摘要
【目的】本文针对行星探测数据的深度挖掘和智能提取的迫切需求,基于国内外行星探测获取的海量遥感数据,开展了行星探测特征信息提取与知识挖掘的关键技术及其应用研究。【方法】突破了多源、异构的行星数据的重构融合和可视化技术,克服了单一传感器成像信息不足的问题,可生成具有丰富空间和光谱信息的高质量遥感图像。建立了基于可见近红外光谱探测数据的物质成分反演模型,可提取月球及火星矿物光谱特征参量并反演月表元素、矿物的含量与分布。开发了融合多源数据的月壤厚度反演与次表层结构反演算法,利用微波和雷达数据获取月壤厚度及其物理性质,可对次表层结构和地层信息进行分析。利用月球和火星的影像及高程数据,实现了表面多尺度地形因子计算和基于深度学习的典型形貌特征自动提取、绝对模式年龄计算和地质要素制图功能。【结果】在此基础上,实现形貌要素、物质成分信息、次表层结构的集成平台展示和互操作分析,研制了具有自主知识产权的行星数据分析挖掘软件工具。该工具将在国家空间科学数据中心公开部署,并在山东大学威海行星数据系统(PDS)实验室镜像发布,以支撑行星数据制图和地质演化等相关研究。
[Purpose]This article focuses on the demand for deep mining and intelligent feature extraction of planetary exploration data.It investigates key technologies and applications for extracting feature information and knowledge mining from massive remote sensing data obtained during various planetary explorations.[Method]This study breaks through the challenges of reconstructing,fusing,and visualizing multi-source and heterogeneous planetary data,addressing the limitations of insufficient imaging information from single sensor to generate high-quality remote sensing images rich in spatial and spectral information.Spectral characteristic parameters of lunar and martian minerals are extracted from visible near-infrared spectroscopic data,enabling the inversion of the content and distribution of elements and minerals on the lunar and martian surface.Additionally,microwave and radar data are utilized to obtain information regarding the thickness and physical properties of lunar regolith,along with the subsurface structure of typical regions on the Moon and Mars.By employing images and elevation data of the Moon and Mars,multi-scale terrain factors on the surface are calculated,and typical morphological features are automatically extracted using deep learning techniques.[Results]Finally,an integrated platform for displaying and analyzing morphological features,material composition information,and subsurface structures has been established.Furthermore,a planetary data analysis and mining software tool with independent intellectual property rights is developed,which will be released by National Space Science Data Center and Planetary Data System(PDS)Laboratory of Shandong University at Weihai,to support planetary data mapping and geological evolution researches.
作者
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
LING Zongcheng;LI Bo;WEI Guangfei;GUO Dijun;LYU Yingbo;LIU Changqing;ZHU Kai;CHEN Jian;ZHAO Qiang;LI Jing;HU Guoping;WANG Jiao;LIU Jianzhong(School of Space Sciences and Technology,Institute of Space Sciences,Shandong University,Weihai,Shandong 264209,China;Institute of Geochemistry,Chinese Academy of Sciences,Guiyang,Guizhou 550081,China;Deep Space Exploration Laboratory,Hefei,Anhui 230026,China;State Key Laboratory of Solar Activity and Space Weather,National Space Science Center,Chinese Academy of Sciences,Beijing,100190,China;Department of Surveying and Planning,Shangqiu Normal University,Shangqiu,Henan 476000,China;College of Geoexploration Science and Technology,Jinlin University,Changchun,Jilin 130026,China;School of Geospatial Engineering and Science,Sun Yat-Sen University,Zhuhai,Guangdong 519082,China;School of Information and Engineering,China University of Geosciences(Beijing),Beijing 100083,China)
基金
国家重点研发计划项目(2022YFF0711400):空间科学大数据智能管理与分析挖掘关键技术及应用。
关键词
行星探测数据
知识挖掘
物质成分
次表层结构
形貌要素
可视化
重构融合
planetary exploration data
knowledge mining
chemical and mineralogical composition
subsurface structure
morphological features
visualization
reconstruction and fusion
