Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR

Chlorophyll plays a significant role in evaluating vegetation health and forest carbon sink. In this study, a total of 36 characteristic variables from hyperspectral image and lidar point cloud data acquired through an unmanned aerial vehicle (UAV) platform were used to evaluate the accuracy of stat...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhuonan Meng, Ying Yu, Xiguang Yang, Tao Yang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/10/1699
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850125880525848576
author Zhuonan Meng
Ying Yu
Xiguang Yang
Tao Yang
author_facet Zhuonan Meng
Ying Yu
Xiguang Yang
Tao Yang
author_sort Zhuonan Meng
collection DOAJ
description Chlorophyll plays a significant role in evaluating vegetation health and forest carbon sink. In this study, a total of 36 characteristic variables from hyperspectral image and lidar point cloud data acquired through an unmanned aerial vehicle (UAV) platform were used to evaluate the accuracy of statistical models including multiple stepwise regression, BP neural network, BP neural network optimized by firefly algorithm, random forest, and the mixed data-driven mechanistic model PROSPECT model in estimating chlorophyll content for three different forest types in Maoershan Forest Farm of Northeast Forestry University in Heilongjiang Province, namely coniferous forest, broad-leaved forest, and coniferous–broad-leaved mixed forest. The accuracy of the models was evaluated by the coefficient of determination (R<sup>2</sup>) and root mean square error (RMSE). The results show that random forest (R<sup>2</sup> = 0.59–0.64, RMSE = 3.79–5.83 µg·cm<sup>−2</sup>) among all statistical models is superior to other models. The accuracy of the mechanism model was the highest (R<sup>2</sup> = 0.97, RMSE = 3.40 µg·cm<sup>−2</sup>). There were significant differences in chlorophyll content among different forest types. It ranged from 25.25 to 31.60 µg·cm<sup>−2</sup> for broad-leaved forests, which was higher than that of coniferous and broad-leaved mixed forests (13.52–23.93 µg·cm<sup>−2</sup>) and coniferous forests (6.40–13.71 µg·cm<sup>−2</sup>). In the horizontal direction, the chlorophyll content near the center of the canopy was lower than that at the edge of the canopy. In the vertical direction, there was no significant difference in chlorophyll content between different canopies of <i>Pinus sylvestris</i> var. <i>mongolica</i>, while there was a significant difference in chlorophyll content between the upper, middle, and lower canopies of <i>Juglans mandshurica</i>. For different tree species, the variation in chlorophyll with crown height was different.
format Article
id doaj-art-229fc2c3838145ed88cf3eefcf4b8b64
institution OA Journals
issn 2072-4292
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-229fc2c3838145ed88cf3eefcf4b8b642025-08-20T02:34:02ZengMDPI AGRemote Sensing2072-42922025-05-011710169910.3390/rs17101699Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDARZhuonan Meng0Ying Yu1Xiguang Yang2Tao Yang3School of Forestry, Northeast Forestry University, Harbin 150040, ChinaSchool of Forestry, Northeast Forestry University, Harbin 150040, ChinaSchool of Forestry, Northeast Forestry University, Harbin 150040, ChinaSchool of Forestry, Northeast Forestry University, Harbin 150040, ChinaChlorophyll plays a significant role in evaluating vegetation health and forest carbon sink. In this study, a total of 36 characteristic variables from hyperspectral image and lidar point cloud data acquired through an unmanned aerial vehicle (UAV) platform were used to evaluate the accuracy of statistical models including multiple stepwise regression, BP neural network, BP neural network optimized by firefly algorithm, random forest, and the mixed data-driven mechanistic model PROSPECT model in estimating chlorophyll content for three different forest types in Maoershan Forest Farm of Northeast Forestry University in Heilongjiang Province, namely coniferous forest, broad-leaved forest, and coniferous–broad-leaved mixed forest. The accuracy of the models was evaluated by the coefficient of determination (R<sup>2</sup>) and root mean square error (RMSE). The results show that random forest (R<sup>2</sup> = 0.59–0.64, RMSE = 3.79–5.83 µg·cm<sup>−2</sup>) among all statistical models is superior to other models. The accuracy of the mechanism model was the highest (R<sup>2</sup> = 0.97, RMSE = 3.40 µg·cm<sup>−2</sup>). There were significant differences in chlorophyll content among different forest types. It ranged from 25.25 to 31.60 µg·cm<sup>−2</sup> for broad-leaved forests, which was higher than that of coniferous and broad-leaved mixed forests (13.52–23.93 µg·cm<sup>−2</sup>) and coniferous forests (6.40–13.71 µg·cm<sup>−2</sup>). In the horizontal direction, the chlorophyll content near the center of the canopy was lower than that at the edge of the canopy. In the vertical direction, there was no significant difference in chlorophyll content between different canopies of <i>Pinus sylvestris</i> var. <i>mongolica</i>, while there was a significant difference in chlorophyll content between the upper, middle, and lower canopies of <i>Juglans mandshurica</i>. For different tree species, the variation in chlorophyll with crown height was different.https://www.mdpi.com/2072-4292/17/10/1699UAVhyperspectralLiDARforest standchlorophyllmechanism models
spellingShingle Zhuonan Meng
Ying Yu
Xiguang Yang
Tao Yang
Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
Remote Sensing
UAV
hyperspectral
LiDAR
forest stand
chlorophyll
mechanism models
title Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
title_full Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
title_fullStr Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
title_full_unstemmed Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
title_short Estimation of Chlorophyll Content at Stand and Individual Tree Level by UAV Hyperspectral Combined with LiDAR
title_sort estimation of chlorophyll content at stand and individual tree level by uav hyperspectral combined with lidar
topic UAV
hyperspectral
LiDAR
forest stand
chlorophyll
mechanism models
url https://www.mdpi.com/2072-4292/17/10/1699
work_keys_str_mv AT zhuonanmeng estimationofchlorophyllcontentatstandandindividualtreelevelbyuavhyperspectralcombinedwithlidar
AT yingyu estimationofchlorophyllcontentatstandandindividualtreelevelbyuavhyperspectralcombinedwithlidar
AT xiguangyang estimationofchlorophyllcontentatstandandindividualtreelevelbyuavhyperspectralcombinedwithlidar
AT taoyang estimationofchlorophyllcontentatstandandindividualtreelevelbyuavhyperspectralcombinedwithlidar