Phenological dataset for ecological forecasting - PheDEF - Sentinel-2 image and vegetation indices subsets

This dataset combines phenology and climate data from multiple sources in two tropical forest ecosystems, a moist semi-deciduous and a dry semi-deciduous forest, that can be used for machine learning applications in climate, forests, and biodiversity conservation at community and landscape scales. This dataset includes Sentinel-2 image subsets (Sentinel-2 Level 2A Surface Reflectance) and vegetation indices extracted from them.<br>Images were downloaded using the OpenEO Python API of Copernicus Data Space Ecosystem (https://dataspace.copernicus.eu/). To calculate vegetation indices, bands were scaled using the scaling Factor SR = (DN /10000) in the product documentation available at https://docs.sentinel-hub.com/api/latest/data/sentinel-2-l2a/. Indices were then multiplied by 10000, and the datatype was set to int16.<br>

本数据集整合了两个热带森林生态系统（湿润半落叶林与干燥半落叶林）的多源物候与气候数据，可用于社区及景观尺度下气候、森林与生物多样性保护领域的机器学习应用。本数据集包含哨兵二号（Sentinel-2）Level 2A地表反射率影像子集，以及从中提取的植被指数。
影像通过哥白尼数据空间生态系统（Copernicus Data Space Ecosystem）的OpenEO Python API下载，下载来源网址为https://dataspace.copernicus.eu/。
为计算植被指数，需按照Sentinel Hub官方文档（https://docs.sentinel-hub.com/api/latest/data/sentinel-2-l2a/）中的说明，使用缩放因子SR = (DN /10000)对波段进行缩放；随后将指数结果乘以10000，并将数据类型设置为int16。