Machine Learning Classification of Endangered Tree Species in a Tropical Submontane Forest Using WorldView-2 Multispectral Satellite Imagery and Imbalanced Dataset

Colbert M Jackson,Elhadi Adam

doi:10.3390/rs13244970

Abstract

Accurate maps of the spatial distribution of tropical tree species provide valuable insights for ecologists and forest management. The discrimination of tree species for economic, ecological, and technical reasons is usually necessary for achieving promising results in tree species mapping. Most of the data used in tree species mapping normally have some degree of imbalance. This study aimed to assess the effects of imbalanced data in identifying and mapping trees species under threat in a selectively logged sub-montane heterogeneous tropical forest using random forest (RF) and support vector machine with radial basis function (RBF-SVM) kernel classifiers and WorldView-2 multispectral imagery. For comparison purposes, the original imbalanced dataset was standardized using three data sampling techniques: oversampling, undersampling, and combined oversampling and undersampling techniques in R. The combined oversampling and undersampling technique produced the best results: F1-scores of 68.56 ± 2.6% for RF and 64.64 ± 3.4% for SVM. The balanced dataset recorded improved classification accuracy compared to the original imbalanced dataset. This research observed that more separable classes recorded higher F1-scores. Among the species, Syzygium guineense and Zanthoxylum gilletii were the most accurately mapped whereas Newtonia buchananii was the least accurately mapped. The most important spectral bands with the ability to detect and distinguish between tree species as measured by random forest classifier, were the Red, Red Edge, Near Infrared 1, and Near Infrared 2.

Highlights

Tropical forests comprise woody, evergreen vegetation, cover 47% of the world’s total forest area [1], and host the highest proportion of global tree diversity, i.e., with more than53,000 tree species, compared to approximately 124 in temperate Europe [2]
This study aimed to evaluate the impact of imbalanced data in mapping endangered trees species in a selectively logged sub-montane heterogeneous tropical forest using random forest and support vector machine classifiers, and WorldView-2 multispectral imagery
This study aimed to assess the effects of imbalanced data on identifying and mapping trees species under threat in a selectively logged sub-montane heterogeneous tropical forest using random forest (RF) and support vector machine (SVM) classifiers and WorldView-2 multispectral imagery

Summary

Introduction

Tropical forests comprise woody, evergreen vegetation, cover 47% of the world’s total forest area [1], and host the highest proportion of global tree diversity, i.e., with more than53,000 tree species, compared to approximately 124 in temperate Europe [2]. The height of the tree crowns forming the forest canopy is in the range of 30 to 50 m, but emergent trees may attain heights of approximately 70 m. Of the globe, and they are home to more than half of all earth’s biodiversity [1]. Vital environmental processes such as the water cycle, soil conservation, carbon sequestration, and habitat protection are immensely regulated by tropical tree species [1], those forests maintain the ecosystem services and mitigate climate change [3]. Information on key parameters such as tree species, tree diameter, and height, crown size, and location are important for resource management, biodiversity assessment, ecosystem services assessment, and conservation [3].

Objectives

Methods

Discussion

Conclusion