Enhancing Personalized Agriculture With Cutting-Edge Hybrid Machine Learning Models And Intelligent Edge Computing For Sustainable Farming

The rapid advancement of artificial intelligence and edge computing has enabled personalized agriculture, optimizing farming practices by tailoring interventions to individual crop needs. Traditional methods often lead to inefficiencies in resource utilization, pest control, and irrigation management. This paper introduces a hybrid machine learning framework integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models with edge computing to enable real-time, site-specific decision-making. IoT sensors collect real-time data on soil moisture, temperature, and humidity, while aerial drones with multispectral imaging provide insights into crop health. XGBoost processes this data for soil health classification and pest risk prediction, achieving 92% accuracy. The hybrid CNN-LSTM model enhances irrigation and pest control predictions by 15% over standalone models, allowing farmers to make more precise, data-driven decisions. Field trials demonstrate a 25% increase in crop yield and a 30% reduction in water usage compared to conventional techniques. Edge computing ensures low-latency processing, enabling real-time implementation without cloud-based constraints. This research bridges the gap between real-time data acquisition, processing, and decision-making, offering a scalable, cost-effective solution for sustainable agriculture by reducing resource wastage, improving food security, and promoting environmentally responsible farming.