Reference Dataset for Land Use Change Mapping in Ghana's Cocoa Landscape (2024–2025)

This dataset was produced by the Centre for Remote Sensing and Geographic Information Services (CERSGIS) as part of the project Reference Data Collection for Improving Land Use Change Mapping in Ghana. The primary objective was to develop high-quality reference data to enhance the accuracy of remote sensing-based land use and land cover (LULC) change mapping using machine learning methods in Ghana’s cocoa production landscapes.The dataset comprises: cocoa_farms: 21,031 geocoded cocoa farm polygons, including agroforestry and shadeless cocoa plots - collected using OpenForis Ground homogeneous_cocoa_farm: 14,192 homogeneous cocoa polygons (shadeless) digitised from total cocoa plots other_land_uses: 20,035 additional geocoded points and polygons representing informal gold mining, degraded forest, oil palm (commercial and subsistence), and rubber (commercial and subsistence) - collected with Collect Earth Online gha_cocoa_hh_public: 485 anonymised cluster records derived from 4,444 individual household survey that complement the geospatial data and provide socioeconomic context - collected with KoboToolbox This dataset provides a critical foundation for automated land cover classification and change detection models in tropical forested regions, where land use is heterogeneous and dynamic. It was developed to support researchers, policymakers, and practitioners across sub-Saharan Africa engaged in monitoring commodity-driven deforestation, landscape restoration, and sustainable land management.This dataset was originally created with support from Lacuna Fund, the world’s first collaborative effort to provide data scientists, researchers, and social entrepreneurs in low- and middle-income contexts globally with the resources they need to produce labelled datasets that address urgent problems in their communities. Lacuna Fund is a funder collaborative that includes The Rockefeller Foundation, Google.org, Canada’s International Development Research Centre, the German Federal Ministry for Economic Cooperation and Development (BMZ) with GIZ as implementing agency, Wellcome Trust, Gordon and Betty Moore Foundation, Patrick J. McGovern Foundation, and The Robert Wood Johnson Foundation. See https://lacunafund.org/about/ for more information. Please contact [e-mail] with any questions or report an issue on Github here. Let us know how you plan to use the dataset. We are very interested in potential collaborations. NOTE: The cocoa farm geospatial data does not represent property or farm boundaries and should not be used for compliance / legal purposes. This data was collected for the purposes of training remote sensing models for improved mapping of cocoa and other land covers, and not for geolocating specific farms for the purposes of compliance with any regulation. Field data collectors did not trace property boundaries in the field, and field data was checked for quality and potentially edited in GIS. Therefore, these polygons represent only portions of cocoa farms. The sizes of cocoa polygons in this dataset do not necessarily relate to the size of an entire farm for a given location Project Team: CERSGIS - Foster Mensah, Bashara Abubakari SERVIR/UAH - Jacob Abramowitz WRI - James Warburton, Ashleigh Zosel-Harper, Emma Hodoka Data Collection Team: CERSGIS, University of Ghana (Centre for Climate Change and Sustainability Studies, Department of Geography and Resource Development), YouthMappers (University of Ghana Chapter, University of Cape Coast Chapter).本数据集由遥感与地理信息服务中心（Centre for Remote Sensing and Geographic Information Services, CERSGIS）为“加纳土地利用变化制图改进参考数据采集”项目编制。其核心目标是构建高质量参考数据，以提升加纳可可种植区基于遥感技术、结合机器学习方法开展的土地利用与土地覆盖（Land Use and Land Cover, LULC）变化制图精度。 本数据集包含以下内容： 1. cocoa_farms：21031个带地理编码的可可农场多边形，涵盖农林复合种植及无遮荫可可种植地块，通过OpenForis Ground工具采集。 2. homogeneous_cocoa_farm：14192个从全部可可地块中数字化得到的均质无遮荫可可种植多边形。 3. other_land_uses：20035个额外的带地理编码的点与多边形，涵盖非正式金矿开采、退化森林、商业与自给式油棕种植、商业与自给式橡胶种植等其他土地利用类型，通过Collect Earth Online工具采集。 4. gha_cocoa_hh_public：485条匿名集群记录，源自4444份个人家庭调查数据，用于补充地理空间数据并提供社会经济背景信息，通过KoboToolbox工具采集。 本数据集为热带森林地区的自动化土地覆盖分类与变化检测模型提供了关键基础——这类区域的土地利用往往具有异质性与动态性。本数据集旨在支持撒哈拉以南非洲地区从事商品驱动型森林砍伐监测、景观修复与可持续土地管理的研究人员、政策制定者与从业者开展相关工作。 本数据集最初由拉克纳基金（Lacuna Fund）支持开发。拉克纳基金是全球首个协作型资助项目，旨在为全球低收入和中等收入地区的数据科学家、研究人员与社会创业者提供所需资源，以构建能够解决当地紧迫问题的标注数据集。该基金由洛克菲勒基金会（The Rockefeller Foundation）、Google.org、加拿大国际发展研究中心（Canada’s International Development Research Centre）、德国联邦经济合作与发展部（German Federal Ministry for Economic Cooperation and Development, BMZ），由德国国际合作机构（Deutsche Gesellschaft für Internationale Zusammenarbeit, GIZ）作为执行机构、惠康基金会（Wellcome Trust）、戈登与贝蒂·摩尔基金会（Gordon and Betty Moore Foundation）、帕特里克·J·麦戈文基金会（Patrick J. McGovern Foundation）以及罗伯特·伍德·约翰逊基金会（The Robert Wood Johnson Foundation）联合发起。更多信息可访问https://lacunafund.org/about/。 如有任何疑问，请发送邮件至[e-mail]，或在此处的Github页面提交问题反馈。请告知我们您计划如何使用本数据集，我们非常期待开展潜在合作。 【注意事项】本数据集包含的可可农场地理空间数据不代表产权或农场边界，不得用于合规或法律用途。本数据采集的目的是训练遥感模型以提升可可及其他土地覆盖类型的制图精度，而非用于定位特定农场以满足任何监管合规需求。野外数据采集人员未在实地追踪产权边界，且野外数据已在地理信息系统（GIS）中完成质量检查与必要编辑。因此，本数据集内的多边形仅代表可可农场的部分区域，数据中的可可种植多边形面积并不必然对应某一地点完整农场的面积。 项目团队： CERSGIS——福斯特·门萨（Foster Mensah）、巴沙拉·阿布巴卡里（Bashara Abubakari） SERVIR/UAH——雅各布·阿布拉莫维茨（Jacob Abramowitz） 世界资源研究所（World Resources Institute, WRI）——詹姆斯·沃伯顿（James Warburton）、阿什利·佐泽尔-哈珀（Ashleigh Zosel-Harper）、艾玛·霍多卡（Emma Hodoka） 数据采集团队： 加纳大学遥感与地理信息服务中心、加纳大学（气候变化与可持续发展研究中心、地理与资源发展系）、青年制图者（YouthMappers，加纳大学分会、海岸角大学分会）