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 biomass of the subtropical forests in Hunan Province, China. XGBoost is a scalable tree boosting system that is widely used by data scientists and provides state-of-the-art results for many problems. It can process an entire dataset with billions of examples using a minimal amount of computational resources through the particular way of cache access patterns, data compression, and data fragmentation. The results include: (1) The combination of Landsat 8 and Sentinel-1A images as predictor variables in the XGBoost model provided the best AGB estimation. (2) In contrast to the LR method, the F-test results indicated that a significant improvement in AGB estimation was achieved with the RF and XGBoost algorithms. (3) The effect of parameter optimization was found to be more significant on XGBoost than on RF. (4) The XGBoost model is an effective method for AGB estimation and can reduce the problems of overestimation and underestimation. This research provides a new way of estimating AGB for the subtropical forest based on remote sensing through the synergy of different sensors datasets and modeling algorithms.

An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products

“…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.…”

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

“…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.…”

Combining Kriging Interpolation to Improve the Accuracy of Forest Aboveground Biomass Estimation Using Remote Sensing Data

“…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.…”