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

• Author(s): Asamoah Oppong Zadok
• Paper ID: 1713512
• Page: 789-803
• Published Date: 31-03-2022
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 5 Issue 9 March-2022

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.

Citations

IRE Journals:
Asamoah Oppong Zadok "AI-Driven Crop Yield Prediction Models for Smallholder Farmers in Sub-Saharan Africa" Iconic Research And Engineering Journals Volume 5 Issue 9 2022 Page 789-803 https://doi.org/10.64388/IREV5I9-1713512

IEEE:
Asamoah Oppong Zadok "AI-Driven Crop Yield Prediction Models for Smallholder Farmers in Sub-Saharan Africa" Iconic Research And Engineering Journals, 5(9) https://doi.org/10.64388/IREV5I9-1713512