Machine Learning and Multi-source Remote Sensing in Forest Aboveground Biomass Estimation: A Review
This work provides a systematic guide for researchers and practitioners in forestry and environmental science to select optimal methods and data sources for biomass estimation, though it is incremental as a review.
This review analyzed 25 papers to identify effective combinations of machine learning methods and multi-source remote sensing for forest aboveground biomass estimation, finding that Extreme Gradient Boosting performed best in 75% of comparative studies and Sentinel-1 was the most used remote sensing source.
Quantifying forest aboveground biomass (AGB) is crucial for informing decisions and policies that will protect the planet. Machine learning (ML) and remote sensing (RS) techniques have been used to do this task more effectively, yet there lacks a systematic review on the most recent working combinations of ML methods and multiple RS sources, especially with the consideration of the forests' ecological characteristics. This study systematically analyzed 25 papers that met strict inclusion criteria from over 80 related studies, identifying all ML methods and combinations of RS data used. Random Forest had the most frequent appearance (88\% of studies), while Extreme Gradient Boosting showed superior performance in 75\% of the studies in which it was compared with other methods. Sentinel-1 emerged as the most utilized remote sensing source, with multi-sensor approaches (e.g., Sentinel-1, Sentinel-2, and LiDAR) proving especially effective. Our findings provide grounds for recommending which sensing sources, variables, and methods to consider using when integrating ML and RS for forest AGB estimation.