High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data
Forests are vital carbon sinks, with tree height and biomass critical for carbon research. NASA's GEDI spaceborne LiDAR enhances vegetation monitoring through 3D structure analysis. This study established relationships between GEDI products and Sentinel-1/2, Landsat 8, ALOS, and GLO-30 features...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10924716/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850147624251817984 |
|---|---|
| author | Bo Zhang Li Zhang Min Yan Jian Zuo Yuqi Dong Bowei Chen |
| author_facet | Bo Zhang Li Zhang Min Yan Jian Zuo Yuqi Dong Bowei Chen |
| author_sort | Bo Zhang |
| collection | DOAJ |
| description | Forests are vital carbon sinks, with tree height and biomass critical for carbon research. NASA's GEDI spaceborne LiDAR enhances vegetation monitoring through 3D structure analysis. This study established relationships between GEDI products and Sentinel-1/2, Landsat 8, ALOS, and GLO-30 features using the AutoML method. We constructed a total of 432 features, primarily from 14 types of earth observation features. In a 95.56% forest-covered area, AutoML improved canopy height (FCH) and biomass (AGBD) accuracy by up to 5.25 m and 32.18 Mg/ha over other methods. Polarization interference features, especially phase, explain 20% of forest parameters, showing high stability. Wavelet and Fourier-based texture features also demonstrate strong potential. Two mapping methods are proposed: 10 m resolution (FCH <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 11.49 m; AGBD <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 133.56 Mg/ha) and 500 m resolution (FCH <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.64, RMSE = 10.06 m; AGBD <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.66, RMSE = 114.25 Mg/ha). Compared to existing maps (AGBD: <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> <inline-formula><tex-math notation="LaTeX">$<$</tex-math></inline-formula> 0.1, RMSE <inline-formula><tex-math notation="LaTeX">$>$</tex-math></inline-formula> 180 Mg/ha; FCH: <inline-formula><tex-math notation="LaTeX">$R <$</tex-math></inline-formula> 0.2, RMSE <inline-formula><tex-math notation="LaTeX">$>$</tex-math></inline-formula> 15 m), our method (AGBD <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> = 0.74, RMSE = 131.39 Mg/ha; FCH <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> = 0.73, RMSE = 11.30 m) significantly improves accuracy. The approach shows minimal saturation effects and broad applicability for forest parameter estimation. |
| format | Article |
| id | doaj-art-0ffa1fadd65747608ea78553d8742d6d |
| institution | OA Journals |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-0ffa1fadd65747608ea78553d8742d6d2025-08-20T02:27:31ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01189084911810.1109/JSTARS.2025.355087810924716High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 DataBo Zhang0https://orcid.org/0000-0002-7226-1088Li Zhang1https://orcid.org/0000-0002-5880-7507Min Yan2https://orcid.org/0000-0001-7234-1590Jian Zuo3Yuqi Dong4Bowei Chen5https://orcid.org/0000-0002-6377-1094International Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, ChinaForests are vital carbon sinks, with tree height and biomass critical for carbon research. NASA's GEDI spaceborne LiDAR enhances vegetation monitoring through 3D structure analysis. This study established relationships between GEDI products and Sentinel-1/2, Landsat 8, ALOS, and GLO-30 features using the AutoML method. We constructed a total of 432 features, primarily from 14 types of earth observation features. In a 95.56% forest-covered area, AutoML improved canopy height (FCH) and biomass (AGBD) accuracy by up to 5.25 m and 32.18 Mg/ha over other methods. Polarization interference features, especially phase, explain 20% of forest parameters, showing high stability. Wavelet and Fourier-based texture features also demonstrate strong potential. Two mapping methods are proposed: 10 m resolution (FCH <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 11.49 m; AGBD <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.53, RMSE = 133.56 Mg/ha) and 500 m resolution (FCH <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.64, RMSE = 10.06 m; AGBD <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> = 0.66, RMSE = 114.25 Mg/ha). Compared to existing maps (AGBD: <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> <inline-formula><tex-math notation="LaTeX">$<$</tex-math></inline-formula> 0.1, RMSE <inline-formula><tex-math notation="LaTeX">$>$</tex-math></inline-formula> 180 Mg/ha; FCH: <inline-formula><tex-math notation="LaTeX">$R <$</tex-math></inline-formula> 0.2, RMSE <inline-formula><tex-math notation="LaTeX">$>$</tex-math></inline-formula> 15 m), our method (AGBD <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> = 0.74, RMSE = 131.39 Mg/ha; FCH <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> = 0.73, RMSE = 11.30 m) significantly improves accuracy. The approach shows minimal saturation effects and broad applicability for forest parameter estimation.https://ieeexplore.ieee.org/document/10924716/ALOS-2 PALSAR-2forest parametersGlobal Ecosystem Dynamics Investigation (GEDI)Landsat 8Sentinel-1/2 |
| spellingShingle | Bo Zhang Li Zhang Min Yan Jian Zuo Yuqi Dong Bowei Chen High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ALOS-2 PALSAR-2 forest parameters Global Ecosystem Dynamics Investigation (GEDI) Landsat 8 Sentinel-1/2 |
| title | High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data |
| title_full | High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data |
| title_fullStr | High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data |
| title_full_unstemmed | High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data |
| title_short | High-Resolution Mapping of Forest Parameters in Tropical Rainforests Through AutoML Integration of GEDI With Sentinel-1/2, Landsat 8, and ALOS-2 Data |
| title_sort | high resolution mapping of forest parameters in tropical rainforests through automl integration of gedi with sentinel 1 2 landsat 8 and alos 2 data |
| topic | ALOS-2 PALSAR-2 forest parameters Global Ecosystem Dynamics Investigation (GEDI) Landsat 8 Sentinel-1/2 |
| url | https://ieeexplore.ieee.org/document/10924716/ |
| work_keys_str_mv | AT bozhang highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data AT lizhang highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data AT minyan highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data AT jianzuo highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data AT yuqidong highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data AT boweichen highresolutionmappingofforestparametersintropicalrainforeststhroughautomlintegrationofgediwithsentinel12landsat8andalos2data |