Phenological dataset for ecological forecasting - PheDEF - Landsat image subsets and derived vegetation indices

This dataset is part of a data collection that 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. The dataset includes Landsat satellite image subsets and derived indices.Images were downloaded using the Earth Explorer Python API. Individual bands were stacked and cropped to the study area. To calculate the vegetation indices, bands were scaled using the scaling Factor SR = (DN * 0.0000275) - 0.2 as described in the Landsat8-9, Collection2 Level2 Science Product Guide. Indices were then multiplied by 10000, and the datatype was set to int16. We acknowledge the use of imagery provided by services from NASA's Global Imagery Browse Services (GIBS), part of NASA's Earth Science Data and Information System (ESDIS).

本数据集隶属于一项整合多源物候与气候数据的综合数据项目，该项目涵盖湿润半落叶林与干旱半落叶林两类热带森林生态系统，可应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任务。数据集包含Landsat卫星影像子集（Landsat satellite image subsets）及其衍生指数。影像通过Earth Explorer Python应用程序接口（Earth Explorer Python API）下载，对各波段进行拼接并裁剪至研究区范围。为计算植被指数，依据《Landsat 8-9 Collection 2 Level 2科学产品指南》中的说明，采用缩放系数SR = (DN × 0.0000275) - 0.2对波段进行归一化缩放处理。随后将所得指数乘以10000，并将数据类型设置为int16。本研究感谢使用美国国家航空航天局（National Aeronautics and Space Administration，NASA）地球科学数据与信息系统（Earth Science Data and Information System，ESDIS）下属的全球影像浏览服务（Global Imagery Browse Services，GIBS）所提供的影像数据。