Verifying Practices of Regenerative Agriculture: African Smallholder Farmer Dataset for Remote Sensing and Machine Learning (Papers Track)

Yohei Nakayama (Degas Ltd); Grace Antwi (Degas Ltd); Seiko Shirasaka (Keio University)

Paper PDF Poster File Cite
Agriculture & Food Computer Vision & Remote Sensing


Despite Africa’s contribution to global greenhouse gas (GHG) emissions being only a few %, the continent experiences the harshest impacts, particularly within its food production systems. Regenerative agriculture is receiving a large amount of attention as a method to strengthen both food security and climate change resilience in Africa. For practicing regenerative agriculture, carbon credits are issued, but verifying the methodologies on a large scale is one of the challenging points in popularizing it. In this paper, we provide a comprehensive dataset on regenerative agriculture in sub-Saharan Africa. The dataset has field polygon information and is labeled with several types of regenerative agriculture methodologies. The dataset can be applied to local site analysis, classification, and detection of regenerative agriculture with remote sensing and machine learning. We also highlight several machine learning models and summarize the baseline results on our dataset. We believe that by providing this dataset, we can contribute to the establishment of verification methods for regenerative agriculture. The dataset can be downloaded from