 10(1): 4229.
[3]	XIE M, XIAO Z, XU L, et al. Change in the Earth-moon impactor population at about 3.5 billion years ago[J]. Nature Astronomy, 2020, 5(2): 128-133.
[4]	LI Y, FA W, JIA B. Morphological characterization of decimeter- to hectometer-scale impact craters at the chang’E-3/4/5 landing sites[J]. Journal of Geophysical Research: Planets, 2023, 128(4): e2022JE007703.
[5]	LIU S, DU K, TONG X, et al. In-situ mapping of iron and titanium with the visible and near-infrared image spectrometer (VNIS) along the yutu-2 rover traverse on the farside of the moon[J]. Icarus, 2024, 412: 116003.
[6]	CHAKRABORTY T, PANDEY D Kr, MEHRA R, et al. Polarimetric characterization of chandrayaan-3 landing site near lunar south pole using high resolution chandrayaan-2 DFSAR data[J]. Planetary and S- ace Science, 2024, 251: 105956.
[7]	ZHANG T, PANG Y, ZENG T, et al. Robotic drilling for the chinese chang’E 5 lunar sample-return mission[J]. International Journal of Robotics Research, 2023, 42(8): 586-613.
[8]	ZHONG G, YI X, GAO S, et al. Polycyclic aromatics in the chang’E 5 lunar soils[J]. Nature Communications, 2025, 16(1): 3622.
[9]	HUMM D C, TSCHIMMEL M, BRYLOW S M, et al. Flight calibration of the LROC narrow angle camera[J]. Space Science Reviews, 2016, 200(1-4): 431-473.
[10]	DI K, XU B, LIU B, et al. Geopositioning precision analysis of multiple image triangulation using lro nac lunar images[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, XLI-B4: 369-374.
[11]	岳宗玉, 史珂, 邸凯昌, 等. 撞击坑研究进展与展望[J]. Scientia Sinica Terrae, 2023, 53(11): 2482-2493.
[12]	QIAN Y, XIAO L, ZHAO J, et al. First magnetic and spectroscopic constraints on attenuated space weathering at the chang’e-5 landing site[J]. Icarus, 2024, 410: 115892.
[13]	DI K, JIA M, XIN X, et al. High-resolution large-area digital orthophoto map generation using LROC NAC images[J]. Photogrammetric Engineering and Remote Sensing, 2019, 85(7): 481-491.
[14]	JIA M, DI K, YUE Z, et al. Multi-scale morphologic investigation of craters in the chang’e-4 landing area[J]. Icarus, 2021, 355: 114164.
[15]	LIU W C, WU B. An integrated photogrammetric and photoclinometric approach for illumination-invariant pixel-resolution 3D mapping of the lunar surface[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 153-168.
[16]	VELICHKO S, KOROKHIN V, VELIKODSKY Y, et al. Multiphase photoclinometry as applied to the lunar photometry with LROC NAC data[J]. Planetary and Space Science, 2024, 246: 105914.
[17]	WANG Z, YI J, DING H, et al. Nonlinear circumference-based robust ellipse detection in low-SNR images[J]. Image and Vision Computing, 2024, 144: 104968.
[18]	YANG J, KANG Z. Bayesian network-based extraction of lunar impact craters from optical images and DEM data[J]. Advances in Space Research, 2019, 63(11): 3721-3737.
[19]	MA P, LI C, RAHAMAN M M, et al. A state-of-the-art survey of object detection techniques in microorganism image analysis: from classical methods to deep learning approaches[J]. Artificial Intelligence Review, 2023, 56(2): 1627-1698.
[20]	MOHAN G, RAJA M S, SWATHI S, et al. A novel breast cancer diagnostic using convolutional squared deviation neural network classifier with Al-biruni earth radius optimization in medical IoT system[J]. e-Prime Advances in Electrical Engineering, Electronics and Energy, 2024, 7: 100440.
