Smart IoT-Driven Precision Irrigation: Enhancing Water Efficiency with Machine Learning and Real-Time Environmental Monitoring

The integration of the Internet of Things (IoT) and Machine Learning (ML) in agriculture has transformed traditional farming by enabling real-time monitoring, automated irrigation control, and optimized resource utilization. This study presents an intelligent IoT-based precision irrigation system that leverages ESP32 NodeMCU and Arduino microcontrollers to collect real-time sensor data, including soil moisture, temperature, and humidity. The data is stored in a cloud-based system and analyzed using machine learning models-Random Forest (RF), Long Short-Term Memory (LSTM), and XGBoost-to predict optimal irrigation schedules. Field experiments reveal that IoT-driven irrigation led to a 2.3° C reduction in temperature and a 5 % increase in soil moisture, while ML-based predictive irrigation further enhanced moisture retention by $1.5 \%-2.5 \%$. The proposed system enhances agricultural sustainability, reduces water wastage, and improves overall farm productivity. Future work will focus on refining AI models for real-time anomaly detection, expanding field trials for large-scale deployment, and integrating adaptive decision-making techniques to further optimize water management.