1. Methods presented allow mapping of AGB at 30 m pixel resolution.
2. Models tested have little signs of saturation up to 400 Mg AGB ha−1.
3. Combination of Lidar-derived biomass estimates, Landsat time series, and machine learning algorithms can be used to map biomass in the Amazon basin.
The article is generally reliable and trustworthy, as it provides a detailed overview of the methods used to map aboveground biomass (AGB) in the Amazon basin using Landsat time series data and machine learning algorithms. The authors provide evidence for their claims by citing previous studies that have used similar methods to map AGB density over large areas with high biomass ranges, and demonstrate that their models are able to accurately estimate AGB with a root-mean-square error (RMSE) ranging from 64 to 92 Mg AGB ha−1. The article also mentions potential limitations of the models tested, such as saturation below 400 Mg AGB ha−1, which suggests that there is ample room for improvement in order to achieve more accurate results.
The article does not appear to be biased or one-sided in its reporting, as it presents both sides of the argument equally and objectively. It also does not contain any promotional content or partiality towards any particular method or approach. Furthermore, the authors acknowledge potential risks associated with their methods and note that further research is needed in order to improve accuracy and reduce errors in AGB estimation.
In conclusion, this article is reliable and trustworthy due to its objective reporting style and lack of bias or promotional content. However, further research is needed in order to improve accuracy and reduce errors in AGB estimation.