ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE AGRICULTURE: ENHANCING  CROP PRODUCTIVITY THROUGH MACHINE LEARNING IN KENYA

Ndung’u H., Munyao V.W. Wasike J

Ndung’u H., Munyao V.W. Wasike J Kirinyaga University,

Abstract

Agriculture is the backbone of food security and economic development in many developing countries.However, smallholder farmers continue to face challenges such as climate change, low agricultural
productivity, and unpredictable weather patterns. Artificial Intelligence (AI) has emerged as a promising technology for improving farming productivity and efficiency. Despite its potential, adoption
of machine-to-machine (M2M) and AI technologies remain limited in sub-Saharan Africa due to inadequate infrastructure and technological constraints. This study examined the predictive value of
AI-driven modelling in yield forecasting and optimal potential planting schedules and whether or not machine learning (ML) algorithms can be used to minimize farming risks and enhance agricultural
output. The study analyzed weather patterns, soil characteristics, and historical crop yield data collected from 500 farms in Kirinyaga County, Kenya. A Random Forest regression model was developed to
predict optimal planting and harvesting periods. Model performance was assessed using the Mean Absolute Error (MAE) and the coefficient of determination (R²). Surveys and expert interviews were
conducted to identify barriers to AI adoption among smallholder farmers. The AI model demonstrated strong predictive performance, achieving an R² value of 0.91. Farmers who implemented the AIgenerated recommendations recorded an average crop yield increase of 27%. However, limited digital literacy, inadequate technological infrastructure, and insufficient support services were identified as major barriers to widespread adoption. These results demonstrate that AI-based decision support systems can significantly enhance agricultural productivity through improved resource utilization, and
climate resilience. Integrating AI with Internet of Things (IoT) technologies offers substantial potential for advancing precision agriculture. Future research should focus on developing integrated AI–IoT
farming models and formulating supportive government policies to accelerate AI adoption to optimize agricultural practices in developing countries.