The Use of an Airborne Laser Scanner for Rapid Identification of Invasive Tree Species Acer negundo in Riparian Forests

Abstract

Invasive species significantly impact ecosystems, which is fostered by global warming. Their removal generates high costs to the greenery managers; therefore, quick and accurate identification methods can allow action to be taken with minimal impact on ecosystems. Remote sensing techniques such as Airborne Laser Scanning (ALS) have been widely applied for this purpose. However, many species of invasive plants, such as Acer negundo L., penetrate the forests under the leaves and thus make recognition difficult. The strongly contaminated riverside forests in the Vistula valley were examined in the gradient of the center of Warsaw and beyond its limits within a Natura 2000 priority habitat (91E0), namely, alluvial and willow forests and poplars. This work aimed to assess the potentiality of a dual-wavelength ALS in identifying the stage of the A. negundo invasion. The research was carried out using over 500 test areas of 4 m diameter within the riparian forests, where the habitats did not show any significant traces of transformation. LiDAR bi-spectral data with a density of 6 points/m2 in both channels were acquired with a Riegl VQ-1560i-DW scanner. The implemented approach is based on crown parameters obtained from point cloud segmentation. The Adaptive Mean Shift 3D algorithm was used to separate individual crowns. This method allows for the delineation of individual dominant trees both in the canopy (horizontal segmentation) and undergrowth (vertical segmentation), taking into account the diversified structure of tree stands. The geometrical features and distribution characteristics of the GNDVI (Green Normalized Vegetation Index) were calculated for all crown segments. These features were found to be essential to distinguish A. negundo from other tree species. The classification was based on the sequential additive modeling algorithm using a multi-class loss function. Results with a high accuracy, exceeding 80%, allowed for identifying and localizing tree crowns belonging to the invasive species. With the presented method, we could determine dendrometric traits such as the age of the tree, its height, and the height of the covering leaves of the trees.

Multispectral Light Detection and Ranging Technology and Applications: A Review

“…In MSL sensors, features describing the 3D structure of tree crowns as well as spectral information can be used for more detailed analysis of backscatters. Hence, the characterization of tree species, even identifying invasive ones, is one of the primary and most popular applications of multi-wavelength laser scanning [ 109 ]. Plant reflectance is high at NIR/SWIR wavelengths and low at the green wavelength due to their chlorophyll content, making a combination of the green laser channel and NIR/SWIR wavelength potentially useful for vegetation analysis.…”

“…MSL technology also has the potential to enhance the accuracy of individual tree detection, especially in dense forests with clumped trees, which is quite often challenging using only geometric information [ 109 ]. This capability was first explored by Dai et al [ 17 ], and they applied the mean shift segmentation method in a joint domain of spatial and spectral features.…”

Review of Invasive Plant Functional Traits and Management Using Remote Sensing in Sub-Saharan Africa

“…Previous studies affirm that using optically measured functional traits for remote sensing can help ecologists to better understand the mechanisms and effects of plant invasion (Table 3). Functional traits can be utilized in RS not only to map the invasion of IAPs but also to delineate or group IAPs based on how they share effects on ecosystem processes or how they respond to the environment [54,59,60]. Also, Chacón-Madrigal et al [53] contends that functional traits can be used in RS to determine how closely related IAP species differ in their geographical range sizes.…”

“…Furthermore, the use of a functional trait remote sensing (FTRS) research approach can further improve our knowledge of the dynamics, control, mechanisms, and impacts of alien invasions [53][54][55]. For studying alien invasions, RS is the most thorough and practical method available as it demonstrates great potential to detect functional traits in IAPs [56][57][58][59][60][61]. However, Sub-Saharan Africa (SSA) still has significant gaps in its application when it comes to studying and managing alien plant invasions.…”

Object-Oriented Convolutional Neural Network for Forest Stand Classification Based on Multi-Source Data Collaboration

“…At present, remote sensing data sources used for forest classification include multispectral images, hyperspectral images, and light detection and ranging (LiDAR) data [1,[4][5][6]. However, a single data source often fails to provide the spectral, texture, and spatial information required for forest classification at the same time.…”