Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images

The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Ying Sun [verfasserIn] Jianfeng Huang [verfasserIn] Zurui Ao [verfasserIn] Dazhao Lao [verfasserIn] Qinchuan Xin [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2019

Schlagwörter:	tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning

Übergeordnetes Werk:	In: Forests - MDPI AG, 2010, 10(2019), 11, p 1047
Übergeordnetes Werk:	volume:10 ; year:2019 ; number:11, p 1047

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/f10111047

Katalog-ID:	DOAJ038058790

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ038058790
003	DE-627
005	20230308015107.0
007	cr uuu---uuuuu
008	230227s2019 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/f10111047 \|2 doi
035			\|a (DE-627)DOAJ038058790
035			\|a (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a QK900-989
100	0		\|a Ying Sun \|e verfasserin \|4 aut
245	1	0	\|a Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
264		1	\|c 2019
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.
650		4	\|a tree species diversity
650		4	\|a tropical wetland
650		4	\|a high-resolution remote sensing images
650		4	\|a lidar
650		4	\|a individual tree level
650		4	\|a deep learning
653		0	\|a Plant ecology
700	0		\|a Jianfeng Huang \|e verfasserin \|4 aut
700	0		\|a Zurui Ao \|e verfasserin \|4 aut
700	0		\|a Dazhao Lao \|e verfasserin \|4 aut
700	0		\|a Qinchuan Xin \|e verfasserin \|4 aut
773	0	8	\|i In \|t Forests \|d MDPI AG, 2010 \|g 10(2019), 11, p 1047 \|w (DE-627)614095689 \|w (DE-600)2527081-3 \|x 19994907 \|7 nnns
773	1	8	\|g volume:10 \|g year:2019 \|g number:11, p 1047
856	4	0	\|u https://doi.org/10.3390/f10111047 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/1999-4907/10/11/1047 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1999-4907 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2147
912			\|a GBV_ILN_2148
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 10 \|j 2019 \|e 11, p 1047

