An AIoT-Based Automated Farming Irrigation System for Farmers in Limpopo Province

Abstract

Limpopo, one of South Africa's nine provinces, is mostly rural, where agriculture serves as the primary occupation for around 89 percent of the total population. Agriculture relies on water, making it its most valuable asset. Through irrigation, water is supplied to crops for growth, frost control, and crop cooling. Irrigation can occur naturally, as with precipitation, or artificially, as with sprinklers. However, artificial irrigation is wasteful as it is regulated and monitored through human intervention, leading to water scarcity which is one of the obstacles that threatens the agricultural sector in the province of Limpopo. A machine learning precipitation prediction algorithm optimizes water usage. The paper also describes a system with multiple sensors that detect soil parameters, and automatically irrigate land based on soil moisture by switching the motor on/off. The objective of this paper is to develop an automated farming irrigation system that is both efficient and effective, with the intention of contributing to the resolution of the water crisis in the province of Limpopo. The proposed solution ought to be capable of decreasing labour hours, generating cost savings, ensuring consistent and efficient water usage, and gathering informed data to inform future research. Thus, farmers will have greater access to information regarding when to irrigate, how much water to use, weather alerts, and recommendations. In acquiring these, the ARIMA model was applied alongside DSRM for implementing the mobile application. The results obtained indicate that the use of AI and IoT (AIoT) in agriculture can improve operational efficiency with reduced human intervention as there is real-time data acquisition with real-time processing and predictions.