地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (3): 452-463.doi: 10.12082/dqxxkx.2020.190247

• “数字地形分析”专栏 • 上一篇    下一篇

基于随机森林的黄土地貌分类研究

曹泽涛1,2,3, 方子东1,2,3, 姚瑾4, 熊礼阳1,2,3,*()   

  1. 1. 南京师范大学地理科学学院,南京 210023
    2. 虚拟地理环境教育部重点实验室(南京师范大学),南京 210023
    3. 江苏省地理信息资源开发与利用协同创新中心,南京 210023
    4. 自然资源部第一地理信息制图院,西安 710054
  • 收稿日期:2019-05-23 修回日期:2019-12-09 出版日期:2020-03-25 发布日期:2020-05-18
  • 通讯作者: 熊礼阳 E-mail:xiongliyang@163.com
  • 作者简介:曹泽涛(1997— ),男,江苏扬州人,硕士生,主要从事研究DEM数字地形分析研究。E-mail:zetao_cao_1997@163.com
  • 基金资助:
    国家自然科学基金项目(41601411);国家自然科学基金项目(41671389);江苏高校优势学科建设工程资助项目

Loess Landform Classification based on Random Forest

CAO Zetao1,2,3, FANG Zidong1,2,3, YAO Jin4, XIONG Liyang1,2,3,*()   

  1. 1. School of Geography, Nanjing Normal University, Nanjing 210023, China
    2. Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Nanjing 210023, China
    3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China
    4. The First Institute of Geoinformation Mapping, Ministry of Natural Resources of the People's Republic of China, Xi'an 710054, China
  • Received:2019-05-23 Revised:2019-12-09 Online:2020-03-25 Published:2020-05-18
  • Contact: XIONG Liyang E-mail:xiongliyang@163.com
  • Supported by:
    National Natural Science Foundation of China(41601411);National Natural Science Foundation of China(41671389);Priority Academic Program Development of Jiangsu Higher Education Institutions

摘要:

地貌分类在指导人类建设活动的规模与布局中有着重要的意义。然而,传统的基于数字高程模型(DEM)的地貌分类方法使用的地形因子和考虑到的地貌特征往往比较单一。本文提出了一种基于流域单元的地貌分类方法,该方法考虑了流域单元的多方面特征,包括基本地形因子统计量、地形特征点线统计量、小流域特征和纹理特征。本研究首先基于DEM进行水文分析将研究区域划分成不同的小流域。然后利用数字地形分析提取29个不同方面的特征来表征流域的形态,并基于随机森林(RF)算法进行了特征选择和参数标定。RF是一种基于决策树算法的集成分类器,能有效地处理高维数据,分类精度高。最后选择训练集小流域对RF分类器进行训练,使用训练完成的分类器对整个研究区域的地貌进行分类,研究地貌分异的规律。该实验在我国陕北黄土高原典型黄土地貌区域的地貌分类中取得了较好的结果,结果表明不同的地貌之间存在明显的区域界线,特定的地貌类型在空间上表现出明显的聚集性。通过人工判读进行验证的分类精度达到了85%,Kappa系数为0.83。

关键词: 地貌, 随机森林, 黄土高原, 地形特征, 特征选择, 地貌分类, DEM, 小流域

Abstract:

Landform classification is one of the most important steps tor eveal the mechanisms of surface matter flows and energy conversion, which could inform the scale and layout of human construction activities. However, traditional landform classification methods based on Digital Elevation Model (DEM) often use a small number of topographical derivatives or landform characteristics, resulting in insufficiently precise classification results. However, object-oriented landform classification performs better in that reliable classification can be achieved by maximizing the homogeneity within and between objects. But how to set conditions in object segmentation remains a challenge. In this paper, a geomorphological classification method based on watershed unitwas proposed, by accounting for many characteristics of watershed unit including statistics of basic topographic factors, feature point and feature line, basin and texture characteristics. Firstly, hydrological analysis based on DEM divided the study area into different small basins as the experimental units. Then, 29 features were extracted within each unit to represent watershed morphology using digital terrain analysis; feature selection and parameter calibration were carried out based on Random Forest (RF) algorithm. RF is a supervised integrated learning model aggregating different outputs of a single decision tree to reduce variances that may lead to classification errors in the decision tree. Finally, the watersheds in training set were selected to train the RF classifier, and the trained classifier was used to classify the landform of the whole study area, based on which we studied the landform spatial differentiation pattern. This experiment achieved good results in the landform classification of the Loess Plateau in northern Shaanxi Province. It is one of the areas with the most serious soil erosion and the most fragile eco-environment in the world. Most of them are covered by thick loess, and the topography is fluctuant. Result shows: (1) Compared with manual interpretation, excellent classification results based on small watershed in the study area were obtained, with the classification accuracy reaching 85% and the Kappa coefficient 0.83. (2)All small watersheds were divided into eight types of landforms. The same type of landforms showed obvious spatial aggregation. There were boundaries and transitional zones between different types of landforms. (3) Different geomorphological regions explained different situations of loess deposition and runoff erosion in different regions. Our findings suggest that the combination of RF algorithm and DEM data can achieve better classification results.

Key words: Landform, random forest, loess plateau, terrain feature, feature selection, geomorphological classification, DEM, watershed