2020
DOI: 10.1038/s41598-020-67024-3
|View full text |Cite
|
Sign up to set email alerts
|

Forest aboveground biomass estimation using Landsat 8 and Sentinel-1A data with machine learning algorithms

Abstract: Forest aboveground biomass (AGB) plays an important role in the study of the carbon cycle and climate change in the global terrestrial ecosystem. AGB estimation based on remote sensing is an effective method for regional scale. In this study, Landsat 8 Operational Land Imager and Sentinel-1A data and China’s National Forest Continuous Inventory data in combination with three algorithms, either the linear regression (LR), random forest (RF), or the extreme gradient boosting (XGBoost), were used to estimate biom… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

10
169
0
2

Year Published

2020
2020
2024
2024

Publication Types

Select...
10

Relationship

1
9

Authors

Journals

citations
Cited by 227 publications
(181 citation statements)
references
References 46 publications
10
169
0
2
Order By: Relevance
“…Among the eight regression algorithms, the RF and SVR models have often been used for forest AGB estimation, and their good performances have been demonstrated in published studies [7,24,[107][108][109][110]. In this study, some recently developed algorithms and even some algorithms yet to be established for AGB prediction (e.g., the CatBoost and ERT algorithms), were evaluated.…”
Section: Discussionmentioning
confidence: 99%
“…Among the eight regression algorithms, the RF and SVR models have often been used for forest AGB estimation, and their good performances have been demonstrated in published studies [7,24,[107][108][109][110]. In this study, some recently developed algorithms and even some algorithms yet to be established for AGB prediction (e.g., the CatBoost and ERT algorithms), were evaluated.…”
Section: Discussionmentioning
confidence: 99%
“…To evaluate the biomarkers that have the most influence on the outcome, XGBoost was used to get the relative importances. XGBoost is a powerful machine learning algorithm that estimates features that are the most discriminative of model outcomes ( 33 ). The final importance of a feature is calculated using the mean of its importances across all the trees.…”
Section: Methodsmentioning
confidence: 99%
“…However, the "black box" operation of nonparametric models expresses their complex process through the fitting of a training dataset; thus, the unclear physical mechanisms could lower the interpretability of such models, even though the models could improve the accuracy of AGB estimation [23]. Li et al used Landsat 8 Operational Land Imager (OLI) and Sentinel-1A C-band Synthetic Aperture Radar (SAR) data in combination with three machine learning (ML) algorithms to estimate biomass in subtropical forests in Hunan Province, China [24]; Santi et al used airborne P-band SAR data to estimate forest biomass with ML algorithms [25]; and Yang et al used Global Land Surface Satellite and LiDAR data with ML algorithms to generate a global forest biomass map [26]. These studies proved the potential of ML algorithms in estimating forest biomass from multiple remote sensing data sources.…”
Section: Introductionmentioning
confidence: 99%