Vegetation mapping of No Name Key, Florida using lidar and multispectral remote sensing

Abstract

LIght Detection And Ranging (lidar) data have been widely used in the areas of ecological studies due to lidar's ability to provide information on the vertical structure of vegetation in wildlife habitats. The overall objective of this project was to map the vegetation on No Name Key, Florida where endangered wildlife species reside using publicly available remote sensing data such as lidar data and high resolution aerial images (including National Agricultural Imagery Program (NAIP) images). The methods involved the use of 4 different classification algorithms (Support Vector Machine, Random Forest, Maximum Likelihood, and Mahalanobis Distance), different classification settings (default and custom settings), and normalization (original and normalized input bands) on 2 different input stacked images, NAIP image alone and NAIP combined with lidar data. A majority filter was applied to each classification output before performing the accuracy assessment. The result of performing the image classifications showed the following: across all inputs and classification algorithms, the highest overall accuracy (OA) and kappa coefficient (к) were achieved by the Random Forest classification on the NAIP-lidar stacked image with an applied majority filter and original input bands. The result also showed the airborne data combined with the lidar data resulted in a higher classification accuracy than the airborne data alone; and when normalization was applied to all the input bands or layers, the classification accuracies were not increased in most cases compared to when original bands were used in the classification. In most cases, the application of the majority filter increased the accuracy of the classification results as opposed to when no majority filter was applied. Instead of using default values, when the new parameter values (i.e., custom settings) for the penalty parameter (C) and the gamma (ɤ) were used, the accuracies of the Support Vector Machine (SVM) classified images were slightly increased compared to using the default values for the 2 parameters. With increased availability of public lidar data, combining the aerial image with lidar data would enhance the accuracy of vegetation mapping, which would lead to more effective and accurate wildlife management.

Research hotspots and frontiers in agricultural multispectral technology: Bibliometrics and scientometrics analysis of the Web of Science

“…Based on the analysis of the publications searched, it is known that the current research on multispectral in agriculture is mainly focused on vegetation index ( Chang et al, 2020 ; Kim et al, 2020 ; Mazzia et al, 2020 ), land cover ( Laamrani et al, 2020 ), vegetation classification ( Gibson et al, 2004 ), crop estimation ( Zhou et al, 2017 ), drought monitoring ( Periasamy and Shanmugam, 2016 ), and environmental change ( Brook et al, 2020 ). Among them, the studies related to vegetation indices involves the most papers.…”

Detection of invasive plants using NAIP imagery and airborne LiDAR in coastal Alabama and Mississippi, USA

“…Many studies highlight higher accuracy in detection and vegetation mapping using LiDAR combined with high-resolution multispectral imagery (Asner et al 2008, Kim et al 2020, Liang et al 2020. LiDAR uses laser light to derive three-dimensional information (Popescu 2007).…”

“…Several studies have demonstrated its superiority for high-dimensional input data such as hyperspectral and multi-source data , even with limited training data (Ham et al 2005, Chan et al 2012, Abdel-Rahman et al 2014, Jensen et al 2020, Shoot et al 2021. Kim et al (2020) conducted vegetation mapping with LiDAR and multispectral imagery using four different classification algorithms (Support Vector Machine (SVM), RF, ML, and Mahalanobis Distance). RF classification using NAIP-LiDAR stacked image provided the highest OA (75.7%).…”

Using Airborne Lidar, Multispectral Imagery, and Field Inventory Data to Estimate Basal Area, Volume, and Aboveground Biomass in Heterogeneous Mixed Species Forests: A Case Study in Southern Alabama

“…These models usually contain at least one variable explaining tree height, another explaining canopy cover, and another that accounts for variation in the data, such as a height standard deviation variable [6,31,32]; however, the variables in these models may differ depending on the study site and the foliage type being measured [28,33,34]. Estimates of BA, volume, and AGB can also be acquired from non-parametric machine learning approaches such as random forest (RF), a machine learning algorithm that uses random and iterative samples of the data to produce regression trees and bootstraps data for robust predictive models [35][36][37].…”