Indexfelder

author_variant	y s ys j h jh z a za d l dl q x qx
matchkey_str	article:19994907:2019----::eperigprahsoteapnoteseisiestiarpclelnuigibreiaadihp
hierarchy_sort_str	2019
callnumber-subject-code	QK
publishDate	2019
allfields	10.3390/f10111047 doi (DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133 DE-627 ger DE-627 rakwb eng QK900-989 Ying Sun verfasserin aut Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology Jianfeng Huang verfasserin aut Zurui Ao verfasserin aut Dazhao Lao verfasserin aut Qinchuan Xin verfasserin aut In Forests MDPI AG, 2010 10(2019), 11, p 1047 (DE-627)614095689 (DE-600)2527081-3 19994907 nnns volume:10 year:2019 number:11, p 1047 https://doi.org/10.3390/f10111047 kostenfrei https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 kostenfrei https://www.mdpi.com/1999-4907/10/11/1047 kostenfrei https://doaj.org/toc/1999-4907 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 10 2019 11, p 1047
spelling	10.3390/f10111047 doi (DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133 DE-627 ger DE-627 rakwb eng QK900-989 Ying Sun verfasserin aut Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology Jianfeng Huang verfasserin aut Zurui Ao verfasserin aut Dazhao Lao verfasserin aut Qinchuan Xin verfasserin aut In Forests MDPI AG, 2010 10(2019), 11, p 1047 (DE-627)614095689 (DE-600)2527081-3 19994907 nnns volume:10 year:2019 number:11, p 1047 https://doi.org/10.3390/f10111047 kostenfrei https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 kostenfrei https://www.mdpi.com/1999-4907/10/11/1047 kostenfrei https://doaj.org/toc/1999-4907 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 10 2019 11, p 1047
allfields_unstemmed	10.3390/f10111047 doi (DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133 DE-627 ger DE-627 rakwb eng QK900-989 Ying Sun verfasserin aut Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology Jianfeng Huang verfasserin aut Zurui Ao verfasserin aut Dazhao Lao verfasserin aut Qinchuan Xin verfasserin aut In Forests MDPI AG, 2010 10(2019), 11, p 1047 (DE-627)614095689 (DE-600)2527081-3 19994907 nnns volume:10 year:2019 number:11, p 1047 https://doi.org/10.3390/f10111047 kostenfrei https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 kostenfrei https://www.mdpi.com/1999-4907/10/11/1047 kostenfrei https://doaj.org/toc/1999-4907 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 10 2019 11, p 1047
allfieldsGer	10.3390/f10111047 doi (DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133 DE-627 ger DE-627 rakwb eng QK900-989 Ying Sun verfasserin aut Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology Jianfeng Huang verfasserin aut Zurui Ao verfasserin aut Dazhao Lao verfasserin aut Qinchuan Xin verfasserin aut In Forests MDPI AG, 2010 10(2019), 11, p 1047 (DE-627)614095689 (DE-600)2527081-3 19994907 nnns volume:10 year:2019 number:11, p 1047 https://doi.org/10.3390/f10111047 kostenfrei https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 kostenfrei https://www.mdpi.com/1999-4907/10/11/1047 kostenfrei https://doaj.org/toc/1999-4907 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 10 2019 11, p 1047
allfieldsSound	10.3390/f10111047 doi (DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133 DE-627 ger DE-627 rakwb eng QK900-989 Ying Sun verfasserin aut Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity. tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology Jianfeng Huang verfasserin aut Zurui Ao verfasserin aut Dazhao Lao verfasserin aut Qinchuan Xin verfasserin aut In Forests MDPI AG, 2010 10(2019), 11, p 1047 (DE-627)614095689 (DE-600)2527081-3 19994907 nnns volume:10 year:2019 number:11, p 1047 https://doi.org/10.3390/f10111047 kostenfrei https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 kostenfrei https://www.mdpi.com/1999-4907/10/11/1047 kostenfrei https://doaj.org/toc/1999-4907 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700 AR 10 2019 11, p 1047
language	English
source	In Forests 10(2019), 11, p 1047 volume:10 year:2019 number:11, p 1047
sourceStr	In Forests 10(2019), 11, p 1047 volume:10 year:2019 number:11, p 1047
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning Plant ecology
isfreeaccess_bool	true
container_title	Forests
authorswithroles_txt_mv	Ying Sun @@aut@@ Jianfeng Huang @@aut@@ Zurui Ao @@aut@@ Dazhao Lao @@aut@@ Qinchuan Xin @@aut@@
publishDateDaySort_date	2019-01-01T00:00:00Z
hierarchy_top_id	614095689
id	DOAJ038058790
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ038058790</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230308015107.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230227s2019 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/f10111047</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ038058790</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QK900-989</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Ying Sun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tree species diversity</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tropical wetland</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">high-resolution remote sensing images</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lidar</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">individual tree level</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Plant ecology</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jianfeng Huang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zurui Ao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dazhao Lao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Qinchuan Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Forests</subfield><subfield code="d">MDPI AG, 2010</subfield><subfield code="g">10(2019), 11, p 1047</subfield><subfield code="w">(DE-627)614095689</subfield><subfield code="w">(DE-600)2527081-3</subfield><subfield code="x">19994907</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:11, p 1047</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/f10111047</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/1999-4907/10/11/1047</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1999-4907</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">10</subfield><subfield code="j">2019</subfield><subfield code="e">11, p 1047</subfield></datafield></record></collection>
callnumber-first	Q - Science
author	Ying Sun
spellingShingle	Ying Sun misc QK900-989 misc tree species diversity misc tropical wetland misc high-resolution remote sensing images misc lidar misc individual tree level misc deep learning misc Plant ecology Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
authorStr	Ying Sun
ppnlink_with_tag_str_mv	@@773@@(DE-627)614095689
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	QK900-989
illustrated	Not Illustrated
issn	19994907
topic_title	QK900-989 Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images tree species diversity tropical wetland high-resolution remote sensing images lidar individual tree level deep learning
topic	misc QK900-989 misc tree species diversity misc tropical wetland misc high-resolution remote sensing images misc lidar misc individual tree level misc deep learning misc Plant ecology
