Precision agriculture for smallholder farmers: Maximizing economics productivity using a machine learning-based water recommendation system

Abstract

This study explores how smallholder farmers in various communities can economically optimize productivity, connectivity, and efficiency using precision agricultural technologies, particularly and sensors. The study can empower many small scale farmers by demonstrating customized applications of precision agriculture tools, thus boosting their ability to maximize resource utilization, reducing risks, and increasing yields. Furthermore, this study developed a machine learning (ML) decision-making system to improve crop yield for smallholder farmers economically in rural South Africa. This system specifically optimises irrigation by detecting soil moisture anomalies and providing recommendations to maintain optimalsoil moisture levels. The optimal range was set for the range of 70 to 80%. The system was trained and modelled using several parameters of soil moisture humidity, atmospheric temperature, soil temperature, and soil moisture. A comparison was carried out using MLmodel and Logistic regression, XGBoost, CatBoost, Gradient Boosting and Support vector 13 machine (SVM). The metrics used were accuracy, F1 Score, Recall, and Precision. The results showed 4 that the XGBoost model performed better than the other four models5 with an accuracy of 0.73, an F1 Score of 0.64, and a recall of 0.73. The Gradient Boosting16 model had the 2nd best result with a precision of 0.79. The findings demonstrated that optimizing irrigation systems, enhanced crop yield could be achieved with better stability.