English innovativejournal825@gmail.com
JAIMT Logo

JAIMT

Journal of Artificial Intelligence and Modern Technology (JAIMT)

Published article details, abstract, issue information, DOI, and downloadable manuscript file.

E-ISSN: 1595-6281 Bimonthly Publication Submit: innovativejournal825@gmail.com
Publication Details

An AI-Driven Decision Support System for Optimizing Irrigation and Fertilizer Application in Cassava Farms at Ambrose Alli University, Ekpoma

Author(s)
Article Type Research Article
Pages 80-96
Issue Vol.8 No.1, 2026
Publication Date

Abstract

Cassava production in Nigeria remains significantly below its agronomic potential due to inefficient irrigation practices, imprecise fertilizer application, and increasing climate variability. This study presents the design, implementation, and evaluation of an Artificial Intelligence-driven Decision Support System (AI-DSS) aimed at optimizing irrigation and nutrient management in cassava cultivation at Ambrose Alli University, Ekpoma. The system integrates Internet of Things (IoT)-based soil sensors, hyperlocal weather data from NASA POWER, and machine learning algorithms (Random Forest and XGBoost) to generate real-time agronomic recommendations. A randomized controlled experimental design was employed using 20 plots (10 AI-managed and 10 conventionally managed) over a 12-month cassava growth cycle. Results demonstrate that the AI-DSS achieved a prediction accuracy of 86.4% (RMSE = 0.43), leading to a 21.8% increase in cassava yield (from 15.2 to 18.5 tons/ha) and a 31.2% reduction in water usage. Nutrient Use Efficiency (NUE) improved by 34.7%, while Water Use Efficiency (WUE) increased significantly (p < 0.05). These findings validate the effectiveness of AI-driven precision agriculture in tropical smallholder contexts. Additionally, the system contributed to capacity building by training over 50 students in digital agriculture technologies. The study addresses critical gaps in localized AI adoption in Nigerian agriculture by developing a cost-effective and scalable solution tailored to ferralitic soils and institutional farm settings. It contributes to both academic knowledge and practical implementation pathways for sustainable intensification of cassava production. The research aligns with Sustainable Development Goals 2 and 9 and provides a replicable model for broader agricultural transformation in sub-Saharan Africa.