IoT Enabled Smart Farming System for Optimizing Crop Management Using Sensors and Machine Learning

The rapid advancement of agricultural technologies has unveiled the potential of Internet of Things (IoT) systems to enhance farming practices and improve agricultural productivity. This study proposes an IoT-enabled smart farming system designed to optimize crop management by providing real-time environmental monitoring through sensor integration and machine learning. The focus of the research is on spinach cultivation in tropical climates, where traditional methods often fail to provide timely data on critical factors such as soil moisture, temperature, light intensity, and pH, resulting in inefficiencies and suboptimal crop yields. The proposed system employs sensors to monitor these environmental parameters, with data transmitted to the cloud for analysis using machine learning algorithms, specifically Random Forest and Linear Regression models. A 30day trial was conducted to assess the system performance, which demonstrated a 20.2% reduction in water usage, a reduction in harvest time from 34 to 29 days, and an increase in crop yield from 720g to 850g. Additionally, plant health levels were consistently maintained above 90%. The findings validate the effectiveness of the IoT-enabled system in enhancing resource efficiency, increasing productivity, and promoting sustainable farming practices. This research provides a scalable solution that leverages smart farming technologies to contribute to food security and the sustainable development of agriculture.