Machine Learning Approach in IoT-based Smart Irrigation: A Review for Sustainable Agriculture

With rising global food demand and increasing stress on freshwater resources, agriculture faces mounting pressure to optimize water use. Traditional irrigation methods are inefficient, often causing substantial water loss due to runoff, evaporation, and overwatering. This review highlights the potential of Artificial Intelligence (AI), especially Machine Learning (ML), to revolutionize irrigation practices by enabling precision and water-efficient agriculture. Smart irrigation systems powered by ML leverage data from IoT sensors-monitoring soil moisture, humidity, temperature, and rainfall to automate water delivery based on real-time field conditions. Advanced models such as SVM, KNN, and CNNs help forecast water requirements, minimize wastage, and improve crop yield. It also addresses challenges like high system costs, inconsistent sensor data, and the need for farmer training. The study emphasizes the importance of integrating AI, affordable sensing technologies, and open data platforms to promote sustainable, climate-resilient agriculture and ensure optimal water usage in diverse agricultural environments.