ABSTRACT

Forest inventory based on airborne laser scanning produces data for small grid cells. Various segmentation methods are used to cluster the grid cells into spatially continuous larger areas that correspond to forest stands. This study examined the performance of self-organizing map (SOM) in the delineation of forest stands. The SOM is also called Kohonen map or Kohonen network, according to the developer of the method. The data consisted of stand attribute grids in 16-m resolution. Spatiality was integrated in the SOM by using the geographical coordinates as criteria in the clustering. The clusters created by the SOM were spatially distinct and formed continuous areas corresponding to traditional stands when geographical coordinates were given more weight in the clustering compared to other stand attributes such as fertility class and stand basal area. The delineation improved when the attributes of the created stands were used as the starting point of repeated SOM rounds, and removing small stands at the beginning of each round. When small within-stand variation in stand attributes was targeted, the SOM often produced irregular stands consisting of disconnected parts. These delineations could be fine-tuned by applying mode filtering to the grid of stand numbers generated by the SOM algorithm.

摘要

基于机载激光扫描的森林资源清查可生成小型网格单元的数据。各种分割方法用于将网格单元聚类为与林分相对应的空间连续的较大区域。这项研究检查了在森林林分界中自组织图（SOM）的性能。根据该方法的开发者，SOM也称为Kohonen地图或Kohonen网络。数据由分辨率为16 m的林分属性网格组成。通过使用地理坐标作为聚类的标准，将空间性集成到SOM中。与其他林分属性（例如肥力类别和林分基础面积）相比，当地理坐标在聚类中具有更大的权重时，由SOM创建的群集在空间上是不同的，并形成了与传统林分相对应的连续区域。当将创建的看台的属性用作重复SOM回合的起点并在每个回合开始时删除小看台时，划定会有所改善。当针对展台属性在展台内进行较小的变化时，SOM经常会产生由不连贯零件组成的不规则展台。通过将模式过滤应用于由SOM算法生成的展位号网格，可以对这些描述进行微调。并在每个回合开始时移除小看台。当针对展台属性在展台内进行较小的变化时，SOM经常会产生由不连贯零件组成的不规则展台。通过将模式过滤应用于由SOM算法生成的展位号网格，可以对这些描述进行微调。并在每个回合开始时移除小看台。当针对展台属性在展台内进行较小的变化时，SOM经常会产生由不连贯零件组成的不规则展台。通过将模式过滤应用于由SOM算法生成的展位号网格，可以对这些描述进行微调。