Christine Muthee
AI mapping of smallholder crop data – Scientific Data Research Highlight (2025).
doi: https://doi.org/10.1038/d44148-025-00280-5
Asamoah Oppong, Z. (2022). AI‑Driven Crop Yield Prediction Models for Smallholder Farmers in Sub‑Saharan Africa. Iconic Research and Engineering Journals, Volume 5 Issue 9.
Becker‑Reshef, I., et al. (2023). Strengthening food security monitoring through satellite‑based crop type and yield estimation. Remote Sensing Environment, 292, 113577.
Geyman et al. (2025). An Africa‑wide agricultural production database to support policy and satellite‑based measurement systems. Scientific Data (Nature).
Gokool, S., Mahomed, M., Brewer, K., Naiken, V., Clulowa, A., Sibanda, M., Mabhaudhi, T. (2024). Crop mapping in smallholder farms using unmanned aerial vehicle imagery and geospatial cloud computing infrastructure. Heliyon, 10 (2024) e26913.
Guo, Z. (2024). From Space to Soil: Advancing Crop Mapping and Ecosystem Insights for Smallholder Agriculture.
Jayne, T.S., Muyanga, M., Wineman, A., et al. (2019). Are medium-scale farms driving agricultural transformation in sub-Saharan Africa? Agricultural Economics, 50:75–95.
https://doi.org/10.1111/agec.12535
Kerner, H., Chaudhari, S., Ghosh, A., Robinson, C., Ahmad, A., Choi, E., Jacobs, N. et al. (2024). Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation. arXiv preprint arXiv:2409.16252.
Lida, K., Rahim, S., Hutber, C., Grau, G., Moss, C., & Douglas, O. (2026). Government AI Readiness Index 2025. Oxford Insights.
Musoni, M., & Adeniyi, D. (2025). How AI can benefit smallholder farmers in Africa: Opportunities for EU‑Africa. ECDPM Discussion Paper No. 396.
Nakalembe, C., et al. (2025). Challenges and opportunities for crop type mapping in smallholder systems of sub‑Saharan Africa. Remote Sensing, 17(2), 412.
Omotoso, A.B., & Omotayo, A.O. (2024). The interplay between agriculture, greenhouse gases, and climate change in Sub-Saharan Africa. Regional Environmental Change, 24, 1 (2024).
https://doi.org/10.1007/s10113-023-02159-3
Potapov, P., Turubanova, S., Hansen, M.C. et al. (2022). Global maps of cropland extent and change show accelerated cropland expansion in the twenty‑first century. Nature Food 3, 19–28 (2022).
https://doi.org/10.1038/s43016-021-00429-z
Rahman, A.N., Kotu, B.H., Tetteh, F.M., Karikari, B., Akinseye, F.M., Ansah, T., Mutungi, C., & Kizito, F. (2024). Editorial: Sustainable intensification of smallholder farming systems in Sub‑Saharan Africa and South Asia. Frontiers in Sustainable Food Systems, 8:1399430.
doi: 10.3389/fsufs.2024.1399430
United Nations Department of Economic and Social Affairs. (2024). World population projections.
UNFCCC (2025, November 15). Ethiopia: Press Briefing on hosting COP 32 in Ethiopia. Belém, Brazil.
Wang, S., Waldner, F., & Lobell, D.B. (2022). Unlocking Large-Scale Crop Field Delineation in Smallholder Farming Systems with Transfer Learning and Weak Supervision. Remote Sensing 14 (22): 5738. doi:10.3390/rs14225738.
WRI Africa (2026). AI Mapping for Small-Scale Farm Transformation.
https://africa.wri.org/initiatives/ai-mapping-small-scale-farm-transformation
Sessions
Accurate crop field boundary delineation is foundational for agricultural mapping, yield estimation, and decision support systems. Yet existing AI models, trained predominantly on data from the Global North, perform poorly in underrepresented farming systems such as those in Sub-Saharan Africa (typically under 2 hectares, irregularly shaped) and South America (characterized by shifting cultivation and complex morphologies). This data gap misleads agricultural statistics, weak policies, and inefficient resource allocation.
We leveraged AI and open-source remote sensing data to automatically delineate field boundaries in both regions using transfer learning, adapting pretrained global models to local contexts. In South America, we annotated over 46,000 field boundaries for model training and generated more than 10 million boundaries continent-wide. In East Africa's Great Rift Valley, we automatically detected over 400,000 farms from just 6,000 samples, incorporating multi-stakeholder annotation workflows and quality assurance pipelines refined from lessons learned in South America.
Our results show that models trained on limited but high-quality local annotations scale effectively to out-of-sample regions. In Africa, delineated fields have enabled field level crop type and yield data collection, in preparation for field level crop type mapping, yield estimation and monitoring of agroecological and regenerative agriculture practices. In South America, they have supported supply chain auditing for deforestation-free commitments, EUDR compliance, country-level crop forecasting, and scope 3 emissions estimation. Across both regions, the approach has strengthened national and subnational agricultural data systems and climate resilience frameworks.
By demonstrating AI model transferability across contrasting geographies, this work charts a pathway toward open, inclusive, and scalable Earth observation systems that close critical data gaps in the Global South, positioning AI as a core enabler of sustainable agricultural monitoring at national and subnational scales.