[21]	PRAMANIK A, SARKER S, SARKAR S, et al. FGI-CogViT: fuzzy granule-based interpretable cognitive vision transformer for early detection of alzheimer’s disease using MRI scan images[J]. Information Systems Frontiers, 2024.
[22]	AL-ALI A, ELHARROUSS O, QIDWAI U, et al. ANFIS-net for automatic detection of COVID-19[J]. Scientific Reports, 2021, 11(1): 17318.
[23]	YAP F Y, VARGHESE B A, CEN S Y, et al. Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses[J]. European Radiology, 2021, 31(2): 1011-1021.
[24]	HERDIANA I, KAMAL M A, TRIYANI, et al. A more precise elbow method for optimum K-means clustering[A]. arXiv, 2025.
[25]	YUAN C, YANG H. Research on K-value selection method of K-means clustering algorithm[J]. Open access Journal of multidisciplinary science, 2019, 2(2): 226-235.
[26]	HIGGINS S, DUTTA S, KAKAR R S. Machine learning for lumbar and pelvis kinematics clustering[J]. Computer Methods in Biomechanics and Biomedical Engineering, 2024, 27(10): 1332-1345.
[27]	CHEN Y, LIU L, ZHENG D, et al. Estimating travellers’ value when purchasing auxiliary services in the airline industry based on the RFM model[J]. Journal of Retailing and Consumer Services, 2023, 74: 103433.
[28]	MARKANTONIS I, VLACHOGIANNIS D, SFETSOS A, et al. Atmospheric preconditions investigation of wet-cold compound events in Greece between 1980 and 2004[J]. Theoretical and Applied Climatology, 2024, 155(8): 8151-8163.
[29]	REBULI K B, OZELLA L, VANNESCHI L, et al. Multi-algorithm clustering analysis for characterizing cow productivity on automatic milking systems over lactation periods[J]. Computers and Electronics in Agriculture, 2023, 211: 108002.
[30]	LARA-NAVARRA P, SÁNCHEZ-PÉREZ E A, FERRER-SAPENA A, et al. Singularity in higher education: methods for detection and classification[J]. Expert Systems with Applications, 2024, 239: 122306.
[31]	RAYA-TAPIA A Y, SÁNCHEZ-ZARCO X G, CANSINO-LOEZA B, et al. A typology country framework to evaluate the SDG progress and food waste reduction based on clustering analysis[J]. Trends in Food Science & Technology, 2024, 143: 104304.
[32]	BŁAŻEJEWSKI W, BARCIKOWSKI M, STOSIAK M, et al. A novel design of a low-pressure composite vessel with inspection opening - design, manufacturing and testing[J]. Alexandria Engineering Journal, 2024, 91: 442-456.
[33]	ZHOU Y, YAN L, ZHAO H, et al. A new classification and index calibration of lunar impact craters for digital terrain analysis[J]. Astronomy Reports, 2019, 63(12): 1069-1079.
[34]	SCAIONI M, YORDANOV V, BRUNETTI M T, et al. Recognition of landslides in lunar impact craters[J]. European Journal of Remote Sensing, 2018, 51(1): 47-61.
[35]	GEWERS F L, FERREIRA G R, ARRUDA H F D, et al. Principal component analysis: a natural approach to data exploration[J]. ACM Computing Surveys, 2022, 54(4): 1-34.
[36]	HEINRICHS F. GT-PCA: effective and interpretable dimensionality reduction with general transform-invariant principal component analysis[A]. arXiv, 2024.
[37]	CHITRA G, HARI GANESH S. Cultural algorithm based principal component analysis (CA-PCA) approach for handling high dimensional data[J]. The Scientific Temper, 2024, 15(spl-1): 86-96.
[38]	HOLSAPPLE K A. Geologic collisions: impact cratering[J]. Science, 1989, 245(4923): 1261-1262. pmid: 17747890
[39]	LI C L, MU L L, ZOU X D, et al. Analysis of the geomorphology surrounding the chang’e-3 landing site[J]. Research in Astronomy and Astrophysics, 2014, 14(12): 1514-1529.

