A Novel Feature Extension Method for the Forest Disaster Monitoring Using Multispectral Data

Yinghui Quan,Mengdao Xing,Xian Zhong,Wei Feng,Gabriel Dauphin,Lianru Gao

doi:10.3390/rs12142261

Abstract

Remote sensing images classification is the key technology for monitoring forest changes. Texture features have been demonstrated to have better effectiveness than spectral features in the improvement of the classification accuracy. The accuracy of extracting texture information by window-based method depends on the choice of the window size. Moreover, the size should ideally match the spatial scale of the object or class under consideration. However, most of the existing texture feature extraction methods are all based on a single window and do not adequately consider the scale of different objects. Our first proposition is to use a composite window for extracting texture features, which is a small window surrounded by a larger window. Our second proposition is to reinforce the performance of the trained ensemble classifier by training it using only the most important features. Considering the advantages of random forest classifier, such as fast training speed and few parameters, these features feed this classifier. Measures of feature importance are estimated along with the growth of the base classifiers, here decision trees. We aim to classify each pixel of the forest images disturbed by hurricanes and fires in three classes, damaged, not damaged, or unknown, as this could be used to compute time-dependent aggregates. In this study, two research areas—Nezer Forest in France and Blue Mountain Forest in Australia—are utilized to validating the effectiveness of the proposed method. Numerical simulations show increased performance and improved monitoring ability of forest disturbance when using these two propositions. When compared with the reference methods, the best increase of the overall accuracy obtained by the proposed algorithm is 4.77% and 2.96% on the Nezer forest data and Blue Mountain forest data, respectively.

Highlights

As an integral part of natural ecosystems, forests regulate the circulation of air and water in nature and protect the soil from wind and rain, they reduce the harm caused by environmental pollution to people
The threshold seems to be 7×7 for Nezer forest and 5×5 for Blue Mountain forest, as among {M2, M3, M4}, and M4 is best performing on the first dataset and M3 is best performing on the second dataset
Using a composite window proves to be successful on both datasets when compared to using a window having the best performing size, as M5 is increasing the overall accuracy by 0.5% when compared to M4 on the first dataset, and when compared to M3 on the second dataset

Summary

Introduction

As an integral part of natural ecosystems, forests regulate the circulation of air and water in nature and protect the soil from wind and rain, they reduce the harm caused by environmental pollution to people. Hurricanes and fires are two types of natural disturbances to forest ecosystems [2,3]. A severe hurricane can widely impact on the vegetation composition, structure, and succession of forests, and influence the terrestrial carbon sink [4,5]. Damages from fires, a common and prevalent disturbance that affects the forest [3,6,7,8], can be severe, reducing species richness and above-ground live biomass [9]. Between 2015 and 2020, ~10 m hectares of the world’s forests have been lost each year according to the records of the Food and Agriculture Organization of the United Nations [10]

Objectives

Methods

Results

Discussion

Conclusion