Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data

The spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tr...

Full description

Bibliographic Details
Main Authors: Haoming Wan, Yunwei Tang, Linhai Jing, Hui Li, Fang Qiu, Wenjin Wu
Format: Article
Language:English
Published: MDPI AG 2021-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/13/1/144
_version_ 1797542368266682368
author Haoming Wan
Yunwei Tang
Linhai Jing
Hui Li
Fang Qiu
Wenjin Wu
author_facet Haoming Wan
Yunwei Tang
Linhai Jing
Hui Li
Fang Qiu
Wenjin Wu
author_sort Haoming Wan
collection DOAJ
description The spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tree species in a timely and accurate manner. At present, a large amount of remote sensing data have been accumulated, including high-spatial-resolution images, time-series images, light detection and ranging (LiDAR) data, etc. However, these data have not been fully utilized. To accurately identify the tree species of forest stands, various and complementary data need to be synthesized for classification. A curve matching based method called the fusion of spectral image and point data (FSP) algorithm was developed to fuse high-spatial-resolution images, time-series images, and LiDAR data for forest stand classification. In this method, the multispectral Sentinel-2 image and high-spatial-resolution aerial images were first fused. Then, the fused images were segmented to derive forest stands, which are the basic unit for classification. To extract features from forest stands, the gray histogram of each band was extracted from the aerial images. The average reflectance in each stand was calculated and stacked for the time-series images. The profile curve of forest structure was generated from the LiDAR data. Finally, the features of forest stands were compared with training samples using curve matching methods to derive the tree species. The developed method was tested in a forest farm to classify 11 tree species. The average accuracy of the FSP method for ten performances was between 0.900 and 0.913, and the maximum accuracy was 0.945. The experiments demonstrate that the FSP method is more accurate and stable than traditional machine learning classification methods.
first_indexed 2024-03-10T13:29:36Z
format Article
id doaj.art-0089c540815344e0ac7155fc3eb2f2bb
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-10T13:29:36Z
publishDate 2021-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-0089c540815344e0ac7155fc3eb2f2bb2023-11-21T08:10:36ZengMDPI AGRemote Sensing2072-42922021-01-0113114410.3390/rs13010144Tree Species Classification of Forest Stands Using Multisource Remote Sensing DataHaoming Wan0Yunwei Tang1Linhai Jing2Hui Li3Fang Qiu4Wenjin Wu5Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaGeospatial Information Sciences, The University of Texas at Dallas, 800 West Campbell Road, Richardson, TX 75080, USAKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaThe spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tree species in a timely and accurate manner. At present, a large amount of remote sensing data have been accumulated, including high-spatial-resolution images, time-series images, light detection and ranging (LiDAR) data, etc. However, these data have not been fully utilized. To accurately identify the tree species of forest stands, various and complementary data need to be synthesized for classification. A curve matching based method called the fusion of spectral image and point data (FSP) algorithm was developed to fuse high-spatial-resolution images, time-series images, and LiDAR data for forest stand classification. In this method, the multispectral Sentinel-2 image and high-spatial-resolution aerial images were first fused. Then, the fused images were segmented to derive forest stands, which are the basic unit for classification. To extract features from forest stands, the gray histogram of each band was extracted from the aerial images. The average reflectance in each stand was calculated and stacked for the time-series images. The profile curve of forest structure was generated from the LiDAR data. Finally, the features of forest stands were compared with training samples using curve matching methods to derive the tree species. The developed method was tested in a forest farm to classify 11 tree species. The average accuracy of the FSP method for ten performances was between 0.900 and 0.913, and the maximum accuracy was 0.945. The experiments demonstrate that the FSP method is more accurate and stable than traditional machine learning classification methods.https://www.mdpi.com/2072-4292/13/1/144forest stands classificationcurve matchingdata fusionmultisource remote sensing datasegmentationtree species mapping
spellingShingle Haoming Wan
Yunwei Tang
Linhai Jing
Hui Li
Fang Qiu
Wenjin Wu
Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
Remote Sensing
forest stands classification
curve matching
data fusion
multisource remote sensing data
segmentation
tree species mapping
title Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
title_full Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
title_fullStr Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
title_full_unstemmed Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
title_short Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data
title_sort tree species classification of forest stands using multisource remote sensing data
topic forest stands classification
curve matching
data fusion
multisource remote sensing data
segmentation
tree species mapping
url https://www.mdpi.com/2072-4292/13/1/144
work_keys_str_mv AT haomingwan treespeciesclassificationofforeststandsusingmultisourceremotesensingdata
AT yunweitang treespeciesclassificationofforeststandsusingmultisourceremotesensingdata
AT linhaijing treespeciesclassificationofforeststandsusingmultisourceremotesensingdata
AT huili treespeciesclassificationofforeststandsusingmultisourceremotesensingdata
AT fangqiu treespeciesclassificationofforeststandsusingmultisourceremotesensingdata
AT wenjinwu treespeciesclassificationofforeststandsusingmultisourceremotesensingdata