AI-Driven Crop Yield Prediction Models for Smallholder Farmers in Sub-Saharan Africa

References

[1] Burke, M., & Lobell, D. B. (2017). Satellite-based assessment of yield variation and its determinants in smallholder African systems. Proceedings of the National Academy of Sciences of the United States of America, 114(9), 2189–2194. https://doi.org/10.1073/pnas.1616919114

[2] Carletto, C., Gourlay, S., & Winters, P. (2015). From guesstimates to GPStimates: Land area measurement and implications for agricultural analysis. Journal of African Economies, 24(5), 593–628. https://doi.org/10.1093/jae/ejv011

[3] Challinor, A. J., Watson, J., Lobell, D. B., Howden, S. M., Smith, D. R., & Chhetri, N. (2018). A meta-analysis of crop yield under climate change and adaptation. Nature Climate Change, 8(7), 628–635. https://doi.org/10.1038/s41558-018-0208-x

[4] Dinku, T., Cousin, R., Ceccato, P., Connor, S. J., & Thomson, M. C. (2018). Validation of satellite rainfall products over East Africa’s complex topography. International Journal of Remote Sensing, 39(13), 4140–4168. https://doi.org/10.1080/01431161.2018.1430399

[5] Food and Agriculture Organization of the United Nations. (2020). FAOSTAT statistical database. https://www.fao.org/faostat

[6] Gourlay, S., Kilic, T., & Lobell, D. B. (2019). Could the debate be over? Errors in farmer-reported production and their implications for the inverse scale–productivity relationship in Uganda. Journal of Development Economics, 141, 102376. https://doi.org/10.1016/j.jdeveco.2019.102376

[7] Intergovernmental Panel on Climate Change. (2021). Climate change 2021: The physical science basis. Cambridge University Press. https://www.ipcc.ch/report/ar6/wg1/

[8] Jin, Z., Azzari, G., Burke, M., Aston, S., & Lobell, D. B. (2021). Mapping smallholder yield heterogeneity at scale in Eastern Africa. Remote Sensing of Environment, 253, 112170. https://doi.org/10.1016/j.rse.2020.112170

[9] Lobell, D. B., & Burke, M. (2018). Environmental impacts on crop yield. In D. B. Lobell & M. Burke (Eds.), Climate change and food security (pp. 31–54). Springer. https://doi.org/10.1007/978-94-024-1442-5_2

[10] Lobell, D. B., Azzari, G., Marshall, B., Gourlay, S., Jin, Z., Kilic, T., & Murray, S. (2019). Eyes in the sky, boots on the ground: Assessing satellite- and ground-based approaches to crop yield measurement. Remote Sensing of Environment, 216, 582–595. https://doi.org/10.1016/j.rse.2018.07.010

[11] Roudier, P., Muller, B., D’Aquino, P., Roncoli, C., Soumaré, M. A., Batté, L., & Sultan, B. (2021). The role of climate forecasts in smallholder agriculture: Lessons from West Africa. Climate Services, 22, 100232. https://doi.org/10.1016/j.cliser.2021.100232

[12] Sultan, B., Defrance, D., & Iizumi, T. (2019). Evidence of crop production losses in West Africa due to historical global warming. Science Advances, 5(2), eaav0537. https://doi.org/10.1126/sciadv.aav0537

[13] You, J., Li, X., Low, M., Lobell, D., & Ermon, S. (2020). Deep Gaussian process for crop yield prediction based on remote sensing data. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01), 455–462. https://doi.org/10.1609/aaai.v34i01.5407

@article{1713512,
      author = {Asamoah Oppong Zadok},
      title = {AI-Driven Crop Yield Prediction Models for Smallholder Farmers in Sub-Saharan Africa},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {5},
      number = {9},
      pages = {789-803},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1713512.pdf},
      abstract = {The increasing exposure of smallholder farming systems in Sub-Saharan Africa to climate variability has intensified the need for reliable crop yield prediction methods that can support agricultural planning and food security interventions. Conventional yield estimation approaches based on surveys, statistical aggregation, and process-based models have shown limited capacity to capture non-linear crop?climate interactions and localized yield variability, particularly in data-constrained environments. Recent advances in artificial intelligence and machine learning have introduced new opportunities for modeling complex relationships between climate conditions, environmental factors, and crop performance.
The review examines how machine learning models incorporate climate variability, the data sources they rely on, the spatial scales at which predictions are generated, and the extent to which these models align with smallholder decision-making contexts. Through comparative analysis, the review evaluates model performance, validation practices, data dependence, and reported limitations. The findings indicate that machine learning models, particularly tree-based approaches, generally outperform traditional statistical methods in capturing non-linear yield responses to climate variability. However, their practical applicability in smallholder contexts remains constrained by data scarcity, coarse spatial resolution, limited validation under real-world conditions, and weak integration of farmer-level constraints. The paper highlights key gaps in the existing literature and emphasizes the need for data-efficient, scale-appropriate, and decision-relevant modeling approaches to improve the utility of AI-driven yield prediction in climate-sensitive smallholder agricultural systems.},
      month = {March},
      doi = {https://doi.org/10.64388/IREV5I9-1713512}
  }