基于DEM的一体化山地特征要素提取

The Extraction of Characteristic Elements of Mountain based on DEM

山顶点和山脊线等特征地形要素是构成地表地形及其起伏变化的基本框架,对地形在地表的空间分布具有控制作用。基于DEM研究山顶点、山脊线及其空间组合关系,是DEM地表形态特征研究的重要内容,也是衔接从地形特征分析向山峰等地貌学本源语言的途径之一。本文以四川盆地西南缘与青藏高原过渡地带的川西凉山山原为例,基于山峰-山脊线-控制范围一体化构建的算法策略,识别了山峰和山脊线及其等级、主山脊及其范围。结果表明,研究区内有主峰9座,次峰53座,平均高程2540 m;山脊线230条,其中主山脊9条,平均长度60 km;9大山系,近南北走向,平均控制面积1017 km^2。研究用模糊隶属度方法对算法所提取的主峰、主脉进行精度验证,隶属度介于0.98~1.00和0.37~0.57时提取的主峰、主脉基本吻合算法提取的结果。研究采用一体化山地特征要素提取方法,实现了各山地要素间紧密联系、总体结构与区域地貌特征相对吻合的目标;完成了由栅格单元向地理对象的转变;可以应用于协助地貌类型划分,协同区域地理规划等。

As a vital source of spatial data, DEM plays an important role in the process of geomorphologic characteristics analysis. DEM provides us an opportunity to study the earth surface with an even broader perspective aided by digital terrain structure analysis. The terrain surface often can be regarded as a combination of some fundamental elements, which include the peaks, ridge lines and valley, etc. The peaks and ridge lines depict the macro relief of the terrain, which explains why they often can be used to reveal the morphology,pattern, and evolution processes of the landform. Although the platform of ArcGIS enables the peaks and ridges to be extracted efficiently, there are still many obstacles in existence on the issue of landform features extraction.Firstly, the peaks and ridges extracted by the existing methods are independent of each other, ignoring the expression of their relationship. Secondly, the peaks often be picked out since they are the highest point in a given neighborhood, but these peaks are not necessarily mountain tops in the geomorphological sense and in cognition of mankind. The Liangshan Plateau Mountain in Sichuan Province is taken as a case study, since it is a typical mountainous area and is a transitional zone between the Qinghai-Tibet Plateau and the southwest edge of Sichuan Basin. A novel integrated strategy is provided in the paper to extract mountain peaks and ridges that are close to human cognition. The first step of the method is to section the terrain to obtain the highest points in every patches and the border of the patches. Then the ridge lines are extracted and ordered by a coding formula.An important step in the process is to identify the main peaks and the major ridge lines and finalize the integration of the peaks, mountain ridge lines and their territory. For the purpose of verification, the peaks and ridges extracted by the fuzzy logic algorithm are also presented in the paper. For the results, there are 9 main peaks in the region, 53 secondary peaks with an average elevation of 2540 m. And then 230 ridge lines are obtained, of which 9 main mountain ridges with an average length of 60 km. Besides, there are 9 mountains with an average area of 1017 km^2. Overall, the mountain system in this area shows a nearly north-south trend. When the fuzzy membership of peaks is between 0.98 and 1, the mountain peaks obtained by the two methods roughly coincide with each other, while the corresponding membership of the ridge lines is between 0.37 and 0.57. When compared with the results obtained by other methods such fuzzy logic method, the advantages of our algorithm are reflected in the better expression of peaks, main ridges and their interrelationships. It is important in helping people understand that where the mountain peak is, and that where the mountain ridge is, and it is from this point that we think our algorithms have achieved a preliminary transition from raster matrix to geographical objects.This study can be applied to assist in the classification of geomorphological types, regional geographic planning, etc.