GROW-Africa (Groundtruthing Remote-sensing for Optimizing Yield in Africa) Database, v1.0

The GROW-Africa (Groundtruthing Remote-sensing for Optimizing Yield in Africa) Database includes n = 535,844 georeferenced observations of crop yields across Africa for the period 1960-2023. The vast majority of the observations span the period 2000-2023. The database includes 25 key crops, including maize, sorghum, cassava, groundnuts, cowpeas, rice, yams, and millet. The database assimilates observations from a range of spatial scales, from regional government statistics, to household farmer surveys, to plot-level crop cuts. The GROW-Africa database is intended to provide a platform for performing data-driven analyses of historical yield trends, as well as for training algorithms to quantify crop yields from Earth Observation (satellite) data. The database is described in the publication: Geyman, E.C., Ferris, A., Sahajpal, R., Anderson, W., Lee, D. and Hausmann, N., 2025. An Africa-wide agricultural production database to support policy and satellite-based measurement systems. Scientific Data, 12(1), p.1087. https://www.nature.com/articles/s41597-025-05257-5GROW-Africa（Groundtruthing Remote-sensing for Optimizing Yield in Africa，非洲遥感实地验证优化产量）数据库包含1960年至2023年期间非洲全境共计535,844条带地理坐标的作物产量观测数据，其中绝大多数观测数据的时间跨度为2000年至2023年。该数据库涵盖玉米、高粱、木薯、花生、豇豆、水稻、薯蓣、小米等25种主要作物。数据库整合了多空间尺度的观测资料，涵盖区域政府统计数据、农户家庭调查数据以及地块级作物收割实测数据。GROW-Africa数据库旨在搭建平台，用于开展作物产量历史趋势的数据驱动分析，同时可用于训练基于地球观测（Earth Observation，卫星）数据量化作物产量的算法模型。 该数据库的相关研究成果发表于以下学术文献： Geyman, E.C.、Ferris, A.、Sahajpal, R.、Anderson, W.、Lee, D. 与 Hausmann, N., 2025. 《泛非洲农业生产数据库：支撑政策制定与卫星遥感测量系统》。《科学数据（Scientific Data）》，第12卷第1期，第1087页。 论文链接：https://www.nature.com/articles/s41597-025-05257-5