资源环境科技发展态势分析平台

Countries are required to generate baselines of carbon emissions, or Forest Reference Emission Levels, for implementing REDD+ under the United Nations Framework Convention on Climate Change and to access results-based payments. Developing these baselines requires accurate maps of carbon stocks and historical deforestation. Global remote sensing products provide low-cost solutions for this information, but there has been little validation of these products at national scales. This study compares the ability of currently available products obtained from remote sensing data to deliver estimates of deforestation and associated carbon emissions in Guinea-Bissau, a West African country encompassing the climate and vegetation gradients that are typical of sub-Saharan Africa. We show that disagreements in estimates of deforestation are striking, and this variation leads to high uncertainty in derived emissions. For Guinea-Bissau, we suggest that higher temporal resolution of remote sensing products is required to reduce this uncertainty by overcoming current limitations in differentiating deforestation from seasonality. In contrast, existing datasets of carbon stocks show better agreement, and contribute much less to the variation in estimated emissions. We conclude that using global datasets based on Earth Observation data is a cost-effective solution to make REDD+ operational, but deforestation maps in particular should be derived carefully and their uncertainty assessed.