地球信息科学学报 ›› 2022, Vol. 24 ›› Issue (4): 657-672.doi: 10.12082/dqxxkx.2022.210449

• 地球信息科学理论与方法 • 上一篇    下一篇

基于DEM小流域复杂网络的黄土高原地貌自动识别研究

林偲蔚1,2(), 陈楠1,2,*(), 刘奇祺1,2, 贺卓文1,2   

  1. 1.福州大学空间数据挖掘与信息共享教育部重点实验室,福州 350108
    2.福州大学数字中国研究院(福建),福州 350108
  • 收稿日期:2021-08-03 修回日期:2021-09-07 出版日期:2022-04-25 发布日期:2022-06-25
  • 通讯作者: *陈 楠(1975— ),男,福建厦门人,博士,研究员,主要从事数字地形分析研究。E-mail: chennan@fzu.edu.cn
    *陈 楠(1975— ),男,福建厦门人,博士,研究员,主要从事数字地形分析研究。E-mail: chennan@fzu.edu.cn
  • 作者简介:林偲蔚(1996— ),男,福建漳州人,硕士生,主要从数字地形分析研究。E-mail: n195520011@fzu.edu.cn
  • 基金资助:
    国家自然科学基金项目(41771423)

Geomorphological Automatic Recognition of Loess Plateau based on Complex Network of Small Watershed from DEM

LIN Siwei1,2(), CHEN Nan1,2,*(), LIU Qiqi1,2, HE Zhuowen1,2   

  1. 1. Key Lab for Spatial Data Mining and Information Sharing of Education Ministry, Fuzhou University, Fuzhou 350108, China
    2. The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
  • Received:2021-08-03 Revised:2021-09-07 Online:2022-04-25 Published:2022-06-25
  • Supported by:
    National Natural Science Foundation of China(41771423)

摘要:

地貌识别,对于人类建设,地质构造研究,环境治理等相关领域都有着重要意义。传统的基于像素单元或面向对象的地貌识别方法存在局限性。由于流域小单元具有表面形态的完整性,在地貌演化中具有明确的地理意义,基于流域小单元的地貌识别成为了该领域的一个新热点。然而,基于传统地形因子的地貌识别方法使用的因子往往较为单一或者在地学描述上存在重复性,目前尚无针对流域小单元进行空间结构描述和拓扑关系特征量化的地貌识别研究。基于此,本文基于DEM进行水文分析并通过坡谱方法解决了小流域稳定面积难以确定的问题,在黄土高原样区提取了181个稳定小流域。根据复杂网络理论和地貌学原理提出了流域加权复杂网络的概念和相应的8个定量指标用于流域空间结构的模拟和量化描述。最后采用了基于决策树的XGBoost机器学习算法进行地貌识别,实验对于黄土高原主要地貌类型的识别显现出较好的效果,Kappa系数为86.00%,总体精度达到了88.33%。对于地貌形态特征明显的地貌,复杂网络方法其顾及空间结构和拓扑特征的特性导致了其较高的识别性能,精度和召回率都在90%~100%之间。通过与前人的研究进行对比,其识别结果亦呈现出较高的精度,这些都验证了流域加权复杂网络是一种基于流域小单元地貌识别的高精度且有效的方法。

关键词: 地貌识别, 流域, 数字地形分析, 黄土高原, 地形特征, DEM

Abstract:

Landform recognition is of great significance to human construction, geological structure research, environmental governance and other related fields. Traditional recognition methodology is mainly based on pixel unit or object-oriented recgnition, which existed limitations. Landform recognition based on the watershed unit has become a new hotspot in this field because of its surface morphology integrity and clear geographical significance. However, the traditional methods of landform recognition based on terrain factors are often simple or repeatable in the geological description, which cannot be used to describe the spatial structure and quantify the topological relationship characteristics of the watershed unit. The slope spectrum method was used to solve the problem that it was difficult to determine the stable area of watershed unit, and 181 small watersheds were extracted through hydrological analysis. Based on the theory of complex network and geomorphology, the concept of watershed weighted complex network and 8 quantitative indexes were put forward to simulate and quantify the spatial structure of the watershed. Finally, XGBoost machine learning algorithm is adopted for landform recognition. XGBoost machine learning algorithm based on decision tree is used for landform recognition. The experiment shows a well performance on the landform recognition of the main landform types on the Loess Plateau, with the Kappa coefficient of 86.00% and the overall accuracy of 88.33%. Compared with the landforms having obvious morphological features, the complex network method considers the characteristics of spatial structure and topological features, resulting in higher recognition accuracy and kappa coefficient of 90%~100%. Compared with previous studies, the recognition results show high accuracy, which verifies that the method based on watershed weighted complex network is an effective method with high accuracy for landform recognition based on watershed.

Key words: landform recognition, watershed, digital terrain analysis, Loess Plateau, terrain feature, DEM