A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees

This study explores the potential of using Quantitative Structure Models (QSM) to predict trees' voxel-based Leaf Area Density (LAD) to reduce the workload and data redundancy in studying deciduous trees. For this purpose, leaf-on and leaf-off Terrestrial Laser Scanning (TLS) of 16 Platanus x h...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiguan Shu, Thomas Rötzer, Hadi Yazdi, Astrid Reischl, Ferdinand Ludwig
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Science of Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666017225000525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209987785129984
author Qiguan Shu
Thomas Rötzer
Hadi Yazdi
Astrid Reischl
Ferdinand Ludwig
author_facet Qiguan Shu
Thomas Rötzer
Hadi Yazdi
Astrid Reischl
Ferdinand Ludwig
author_sort Qiguan Shu
collection DOAJ
description This study explores the potential of using Quantitative Structure Models (QSM) to predict trees' voxel-based Leaf Area Density (LAD) to reduce the workload and data redundancy in studying deciduous trees. For this purpose, leaf-on and leaf-off Terrestrial Laser Scanning (TLS) of 16 Platanus x hispanica trees on streets were utilized. QSMs were extracted and interpreted into QSM indexes corresponding to voxels, a novel approach introduced in this study. Twelve standard regression models were tested to predict the LAD value for each voxel using its QSM indexes. The Hist Gradient Boosting Regressor (HGBR) model demonstrated the best performance, with an R-squared score of 0.56 and a mean absolute error of 0.0187 m2/m3 (16.33 %) in the LAD prediction. This deviation mainly happened at the crown center, where branches were dense while leaves were few. The trained model was also applied to another set of 13 young plane trees of different tree sizes at a nursery. Their predicted Leaf Area Index (LAI) was compared to the LAI measured indirectly by hemispherical photography, showing a deviation of 0.12 m2/m2 (8.6 %) for the 3 largest trees with the closest Diameter at Breast Height (DBH) to the street trees. The deviations are larger for young nursery trees with smaller DBHs. Therefore, further experiments are needed to optimize the voxel size and adapt the model to different species with varying crown sizes.
format Article
id doaj-art-cf8824f8be694c1b9df8e69066a60b2c
institution OA Journals
issn 2666-0172
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Science of Remote Sensing
spelling doaj-art-cf8824f8be694c1b9df8e69066a60b2c2025-08-20T02:09:52ZengElsevierScience of Remote Sensing2666-01722025-12-011210024610.1016/j.srs.2025.100246A comparative study of voxel-based leaf area density estimation from quantitative structure models of treesQiguan Shu0Thomas Rötzer1Hadi Yazdi2Astrid Reischl3Ferdinand Ludwig4Professorship for Green Technologies in Landscape Architecture, TUM School of Engineering and Design, Technical University of Munich, Germany; Corresponding author.Chair for Strategic Landscape Planning and Management, Technical University of Munich, GermanyProfessorship for Green Technologies in Landscape Architecture, TUM School of Engineering and Design, Technical University of Munich, GermanyChair for Strategic Landscape Planning and Management, Technical University of Munich, GermanyProfessorship for Green Technologies in Landscape Architecture, TUM School of Engineering and Design, Technical University of Munich, GermanyThis study explores the potential of using Quantitative Structure Models (QSM) to predict trees' voxel-based Leaf Area Density (LAD) to reduce the workload and data redundancy in studying deciduous trees. For this purpose, leaf-on and leaf-off Terrestrial Laser Scanning (TLS) of 16 Platanus x hispanica trees on streets were utilized. QSMs were extracted and interpreted into QSM indexes corresponding to voxels, a novel approach introduced in this study. Twelve standard regression models were tested to predict the LAD value for each voxel using its QSM indexes. The Hist Gradient Boosting Regressor (HGBR) model demonstrated the best performance, with an R-squared score of 0.56 and a mean absolute error of 0.0187 m2/m3 (16.33 %) in the LAD prediction. This deviation mainly happened at the crown center, where branches were dense while leaves were few. The trained model was also applied to another set of 13 young plane trees of different tree sizes at a nursery. Their predicted Leaf Area Index (LAI) was compared to the LAI measured indirectly by hemispherical photography, showing a deviation of 0.12 m2/m2 (8.6 %) for the 3 largest trees with the closest Diameter at Breast Height (DBH) to the street trees. The deviations are larger for young nursery trees with smaller DBHs. Therefore, further experiments are needed to optimize the voxel size and adapt the model to different species with varying crown sizes.http://www.sciencedirect.com/science/article/pii/S2666017225000525Urban forestryTerrestrial laser scanningQuantitative structural modelLeaf area densityTree information modeling
spellingShingle Qiguan Shu
Thomas Rötzer
Hadi Yazdi
Astrid Reischl
Ferdinand Ludwig
A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
Science of Remote Sensing
Urban forestry
Terrestrial laser scanning
Quantitative structural model
Leaf area density
Tree information modeling
title A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
title_full A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
title_fullStr A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
title_full_unstemmed A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
title_short A comparative study of voxel-based leaf area density estimation from quantitative structure models of trees
title_sort comparative study of voxel based leaf area density estimation from quantitative structure models of trees
topic Urban forestry
Terrestrial laser scanning
Quantitative structural model
Leaf area density
Tree information modeling
url http://www.sciencedirect.com/science/article/pii/S2666017225000525
work_keys_str_mv AT qiguanshu acomparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT thomasrotzer acomparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT hadiyazdi acomparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT astridreischl acomparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT ferdinandludwig acomparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT qiguanshu comparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT thomasrotzer comparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT hadiyazdi comparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT astridreischl comparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees
AT ferdinandludwig comparativestudyofvoxelbasedleafareadensityestimationfromquantitativestructuremodelsoftrees