Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory
Biochemicals, such as chlorophyll (Chl) and nitrogen (N), are closely related to photosynthesis process of vegetation. Their accurate estimation is an important topic in remote sensing of vegetation. Previous studies mainly focused on Chl-N content inversion in leaf and canopy level, and few cared a...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9534709/ |
| _version_ | 1818693777017012224 |
|---|---|
| author | Lin Du Zhili Jin Bowen Chen Biwu Chen Wei Gao Jian Yang Shuo Shi Shalei Song Mengmeng Wang Wei Gong Wei Wang |
| author_facet | Lin Du Zhili Jin Bowen Chen Biwu Chen Wei Gao Jian Yang Shuo Shi Shalei Song Mengmeng Wang Wei Gong Wei Wang |
| author_sort | Lin Du |
| collection | DOAJ |
| description | Biochemicals, such as chlorophyll (Chl) and nitrogen (N), are closely related to photosynthesis process of vegetation. Their accurate estimation is an important topic in remote sensing of vegetation. Previous studies mainly focused on Chl-N content inversion in leaf and canopy level, and few cared about their 3-D distributions, which was also an important indicator for the growth status of vegetation (GSV). Hyperspectral LiDAR (HSL) is a novel active remote sensing technology, which has target-sensitive band with hyperspectra resolution. Its 3-D point cloud data simultaneously contains rich spectral and precise geometrical characteristics of the target. This work aims to apply HSL data on 3-D Chl-N content mapping in vegetation through constructing HSL-based spectral indices (SIs). Except for following the SI forms of previous works, the normalized differential vegetation index and ratio index (RI) with four broadbands in an HSL spectral space were successively proposed to invert Chl-N content for the whole vegetation based on the artificial neural network (ANN) method. These four broadbands were transformed based on the relative spectral response curve of detector and the feature weights (FWs) of multiwavelength, respectively. Results show that most HSL-based ANN models can accurately invert Chl-N content with a mean <italic>R<sup>2</sup></italic> of >0.75, and some that fusing broadband data with convolution transformation, namely the FW-based RI, can even obtain a model <italic>R<sup>2</sup></italic> of 0.84 for N content inversion. Thus, HSL can be efficiently applied to 3-D Chl-N content mapping of vegetation and has great potential in GSV monitoring. |
| first_indexed | 2024-12-17T13:19:04Z |
| format | Article |
| id | doaj.art-7b9ce16a7e194735a0cce70cb0468c5f |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-17T13:19:04Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-7b9ce16a7e194735a0cce70cb0468c5f2022-12-21T21:46:55ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01149667967910.1109/JSTARS.2021.31112959534709Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in LaboratoryLin Du0https://orcid.org/0000-0002-4789-6073Zhili Jin1Bowen Chen2Biwu Chen3https://orcid.org/0000-0001-6361-3005Wei Gao4https://orcid.org/0000-0001-7814-3712Jian Yang5Shuo Shi6https://orcid.org/0000-0003-0008-3443Shalei Song7https://orcid.org/0000-0003-1256-2097Mengmeng Wang8https://orcid.org/0000-0001-5379-5773Wei Gong9https://orcid.org/0000-0002-2276-8024Wei Wang10https://orcid.org/0000-0001-7930-9147Artificial Intelligence School, Wuchang University of Technology, Wuhan, ChinaSchool of Geoscience and Info-Physics, Central South University, Changsha, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaState Key Laboratory of Magnetic Resonance and Atomic and Molecular Physics, Wuhan Institute of Physics and Mathematics, Chinese Academy of Sciences, Wuhan, ChinaArtificial Intelligence School, Wuchang University of Technology, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Geoscience and Info-Physics, Central South University, Changsha, ChinaBiochemicals, such as chlorophyll (Chl) and nitrogen (N), are closely related to photosynthesis process of vegetation. Their accurate estimation is an important topic in remote sensing of vegetation. Previous studies mainly focused on Chl-N content inversion in leaf and canopy level, and few cared about their 3-D distributions, which was also an important indicator for the growth status of vegetation (GSV). Hyperspectral LiDAR (HSL) is a novel active remote sensing technology, which has target-sensitive band with hyperspectra resolution. Its 3-D point cloud data simultaneously contains rich spectral and precise geometrical characteristics of the target. This work aims to apply HSL data on 3-D Chl-N content mapping in vegetation through constructing HSL-based spectral indices (SIs). Except for following the SI forms of previous works, the normalized differential vegetation index and ratio index (RI) with four broadbands in an HSL spectral space were successively proposed to invert Chl-N content for the whole vegetation based on the artificial neural network (ANN) method. These four broadbands were transformed based on the relative spectral response curve of detector and the feature weights (FWs) of multiwavelength, respectively. Results show that most HSL-based ANN models can accurately invert Chl-N content with a mean <italic>R<sup>2</sup></italic> of >0.75, and some that fusing broadband data with convolution transformation, namely the FW-based RI, can even obtain a model <italic>R<sup>2</sup></italic> of 0.84 for N content inversion. Thus, HSL can be efficiently applied to 3-D Chl-N content mapping of vegetation and has great potential in GSV monitoring.https://ieeexplore.ieee.org/document/9534709/Artificial neural network (ANN)broadband spectral indexChl-N content mappinghyperspectral LiDAR (HSL) |
| spellingShingle | Lin Du Zhili Jin Bowen Chen Biwu Chen Wei Gao Jian Yang Shuo Shi Shalei Song Mengmeng Wang Wei Gong Wei Wang Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Artificial neural network (ANN) broadband spectral index Chl-N content mapping hyperspectral LiDAR (HSL) |
| title | Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory |
| title_full | Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory |
| title_fullStr | Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory |
| title_full_unstemmed | Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory |
| title_short | Application of Hyperspectral LiDAR on 3-D Chlorophyll-Nitrogen Mapping of Rohdea Japonica in Laboratory |
| title_sort | application of hyperspectral lidar on 3 d chlorophyll nitrogen mapping of rohdea japonica in laboratory |
| topic | Artificial neural network (ANN) broadband spectral index Chl-N content mapping hyperspectral LiDAR (HSL) |
| url | https://ieeexplore.ieee.org/document/9534709/ |
| work_keys_str_mv | AT lindu applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT zhilijin applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT bowenchen applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT biwuchen applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT weigao applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT jianyang applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT shuoshi applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT shaleisong applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT mengmengwang applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT weigong applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory AT weiwang applicationofhyperspectrallidaron3dchlorophyllnitrogenmappingofrohdeajaponicainlaboratory |