High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms
Accurately estimating the above-ground biomass (AGB) of high-density tropical rainforests is a challenging issue. In this study, airborne multi-baseline PolInSAR data were used to estimate the tropical rainforest AGB in Gabon, Africa. The most suitable baseline combination of the PolInSAR data was i...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-03-01
|
Series: | Ecological Indicators |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X24003352 |
_version_ | 1797213437936271360 |
---|---|
author | Hongbin Luo Sitong Qin Jing Li Chi Lu Cairong Yue Guanglong Ou |
author_facet | Hongbin Luo Sitong Qin Jing Li Chi Lu Cairong Yue Guanglong Ou |
author_sort | Hongbin Luo |
collection | DOAJ |
description | Accurately estimating the above-ground biomass (AGB) of high-density tropical rainforests is a challenging issue. In this study, airborne multi-baseline PolInSAR data were used to estimate the tropical rainforest AGB in Gabon, Africa. The most suitable baseline combination of the PolInSAR data was initially determined through baseline selection, and the PolInSAR parameters related to forest height were obtained based on the forest canopy height estimation theory and microwave penetration depth theory. The height parameter, baseline parameter, and observation geometry parameter were then used as independent variables to construct the AGB regression model. Support vector regression (SVR) was chosen as the AGB estimation model, and the global best particle swarm algorithm (GLB-PSO) was used to optimize the SVR model’s parameters. The results show that the RFECV variable selection method is superior to the Pearson method. The GLB-PSO algorithm can also further improve the saturation point of the SVR model—the estimation results show that the saturation point of AGB estimation of PolInSAR multidimensional features combined with the SVR machine learning algorithm is up to 500 Mg/ha, while this saturation point can be increased to 650 Mg/ha when using the GLB-PSO-SVR algorithm. |
first_indexed | 2024-04-24T10:58:16Z |
format | Article |
id | doaj.art-2d834c868df64680b02f9218e30f83bb |
institution | Directory Open Access Journal |
issn | 1470-160X |
language | English |
last_indexed | 2024-04-24T10:58:16Z |
publishDate | 2024-03-01 |
publisher | Elsevier |
record_format | Article |
series | Ecological Indicators |
spelling | doaj.art-2d834c868df64680b02f9218e30f83bb2024-04-12T04:44:50ZengElsevierEcological Indicators1470-160X2024-03-01160111878High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithmsHongbin Luo0Sitong Qin1Jing Li2Chi Lu3Cairong Yue4Guanglong Ou5Key Laboratory of National Forestry and Grassland Administration on Biodiversity Conservation in Southwest China, Southwest Forestry University, Kunming 650224, China; College of Forestry, Southwest Forestry University, Kunming 650224, ChinaKey Laboratory of National Forestry and Grassland Administration on Biodiversity Conservation in Southwest China, Southwest Forestry University, Kunming 650224, China; College of Forestry, Southwest Forestry University, Kunming 650224, ChinaCollege of Forestry, Southwest Forestry University, Kunming 650224, China; Key Laboratory of National Forestry and Grassland Administration on Biodiversity Conservation in Southwest China, Southwest Forestry University, Kunming 650224, ChinaKey Laboratory of National Forestry and Grassland Administration on Biodiversity Conservation in Southwest China, Southwest Forestry University, Kunming 650224, China; College of Forestry, Southwest Forestry University, Kunming 650224, ChinaCollege of Forestry, Southwest Forestry University, Kunming 650224, China; Corresponding authors at: College of Forestry, Southwest Forestry University, Kunming 650224, China.Key Laboratory of National Forestry and Grassland Administration on Biodiversity Conservation in Southwest China, Southwest Forestry University, Kunming 650224, China; College of Forestry, Southwest Forestry University, Kunming 650224, China; Corresponding authors at: College of Forestry, Southwest Forestry University, Kunming 650224, China.Accurately estimating the above-ground biomass (AGB) of high-density tropical rainforests is a challenging issue. In this study, airborne multi-baseline PolInSAR data were used to estimate the tropical rainforest AGB in Gabon, Africa. The most suitable baseline combination of the PolInSAR data was initially determined through baseline selection, and the PolInSAR parameters related to forest height were obtained based on the forest canopy height estimation theory and microwave penetration depth theory. The height parameter, baseline parameter, and observation geometry parameter were then used as independent variables to construct the AGB regression model. Support vector regression (SVR) was chosen as the AGB estimation model, and the global best particle swarm algorithm (GLB-PSO) was used to optimize the SVR model’s parameters. The results show that the RFECV variable selection method is superior to the Pearson method. The GLB-PSO algorithm can also further improve the saturation point of the SVR model—the estimation results show that the saturation point of AGB estimation of PolInSAR multidimensional features combined with the SVR machine learning algorithm is up to 500 Mg/ha, while this saturation point can be increased to 650 Mg/ha when using the GLB-PSO-SVR algorithm.http://www.sciencedirect.com/science/article/pii/S1470160X24003352AGBPolInSARMultidimensional featuresMachine learning |
spellingShingle | Hongbin Luo Sitong Qin Jing Li Chi Lu Cairong Yue Guanglong Ou High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms Ecological Indicators AGB PolInSAR Multidimensional features Machine learning |
title | High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms |
title_full | High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms |
title_fullStr | High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms |
title_full_unstemmed | High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms |
title_short | High-density forest AGB estimation in tropical forest integrated with PolInSAR multidimensional features and optimized machine learning algorithms |
title_sort | high density forest agb estimation in tropical forest integrated with polinsar multidimensional features and optimized machine learning algorithms |
topic | AGB PolInSAR Multidimensional features Machine learning |
url | http://www.sciencedirect.com/science/article/pii/S1470160X24003352 |
work_keys_str_mv | AT hongbinluo highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms AT sitongqin highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms AT jingli highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms AT chilu highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms AT cairongyue highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms AT guanglongou highdensityforestagbestimationintropicalforestintegratedwithpolinsarmultidimensionalfeaturesandoptimizedmachinelearningalgorithms |