Classification of Mediterranean Shrub Species from UAV Point Clouds

Juan Pedro Carbonell-Rivera,Jesús Torralba,Javier Estornell,Luis Ángel Ruiz,Pablo Crespo-Peremarch

doi:10.3390/rs14010199

Juan Pedro Carbonell-Rivera, Jesús Torralba + Show 3 more

Open Access

https://doi.org/10.3390/rs14010199

Copy DOI

Journal: Remote Sensing	Publication Date: Jan 2, 2022
Citations: 14	License type: CC BY 4.0

Affiliation: Universitat Politècnica de València

Abstract

Modelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species’ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the use of UAV-based digital aerial photogrammetry (UAV-DAP) point clouds to classify tree and shrub species in Mediterranean forests, and this information is key for the correct generation of wildfire models. In July 2020, two test sites located in the Natural Park of Sierra Calderona (eastern Spain) were analysed, registering 1036 vegetation individuals as reference data, corresponding to 11 shrub and one tree species. Meanwhile, photogrammetric flights were carried out over the test sites, using a UAV DJI Inspire 2 equipped with a Micasense RedEdge multispectral camera. Geometrical, spectral, and neighbour-based features were obtained from the resulting point cloud generated. Using these features, points belonging to tree and shrub species were classified using several machine learning methods, i.e., Decision Trees, Extra Trees, Gradient Boosting, Random Forest, and MultiLayer Perceptron. The best results were obtained using Gradient Boosting, with a mean cross-validation accuracy of 81.7% and 91.5% for test sites 1 and 2, respectively. Once the best classifier was selected, classified points were clustered based on their geometry and tested with evaluation data, and overall accuracies of 81.9% and 96.4% were obtained for test sites 1 and 2, respectively. Results showed that the use of UAV-DAP allows the classification of Mediterranean tree and shrub species. This technique opens a wide range of possibilities, including the identification of species as a first step for further extraction of structure and fuel variables as input for wildfire behaviour models.

Highlights

Wildfires are the main cause of forest ecosystem disturbance in the Mediterranean basin, modifying the vegetation, fauna, soil, and affecting hydrological and geomorphological processes [1,2]
We propose a methodology for the classification of unmanned aerial vehicles (UAVs)-based digital aerial photogrammetry (UAV-DAP) derived point clouds in tree and shrub species’ types, using multispectral data with low spectral resolution cameras
11,514,975 points with an average density of 1005.3 points·m−2. Their positional error was estimated through the Root Mean Square Error (RMSE) between the Ground Control Points (GCPs) and the position of the computed 3D point, being 3.45 cm for Area 1 and 3.79 cm for Area 2

Summary

Introduction

Wildfires are the main cause of forest ecosystem disturbance in the Mediterranean basin, modifying the vegetation, fauna, soil, and affecting hydrological and geomorphological processes [1,2]. Humans are modifying land use and climate causing an increase in wildfires and burned area, modifying their natural frequency and reducing their period of recurrence [8,9]. Climate change models indicate that the Mediterranean basin will be one of the most affected globally by the rising of temperatures and reduction of precipitation, considering it as a climate change “hot spot” [4,11]. These factors together with the increasing of soil aridity will affect directly the fire regime [5], expecting the increase of wildfire frequency and burned areas [6]

Methods

Results

Conclusion