Water scarcity and inefficient irrigation practices have become critical challenges in the agricultural sector, with traditional irrigation methods often resulting in overuse or underuse of water, leading to poor crop yields and environmental stress. This paper presents an advanced irrigation system that integrates Internet of Things (IoT) sensors with machine learning (ML) algorithms to optimize water usage and improve agricultural productivity. The system utilizes a network of IoT-enabled sensors to continuously monitor real-time environmental parameters such as soil moisture, temperature, humidity, and weather conditions. These data are then fed into machine learning models that predict the optimal irrigation schedule and precise water requirements for crops based on their type, growth stage, and surrounding environmental factors. The proposed system dynamically adjusts water distribution in response to changing field conditions, ensuring minimal water wastage while maintaining optimal soil moisture levels. By automating the irrigation process, this system reduces manual labor and improves water-use efficiency, contributing to the sustainability of farming practices. The results from field testing show significant improvements in both water conservation and crop yield when compared to traditional irrigation techniques. This work highlights the potential of integrating IoT and ML technologies for smart farming and provides a scalable solution for addressing water management challenges in agriculture.