Classification of Forest Vertical Structure in South Korea from Aerial Orthophoto and Lidar Data Using an Artificial Neural Network

Soo-Kyung Kwon,Hyung-Sup Jung,Daeseong Kim,Won-Kyung Baek

doi:10.3390/app7101046

Abstract

Every vegetation colony has its own vertical structure. Forest vertical structure is considered as an important indicator of a forest’s diversity and vitality. The vertical structure of a forest has typically been investigated by field survey, which is the traditional method of forest inventory. However, this method is very time- and cost-consuming due to poor accessibility. Remote sensing data such as satellite imagery, aerial photography, and lidar data can be a viable alternative to the traditional field-based forestry survey. In this study, we classified forest vertical structures from red-green-blue (RGB) aerial orthophotos and lidar data using an artificial neural network (ANN), which is a powerful machine learning technique. The test site was Gongju province in South Korea, which contains single-, double-, and triple-layered forest structures. The performance of the proposed method was evaluated by comparing the results with field survey data. The overall accuracy achieved was about 70%. It means that the proposed approach can classify the forest vertical structures from the aerial orthophotos and lidar data.

Highlights

Since forests are important for human life, forest inventories have been investigated for various purposes for centuries
Forest vertical structure one element that represents the vitality of a forest
The forest inventory has been investigated through field surveys

Summary

Introduction

Since forests are important for human life, forest inventories have been investigated for various purposes for centuries. In Europe, the first inventories were carried out in the 14th and 15th century for the purpose of intensive mine development. Since the 1910s, national forest inventories have been carried out in Norway, Sweden, and Finland, with an emphasis on timber production [1]. The demands of society have changed rapidly over recent decades. In this context, the principles for the conservation and sustainable management of forests have been newly added by the United. Nations General Assembly [2] This was in response to an increasing interest in non-timber aspects of forest structure and the demand for assessing these aspects [3]. In the Republic of Korea, in the 1970s, when the forest inventory was first investigated, it was aimed at reforestation and forest statistics

Objectives

Methods

Results

Conclusion