Tree density has been underestimated in the mountainous regions of Northeast China

Previous attempts to quantify tree density have often underestimated the numbers of trees in mountainous regions with complex terrain. We surveyed trees with a diameter at breast height (DBH) of ≥10 cm across 1,926 plots. By utilizing recursive feature elimination (RFE), we identified six key variab...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunkun Song, Wenqiang Xie, Fang Wu, Xuefeng Cui, Xiaodong Yan, Shuaifeng Song, Jun Ren, Hui Bai, Yu Zhang, Wei Pang, Yueying Xiao, Wang Zhan
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X25005850
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850219216509075456
author Yunkun Song
Wenqiang Xie
Fang Wu
Xuefeng Cui
Xiaodong Yan
Shuaifeng Song
Jun Ren
Hui Bai
Yu Zhang
Wei Pang
Yueying Xiao
Wang Zhan
author_facet Yunkun Song
Wenqiang Xie
Fang Wu
Xuefeng Cui
Xiaodong Yan
Shuaifeng Song
Jun Ren
Hui Bai
Yu Zhang
Wei Pang
Yueying Xiao
Wang Zhan
author_sort Yunkun Song
collection DOAJ
description Previous attempts to quantify tree density have often underestimated the numbers of trees in mountainous regions with complex terrain. We surveyed trees with a diameter at breast height (DBH) of ≥10 cm across 1,926 plots. By utilizing recursive feature elimination (RFE), we identified six key variables for our meta-learner in the stacking process, including the soil silt content, soil clay content, elevation, Normalized Difference Vegetation Index (NDVI), precipitation in the wettest month, and precipitation in the coldest quarter, all of which were found to influence tree density. We developed a stacking ensemble learning algorithm, which ultimately generated a tree density map with a spatial resolution of 30 m for the mountainous regions of Northeast China. The estimated tree count is approximately 27.497 billion. Compared to global tree density datasets, our approach increased R2 to 0.454, while root mean square error (RMSE) and bias improved by 47.90 % and 74.52 %, respectively. This approach can increase the accuracy of local tree density simulations, which is crucial for the precise modeling of the forest carbon sequestration potential, the development of targeted forest conservation strategies, and the implementation of effective carbon management practices.
format Article
id doaj-art-cecb0bc9e084459cac6b4488b4bd4572
institution OA Journals
issn 1470-160X
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-cecb0bc9e084459cac6b4488b4bd45722025-08-20T02:07:27ZengElsevierEcological Indicators1470-160X2025-07-0117611365510.1016/j.ecolind.2025.113655Tree density has been underestimated in the mountainous regions of Northeast ChinaYunkun Song0Wenqiang Xie1Fang Wu2Xuefeng Cui3Xiaodong Yan4Shuaifeng Song5Jun Ren6Hui Bai7Yu Zhang8Wei Pang9Yueying Xiao10Wang Zhan11State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaSchool of Systems Science, Beijing Normal University, Beijing 100875, ChinaSchool of Systems Science, Beijing Normal University, Beijing 100875, China; Corresponding authors.State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; Corresponding authors.College of Urban and Environmental Sciences, Peking University, Beijing 100871, ChinaJilin Provincial Academy of Forestry Sciences, Changchun 130013, ChinaJilin Forest Industry Baishishan Forestry Co.,Ltd., Jiaohe 132500, ChinaJilin Forest Industry Baishishan Forestry Co.,Ltd., Jiaohe 132500, ChinaJilin Forest Industry Baishishan Forestry Co.,Ltd., Jiaohe 132500, ChinaJilin Forest Industry Baishishan Forestry Co.,Ltd., Jiaohe 132500, ChinaJilin Forest Industry Baishishan Forestry Co.,Ltd., Jiaohe 132500, ChinaPrevious attempts to quantify tree density have often underestimated the numbers of trees in mountainous regions with complex terrain. We surveyed trees with a diameter at breast height (DBH) of ≥10 cm across 1,926 plots. By utilizing recursive feature elimination (RFE), we identified six key variables for our meta-learner in the stacking process, including the soil silt content, soil clay content, elevation, Normalized Difference Vegetation Index (NDVI), precipitation in the wettest month, and precipitation in the coldest quarter, all of which were found to influence tree density. We developed a stacking ensemble learning algorithm, which ultimately generated a tree density map with a spatial resolution of 30 m for the mountainous regions of Northeast China. The estimated tree count is approximately 27.497 billion. Compared to global tree density datasets, our approach increased R2 to 0.454, while root mean square error (RMSE) and bias improved by 47.90 % and 74.52 %, respectively. This approach can increase the accuracy of local tree density simulations, which is crucial for the precise modeling of the forest carbon sequestration potential, the development of targeted forest conservation strategies, and the implementation of effective carbon management practices.http://www.sciencedirect.com/science/article/pii/S1470160X25005850Mountainous regionsForestTree densityStackingEnsemble algorithm
spellingShingle Yunkun Song
Wenqiang Xie
Fang Wu
Xuefeng Cui
Xiaodong Yan
Shuaifeng Song
Jun Ren
Hui Bai
Yu Zhang
Wei Pang
Yueying Xiao
Wang Zhan
Tree density has been underestimated in the mountainous regions of Northeast China
Ecological Indicators
Mountainous regions
Forest
Tree density
Stacking
Ensemble algorithm
title Tree density has been underestimated in the mountainous regions of Northeast China
title_full Tree density has been underestimated in the mountainous regions of Northeast China
title_fullStr Tree density has been underestimated in the mountainous regions of Northeast China
title_full_unstemmed Tree density has been underestimated in the mountainous regions of Northeast China
title_short Tree density has been underestimated in the mountainous regions of Northeast China
title_sort tree density has been underestimated in the mountainous regions of northeast china
topic Mountainous regions
Forest
Tree density
Stacking
Ensemble algorithm
url http://www.sciencedirect.com/science/article/pii/S1470160X25005850
work_keys_str_mv AT yunkunsong treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT wenqiangxie treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT fangwu treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT xuefengcui treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT xiaodongyan treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT shuaifengsong treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT junren treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT huibai treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT yuzhang treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT weipang treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT yueyingxiao treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina
AT wangzhan treedensityhasbeenunderestimatedinthemountainousregionsofnortheastchina