FireCCI_Africa_2019_S2: reference fire perimeters obtained from Sentinel-2 imagery over Africa continental for the year 2019

The FireCCI_Africa_2019_S2 reference dataset was derived from S2 images over a set of 50 tiles (sampling units) sampled following a design customized for the Sentinel tiling grid system and to represent major fire regimes of the African continent in the different ecoregions. Over each tile S2 time series were defined based on a set of conditions for minimizing cloud cover and to guarantee series length and a minimum time lag between image pairs. S2 image pairs were classified with a Random Forest (RF) algorithm to provide burned perimeters of depicting areas that burned between the two dates that were combined in a synthetic burned area reference dataset. This dataset represent for each unit burned and unburned polygons and masked areas. A detailed description of the dataset can be found in Stroppiana et al.(2022) ("Sampling design and reference fire perimeters over Africa for the year 2019 from Sentinel-2 for validation of Earth Observation burned area products", in preparation). The FireCCI_Africa_2019_S2 dataset is part of the Burned Area Reference Database (BARD), a database that compiles multitemporal global and regional burned area reference datasets for Earth Observation burned area products validation.

FireCCI_Africa_2019_S2参考数据集源自50个瓦片（采样单元）上的Sentinel-2图像，这些瓦片按照为Sentinel瓦片网格系统量身定制的设计进行采样，旨在表征非洲大陆不同生态区域的主要火灾格局。在每个瓦片上，基于最小化云覆盖和确保时间序列长度以及图像对之间最小时间延迟的条件，定义了S2时间序列。利用随机森林（RF）算法对S2图像对进行分类，以提供表示两个日期之间燃烧区域的燃烧周长，这些日期被组合成合成的燃烧区域参考数据集。该数据集为每个燃烧单元和未燃烧多边形以及掩码区域提供了表征。关于该数据集的详细描述可参考Stroppiana等（2022年）的论文（《2019年非洲Sentinel-2的采样设计和参考火灾周长，用于验证地球观测燃烧面积产品》，待发表）。
FireCCI_Africa_2019_S2数据集是燃烧面积参考数据库（BARD）的一部分，该数据库汇集了多时相全球和区域燃烧面积参考数据集，用于验证地球观测燃烧面积产品。