Optimizing Food Security and Minimizing Waste: An Intelligent Agricultural Forecasting System for Qatar

Qatar's reliance on food imports, limited agricultural land, and growing demand highlight the need for efficient resource management to ensure food security. This paper presents an AI-driven predictive system that forecasts agricultural yield using synthetic data encompassing commerce, hospitality, and agricultural sectors. By integrating these datasets through a Python-based ETL (Extract, Transform, Load) pipeline. These inputs were used to train multiple Recurrent Neural Network (RNN) models to predict future harvested quantities. This cross-sectoral data integration significantly enhances prediction accuracy, contributing to improved resource management, waste reduction, and sustainable agricultural practices. The system's modular design supports future expansion to include more data types, enabling comprehensive agricultural planning and bolstering food security in Qatar.