Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR

Diameter at breast height (DBH) is a fundamental measurement indicator in forest resource surveys. This study explores the use of uncrewed aerial vehicle light detection and ranging (UAV-LiDAR) for individual tree DBH inversion in Chinese fir (<italic>Cunninghamia lanceolata</italic>) pl...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiuen Xu, Yinyin Zhao, Xuejian Li, Lujin Lv, Jiacong Yu, Meixuan Song, Lei Huang, Fangjie Mao, Huaqiang Du
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10964709/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324415589810176
author Jiuen Xu
Yinyin Zhao
Xuejian Li
Lujin Lv
Jiacong Yu
Meixuan Song
Lei Huang
Fangjie Mao
Huaqiang Du
author_facet Jiuen Xu
Yinyin Zhao
Xuejian Li
Lujin Lv
Jiacong Yu
Meixuan Song
Lei Huang
Fangjie Mao
Huaqiang Du
author_sort Jiuen Xu
collection DOAJ
description Diameter at breast height (DBH) is a fundamental measurement indicator in forest resource surveys. This study explores the use of uncrewed aerial vehicle light detection and ranging (UAV-LiDAR) for individual tree DBH inversion in Chinese fir (<italic>Cunninghamia lanceolata</italic>) plantations with complex terrain and rich understory vegetation, and compares the results with those from Backpack-LiDAR. First, individual tree segmentation was performed on the UAV-LiDAR point cloud data from the study area, and individual tree point cloud feature variables were extracted by applying different height thresholds. Then, three types of models&#x2014;statistical model multiple linear regression (MLR), traditional machine learning models including K-nearest neighbor regression and support vector regression, and ensemble learning models including random forest, extreme gradient boosting, and categorical boosting (CatBoost)&#x2014;were employed for DBH inversion. The results show that: 1) Using data above a 5-m height threshold effectively reduces interference from understory vegetation; 2) Key feature variables, such as canopy volume (V), tree height (Hmax), the interquartile range of cumulative height percentiles (AIHiq), and canopy area (S), significantly affect DBH inversion, with V contributing 25% to the feature importance; 3) Ensemble learning models, particularly CatBoost, outperform the other models, achieving an <italic>R</italic><sup>2</sup> of 0.81% &#x2014;14.1% higher than MLR; 4) DBH inversion closely matches field observed data, and UAV-LiDAR performs better than Backpack-LiDAR in complex forest environments. This study provides an efficient and cost-effective approach to forest resource monitoring.
format Article
id doaj-art-e0c4e48868b44292bed947d086828af2
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-e0c4e48868b44292bed947d086828af22025-08-20T03:48:43ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118108461086310.1109/JSTARS.2025.356070410964709Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDARJiuen Xu0Yinyin Zhao1Xuejian Li2https://orcid.org/0000-0002-7553-2576Lujin Lv3Jiacong Yu4Meixuan Song5Lei Huang6Fangjie Mao7https://orcid.org/0000-0003-2005-3452Huaqiang Du8https://orcid.org/0000-0002-6765-2279State Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaState Key Laboratory of Subtropical Silviculture, the Key Laboratory of Carbon Cycling in Forest Ecosystems and Carbon Sequestration of Zhejiang Province, and the School of Environmental and Resources Science, Zhejiang A &amp; F University, Lin'an, ChinaDiameter at breast height (DBH) is a fundamental measurement indicator in forest resource surveys. This study explores the use of uncrewed aerial vehicle light detection and ranging (UAV-LiDAR) for individual tree DBH inversion in Chinese fir (<italic>Cunninghamia lanceolata</italic>) plantations with complex terrain and rich understory vegetation, and compares the results with those from Backpack-LiDAR. First, individual tree segmentation was performed on the UAV-LiDAR point cloud data from the study area, and individual tree point cloud feature variables were extracted by applying different height thresholds. Then, three types of models&#x2014;statistical model multiple linear regression (MLR), traditional machine learning models including K-nearest neighbor regression and support vector regression, and ensemble learning models including random forest, extreme gradient boosting, and categorical boosting (CatBoost)&#x2014;were employed for DBH inversion. The results show that: 1) Using data above a 5-m height threshold effectively reduces interference from understory vegetation; 2) Key feature variables, such as canopy volume (V), tree height (Hmax), the interquartile range of cumulative height percentiles (AIHiq), and canopy area (S), significantly affect DBH inversion, with V contributing 25% to the feature importance; 3) Ensemble learning models, particularly CatBoost, outperform the other models, achieving an <italic>R</italic><sup>2</sup> of 0.81% &#x2014;14.1% higher than MLR; 4) DBH inversion closely matches field observed data, and UAV-LiDAR performs better than Backpack-LiDAR in complex forest environments. This study provides an efficient and cost-effective approach to forest resource monitoring.https://ieeexplore.ieee.org/document/10964709/Categorical boosting (Catboost)Chinese firdiameter at breast height (DBH)ensemble learningunmanned aerial vehicle light detection and ranging (UAV-LiDAR)
spellingShingle Jiuen Xu
Yinyin Zhao
Xuejian Li
Lujin Lv
Jiacong Yu
Meixuan Song
Lei Huang
Fangjie Mao
Huaqiang Du
Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Categorical boosting (Catboost)
Chinese fir
diameter at breast height (DBH)
ensemble learning
unmanned aerial vehicle light detection and ranging (UAV-LiDAR)
title Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
title_full Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
title_fullStr Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
title_full_unstemmed Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
title_short Improving Chinese Fir Plantations DBH Inversion Accuracy Using Ensemble Learning Models Base on UAV-LiDAR
title_sort improving chinese fir plantations dbh inversion accuracy using ensemble learning models base on uav lidar
topic Categorical boosting (Catboost)
Chinese fir
diameter at breast height (DBH)
ensemble learning
unmanned aerial vehicle light detection and ranging (UAV-LiDAR)
url https://ieeexplore.ieee.org/document/10964709/
work_keys_str_mv AT jiuenxu improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT yinyinzhao improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT xuejianli improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT lujinlv improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT jiacongyu improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT meixuansong improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT leihuang improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT fangjiemao improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar
AT huaqiangdu improvingchinesefirplantationsdbhinversionaccuracyusingensemblelearningmodelsbaseonuavlidar