Supply Chain Optimization for Urban Vertical Farming

Supply chain inefficiencies continue to challenge sustainable food distribution, especially in the context of rapidly growing urban populations. Urban vertical farming (UVF) has emerged as a promising solution to meet local food demands with minimal environmental impact. However, optimizing the supply chain for UVF requires advanced tools capable of handling dynamic variables such as weather conditions, spoilage rates, and inventory levels. In recent years, data science and machine learning (ML) have played a vital role in solving such complex problems through predictive modeling and intelligent decision-making systems. This paper proposes a machine learning-based supply chain optimization framework for urban vertical farming, incorporating a Stacking Regressor ensemble model. The model leverages historical data and real-time environmental inputs using the OpenWeather API to predict cost efficiency. Additionally, the system integrates a recommendation engine for crop suggestions and employs various data science techniques for visualizing resource usage and historical weather trends. The framework is deployed as an interactive web application built with Flask, enabling real-time forecasting, intelligent recommendations, and insightful data visualization for improved supply chain sustainability. The proposed model demonstrates robust performance, supporting efficient decision-making for both producers and consumers in urban agriculture.