Abstract

Traditional farming in developing nations often suffers from inefficiency due to a lack of real-time information on soil health, weather conditions, and crop growth, leading to reduced productivity and resource wastage. The aim of this study is to develop a smart agriculture system that integrates the Internet of Things (IoT) and Machine Learning (ML) to improve crop management, optimize resource use, and support sustainable farming practices. By combining IoT with Machine Learning (ML), agriculture can become more sustainable, efficient, and intelligent—paving the way for future-ready, data-driven farming systems that enhance productivity and ensure food security. The findings indicate that the proposed IoT–ML system enables precise monitoring of crops and soil conditions, facilitates data-driven decision-making, and significantly improves resource efficiency. The ensemble-based model achieved high predictive accuracy, demonstrating the effectiveness of combining multiple ML algorithms for smart agriculture applications. Additionally, real-time data updates from WSNs allow farmers to respond quickly to changes in field conditions, reducing losses and increasing productivity. IoT and machine learning are working together to turn agriculture into a data-driven ecosystem that guarantees sustainability, efficiency, and food security for all. In conclusion, integrating IoT and ML creates a robust, intelligent, and scalable farming ecosystem. The system not only improves agricultural efficiency and sustainability but also supports proactive decision-making and long-term food security. It is recommended that policymakers and farmers adopt such smart farming approaches to enhance productivity, optimize resource use, and ensure sustainable agricultural development.

Key words: Internet of Things (IoT), Machine Learning, Precision Farming.