Search

This study addresses the challenge of estimating above-ground biomass (AGB) in the Amazon rainforest by developing a reference geographical database, which provides the ground truth, and comparing the relative importance of using Synthetic Aperture Radar (SAR) and optical remote sensing data to automatically infer AGB. In the experiments reported in this article, we assessed how those two remote sensing data sources impact the accuracy of AGB estimates produced by regression models built with Random Forest (RF) and Extreme Gradient Boosting (XGBoost). The research involved compiling a comprehensive database from many available forest inventories, integrating parcel- and tree-level data to enable precise biomass estimation. The methodology included setting up a spatial data analysis environment, standardizing data, and implementing an experimental protocol with feature selection and leave-one-out cross-validation. The results demonstrate that both kinds of data, i.e., SAR and optical, and their combination can be used for estimating AGB, providing valuable insights for forest management and climate change mitigation efforts. The reference database is available upon request to the corresponding authors.

This paper reports research that is part of a project to combat deforestation in the Brazilian Amazon rainforest by developing an online system designed to forecast deforestation risk over the short term, spanning 2 to 4 weeks. This online platform aims to empower stakeholders with timely data, facilitating proactive conservation and intervention strategies to safeguard the Amazon rainforest. We built a multitemporal database that compiles weekly deforestation alerts from the DETER project, forming our analysis’s backbone. Utilizing the XGBOOST regression algorithm, we have crafted a predictive model that identifies areas within the Amazon at imminent risk of more intensive deforestation. Preliminary results reveal an RMSE of 0.29 for predicting areas under deforestation risk, as validated against early alert data from 2020 to 2023. Our work advances environmental monitoring by focusing on a spatial resolution of 25 km × 25 km, providing accessible, near real-time information on deforestation risks.