Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).

Leaf Area Index (LAI) is a critical indicator of vegetation growth and ecological function. Unlike the relatively uniform crop types and planting methods typically found in agricultural fields, parks typically feature a diverse range of plant species, varied configurations, and complex vertical stru...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Li, Bocheng Wang, Xuefei Zhao, Yichuan Zhang, Lifang Qiao
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0320608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327971294248960
author Yan Li
Bocheng Wang
Xuefei Zhao
Yichuan Zhang
Lifang Qiao
author_facet Yan Li
Bocheng Wang
Xuefei Zhao
Yichuan Zhang
Lifang Qiao
author_sort Yan Li
collection DOAJ
description Leaf Area Index (LAI) is a critical indicator of vegetation growth and ecological function. Unlike the relatively uniform crop types and planting methods typically found in agricultural fields, parks typically feature a diverse range of plant species, varied configurations, and complex vertical structures, making LAI estimation more complex and challenging. To improve the accuracy of LAI estimation in urban parks, this study, by combining unmanned aerial vehicle (UAV) multispectral remote sensing technology with Random Forest (RF) to conduct the inversion and analysis of LAI in Xinxiang People's Park. High-resolution images are obtained using multispectral sensors carried by a UAV, which are then used to calculate the Normalized Difference Vegetation Index (NDVI). Combined with ground-measured vegetation LAI data, this study applies RF to estimate the park LAI. The results indicate that the average LAI of Xinxiang People's Park is 2.30 (for the entire park). excluding the hard surfaces (which account for 36.05%), the average LAI increases to 3.59, indicating good vegetation conditions. The LAI of the park and its distribution are influenced by factors such as plant species, configuration patterns, planting density, aesthetic design, and site function. Accurate LAI inversion is crucial for effective management and optimization of these green spaces. RF can effectively capture the complex nonlinear relationship between NDVI and LAI, with a coefficient of determination (R²) of 0.54 and a root mean square error (RMSE) of 0.91. Although the accuracy is still insufficient, RF's ability to handle nonlinear relationships makes it an effective tool for LAI inversion in complex vegetation environments. LAI inversion of park vegetation based on UAV multispectral imagery can provide valuable insights for the management and optimization of park vegetation.
format Article
id doaj-art-5dbe1e036faf40859f663e98ac9af45d
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-5dbe1e036faf40859f663e98ac9af45d2025-08-20T03:47:44ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e032060810.1371/journal.pone.0320608Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).Yan LiBocheng WangXuefei ZhaoYichuan ZhangLifang QiaoLeaf Area Index (LAI) is a critical indicator of vegetation growth and ecological function. Unlike the relatively uniform crop types and planting methods typically found in agricultural fields, parks typically feature a diverse range of plant species, varied configurations, and complex vertical structures, making LAI estimation more complex and challenging. To improve the accuracy of LAI estimation in urban parks, this study, by combining unmanned aerial vehicle (UAV) multispectral remote sensing technology with Random Forest (RF) to conduct the inversion and analysis of LAI in Xinxiang People's Park. High-resolution images are obtained using multispectral sensors carried by a UAV, which are then used to calculate the Normalized Difference Vegetation Index (NDVI). Combined with ground-measured vegetation LAI data, this study applies RF to estimate the park LAI. The results indicate that the average LAI of Xinxiang People's Park is 2.30 (for the entire park). excluding the hard surfaces (which account for 36.05%), the average LAI increases to 3.59, indicating good vegetation conditions. The LAI of the park and its distribution are influenced by factors such as plant species, configuration patterns, planting density, aesthetic design, and site function. Accurate LAI inversion is crucial for effective management and optimization of these green spaces. RF can effectively capture the complex nonlinear relationship between NDVI and LAI, with a coefficient of determination (R²) of 0.54 and a root mean square error (RMSE) of 0.91. Although the accuracy is still insufficient, RF's ability to handle nonlinear relationships makes it an effective tool for LAI inversion in complex vegetation environments. LAI inversion of park vegetation based on UAV multispectral imagery can provide valuable insights for the management and optimization of park vegetation.https://doi.org/10.1371/journal.pone.0320608
spellingShingle Yan Li
Bocheng Wang
Xuefei Zhao
Yichuan Zhang
Lifang Qiao
Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
PLoS ONE
title Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
title_full Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
title_fullStr Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
title_full_unstemmed Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
title_short Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF).
title_sort inversion and analysis of leaf area index lai of urban park based on unmanned aerial vehicle uav multispectral remote sensing and random forest rf
url https://doi.org/10.1371/journal.pone.0320608
work_keys_str_mv AT yanli inversionandanalysisofleafareaindexlaiofurbanparkbasedonunmannedaerialvehicleuavmultispectralremotesensingandrandomforestrf
AT bochengwang inversionandanalysisofleafareaindexlaiofurbanparkbasedonunmannedaerialvehicleuavmultispectralremotesensingandrandomforestrf
AT xuefeizhao inversionandanalysisofleafareaindexlaiofurbanparkbasedonunmannedaerialvehicleuavmultispectralremotesensingandrandomforestrf
AT yichuanzhang inversionandanalysisofleafareaindexlaiofurbanparkbasedonunmannedaerialvehicleuavmultispectralremotesensingandrandomforestrf
AT lifangqiao inversionandanalysisofleafareaindexlaiofurbanparkbasedonunmannedaerialvehicleuavmultispectralremotesensingandrandomforestrf