topic_unstemmed	misc QK900-989 misc tree species diversity misc tropical wetland misc high-resolution remote sensing images misc lidar misc individual tree level misc deep learning misc Plant ecology
topic_browse	misc QK900-989 misc tree species diversity misc tropical wetland misc high-resolution remote sensing images misc lidar misc individual tree level misc deep learning misc Plant ecology
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Forests
hierarchy_parent_id	614095689
hierarchy_top_title	Forests
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)614095689 (DE-600)2527081-3
title	Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
ctrlnum	(DE-627)DOAJ038058790 (DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133
title_full	Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
author_sort	Ying Sun
journal	Forests
journalStr	Forests
callnumber-first-code	Q
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2019
contenttype_str_mv	txt
author_browse	Ying Sun Jianfeng Huang Zurui Ao Dazhao Lao Qinchuan Xin
container_volume	10
class	QK900-989
format_se	Elektronische Aufsätze
author-letter	Ying Sun
doi_str_mv	10.3390/f10111047
author2-role	verfasserin
title_sort	deep learning approaches for the mapping of tree species diversity in a tropical wetland using airborne lidar and high-spatial-resolution remote sensing images
callnumber	QK900-989
title_auth	Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
abstract	The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.
abstractGer	The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.
abstract_unstemmed	The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4367 GBV_ILN_4700
container_issue	11, p 1047
title_short	Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images
url	https://doi.org/10.3390/f10111047 https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133 https://www.mdpi.com/1999-4907/10/11/1047 https://doaj.org/toc/1999-4907
remote_bool	true
author2	Jianfeng Huang Zurui Ao Dazhao Lao Qinchuan Xin
author2Str	Jianfeng Huang Zurui Ao Dazhao Lao Qinchuan Xin
ppnlink	614095689
callnumber-subject	QK - Botany
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/f10111047
callnumber-a	QK900-989
up_date	2024-07-03T15:46:44.285Z
_version_	1803573373735796736
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ038058790</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230308015107.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230227s2019 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/f10111047</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ038058790</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ86dd98b25fda49e98ba2ef3444d62133</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QK900-989</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Ying Sun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance or resource management. Remote sensing is an efficient alternative to traditional field work to map tree species diversity over large areas. Previous studies have used light detection and ranging (LiDAR) and imaging spectroscopy (hyperspectral or multispectral remote sensing) for species richness prediction. The recent development of very high spatial resolution (VHR) RGB images has enabled detailed characterization of canopies and forest structures. In this study, we developed a three-step workflow for mapping tree species diversity, the aim of which was to increase knowledge of tree species diversity assessment using deep learning in a tropical wetland (Haizhu Wetland) in South China based on VHR-RGB images and LiDAR points. Firstly, individual trees were detected based on a canopy height model (CHM, derived from LiDAR points) by the local-maxima-based method in the FUSION software (Version 3.70, Seattle, USA). Then, tree species at the individual tree level were identified via a patch-based image input method, which cropped the RGB images into small patches (the individually detected trees) based on the tree apexes detected. Three different deep learning methods (i.e., AlexNet, VGG16, and ResNet50) were modified to classify the tree species, as they can make good use of the spatial context information. Finally, four diversity indices, namely, the Margalef richness index, the Shannon−Wiener diversity index, the Simpson diversity index, and the Pielou evenness index, were calculated from the fixed subset with a size of 30 × 30 m for assessment. In the classification phase, VGG16 had the best performance, with an overall accuracy of 73.25% for 18 tree species. Based on the classification results, mapping of tree species diversity showed reasonable agreement with field survey data (<i<R</i<<sup<2</sup<<sub<Margalef</sub< = 0.4562, root-mean-square error RMSE<sub<Margalef</sub< = 0.5629; <i<R</i<<sup<2</sup<<sub<Shannon−Wiener</sub< = 0.7948, RMSE<sub<Shannon−Wiener</sub< = 0.7202; <i<R</i<<sup<2</sup<<sub<Simpson</sub< = 0.7907, RMSE<sub<Simpson</sub< = 0.1038; and <i<R</i<<sup<2</sup<<sub<Pielou</sub< = 0.5875, RMSE<sub<Pielou</sub< = 0.3053). While challenges remain for individual tree detection and species classification, the deep-learning-based solution shows potential for mapping tree species diversity.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tree species diversity</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tropical wetland</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">high-resolution remote sensing images</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lidar</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">individual tree level</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Plant ecology</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jianfeng Huang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zurui Ao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dazhao Lao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Qinchuan Xin</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Forests</subfield><subfield code="d">MDPI AG, 2010</subfield><subfield code="g">10(2019), 11, p 1047</subfield><subfield code="w">(DE-627)614095689</subfield><subfield code="w">(DE-600)2527081-3</subfield><subfield code="x">19994907</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:10</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:11, p 1047</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/f10111047</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/86dd98b25fda49e98ba2ef3444d62133</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/1999-4907/10/11/1047</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1999-4907</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">10</subfield><subfield code="j">2019</subfield><subfield code="e">11, p 1047</subfield></datafield></record></collection>
score	7.398978

Nicht das Richtige dabei?

Schreiben Sie uns!

Deep Learning Approaches for the Mapping of Tree Species Diversity in a Tropical Wetland Using Airborne LiDAR and High-Spatial-Resolution Remote Sensing Images

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?