Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification
Forest types correspond to differences in structural characteristics and species composition that influence biomass and biodiversity values, which are essential measurements for ecological monitoring and management. However, differentiating forest types in tropical regions remains a challenge. This...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/24/4776 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850239541391130624 |
|---|---|
| author | Mary M. McClure Satoshi Tsuyuki Takuya Hiroshima |
| author_facet | Mary M. McClure Satoshi Tsuyuki Takuya Hiroshima |
| author_sort | Mary M. McClure |
| collection | DOAJ |
| description | Forest types correspond to differences in structural characteristics and species composition that influence biomass and biodiversity values, which are essential measurements for ecological monitoring and management. However, differentiating forest types in tropical regions remains a challenge. This study aimed to improve forest type extent mapping by combining structural information from discrete full-waveform LiDAR returns with multitemporal images. This study was conducted in a tropical forest region over complex terrain in north-eastern Tanzania. First, structural classes were generated by applying time-series clustering algorithms. The results showed four different structural clusters corresponding to forest types, montane–humid forest, montane–dry forest, submontane forest, and non-forest, when using the Kshape algorithm. Kshape considers the shape of the full-sequence LiDAR waveform, requiring little preprocessing. Despite the overlap amongst the original clusters, the averages of structural characteristics were significantly different across all but five metrics. The labeled clusters were then further refined and used as training data to generate a wall-to-wall forest cover type map by classifying biannual images. The highest-performing model was a KNN model with 13 spectral and 3 terrain features achieving 81.7% accuracy. The patterns in the distributions of forest types provide better information from which to adapt forest management, particularly in forest–non-forest transitional zones. |
| format | Article |
| id | doaj-art-6b170532977b4b1b95137bf87bcd2b24 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-6b170532977b4b1b95137bf87bcd2b242025-08-20T02:01:09ZengMDPI AGRemote Sensing2072-42922024-12-011624477610.3390/rs16244776Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type ClassificationMary M. McClure0Satoshi Tsuyuki1Takuya Hiroshima2Independent ResearcherDepartment of Global Agricultural Sciences, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 113-8657, JapanDepartment of Global Agricultural Sciences, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 113-8657, JapanForest types correspond to differences in structural characteristics and species composition that influence biomass and biodiversity values, which are essential measurements for ecological monitoring and management. However, differentiating forest types in tropical regions remains a challenge. This study aimed to improve forest type extent mapping by combining structural information from discrete full-waveform LiDAR returns with multitemporal images. This study was conducted in a tropical forest region over complex terrain in north-eastern Tanzania. First, structural classes were generated by applying time-series clustering algorithms. The results showed four different structural clusters corresponding to forest types, montane–humid forest, montane–dry forest, submontane forest, and non-forest, when using the Kshape algorithm. Kshape considers the shape of the full-sequence LiDAR waveform, requiring little preprocessing. Despite the overlap amongst the original clusters, the averages of structural characteristics were significantly different across all but five metrics. The labeled clusters were then further refined and used as training data to generate a wall-to-wall forest cover type map by classifying biannual images. The highest-performing model was a KNN model with 13 spectral and 3 terrain features achieving 81.7% accuracy. The patterns in the distributions of forest types provide better information from which to adapt forest management, particularly in forest–non-forest transitional zones.https://www.mdpi.com/2072-4292/16/24/4776waveform LiDARforest structureclusteringtime-series |
| spellingShingle | Mary M. McClure Satoshi Tsuyuki Takuya Hiroshima Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification Remote Sensing waveform LiDAR forest structure clustering time-series |
| title | Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification |
| title_full | Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification |
| title_fullStr | Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification |
| title_full_unstemmed | Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification |
| title_short | Integration of Structural Characteristics from GEDI Waveforms for Improved Forest Type Classification |
| title_sort | integration of structural characteristics from gedi waveforms for improved forest type classification |
| topic | waveform LiDAR forest structure clustering time-series |
| url | https://www.mdpi.com/2072-4292/16/24/4776 |
| work_keys_str_mv | AT marymmcclure integrationofstructuralcharacteristicsfromgediwaveformsforimprovedforesttypeclassification AT satoshitsuyuki integrationofstructuralcharacteristicsfromgediwaveformsforimprovedforesttypeclassification AT takuyahiroshima integrationofstructuralcharacteristicsfromgediwaveformsforimprovedforesttypeclassification |