	平均值	最大值	最小值
马氏距离	4.3292	1.4271	8.9489
对应的簇	—	簇0和簇4	簇1和簇5

类别	A	B	C	D	E	F	G	H
数量	210	114	58	252	268	33	257	7
占比	17.5%	9.5%	4.8%	21.0%	22.4%	2.8%	21.4%	0.6%
均值	0.36	0.45	0.33	0.22	0.39	0.61	0.26	0.41
方差	0.01	0.04	0.02	0.01	0.02	0.07	0.01	0.04
熵	6.50	7.34	7.11	6.23	6.98	7.28	6.70	7.48
对比度	0.11	0.20	0.14	0.08	0.15	0.26	0.11	0.19

月球撞击坑形态特征的多维度聚类方法研究

A Multi-Dimensional Clustering Method for Morphological Characterization of Lunar Impact Craters

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 39

相关文章 15

编辑推荐

Metrics

本文评价

[1]	凌宗成, 李勃, 魏广飞, 郭弟均, 吕英波, 刘长卿, 朱凯, 陈剑, 赵强, 李静, 胡国平, 王娇, 刘建忠. 行星探测特征信息提取与知识挖掘关键技术及应用研究[J]. 数据与计算发展前沿, 2025, 7(4): 3-19.
[2]	钟佳, 邹自明. 基于直接体可视化方法提取磁层顶结构[J]. 数据与计算发展前沿, 2025, 7(4): 79-88.
[3]	崔潇骁, 赵玉立, 修涵文, 薛晓光, 黄咏政, 何晓辉, 朱江. 面向非规则体离散的高效物质点生成技术研究[J]. 数据与计算发展前沿, 2025, 7(3): 174-184.
[4]	余敏槠, 王杨, 顾睿琪, 单桂华, 金钟. TSPVS：时序学者画像可视化系统[J]. 数据与计算发展前沿, 2024, 6(1): 136-149.
[5]	赵一宁, 肖海力. 国家高性能计算环境运行状态诊断系统[J]. 数据与计算发展前沿, 2024, 6(1): 57-67.
[6]	徐静, 袁慧. 基于RFM模型的上市公司违规行为画像研究[J]. 数据与计算发展前沿, 2023, 5(6): 20-30.
[7]	刘嘉琪,杨斌艳. 我国人工智能与社会科学耦合发展的热点与趋势研究——基于CiteSpace的文献计量分析[J]. 数据与计算发展前沿, 2022, 4(6): 77-91.
[8]	张猛,李健. 鸟类音频数据预处理方法[J]. 数据与计算发展前沿, 2021, 3(5): 130-140.
[9]	石晓霖,毕重科,黄元琪,邓亮,王岳青,王昉. 基于虚拟视点的大规模数值模拟的可交互式原位可视化[J]. 数据与计算发展前沿, 2021, 3(4): 30-43.
[10]	申丽铭,郭雨蒙,王文珂. 基于矢量完全信息熵的流线并行分布方法[J]. 数据与计算发展前沿, 2021, 3(4): 44-53.
[11]	祁荣苓,焦文彬,汪洋. 基于句子向量表示和模糊C均值的电子政务文档自动摘要技术[J]. 数据与计算发展前沿, 2021, 3(2): 103-111.
[12]	李言,陈远平. 科研信息门户的资源推荐技术研究[J]. 数据与计算发展前沿, 2021, 3(2): 112-119.
[13]	翟擎辰,周园春,宋秋成,王建伟,孟珍,张艳玲. 数据降维及聚类算法在烟叶相似性分析中的应用[J]. 数据与计算发展前沿, 2021, 3(1): 112-121.
[14]	杨润佳,刘泽三. 一种工业报警相关性数据挖掘算法[J]. 数据与计算发展前沿, 2020, 2(5): 110-121.
[15]	葛胤池,张辉,宋文燕,王轩. 基于领域本体的科技资源聚类方法研究[J]. 数据与计算发展前沿, 2020, 2(5): 13-22.