Smart City Accessibility Modeling: A Predictive Framework for Mitigating Urban Food Deserts
TL;DR
This research examines a spatial development project in Baltimore, Maryland, using a multi-method computational framework that combines descriptive statistics, multi-variable regressions, travel demand modeling, and Monte Carlo simulations to maximize supply chain logistics and spatial accessibility for community food infrastructure.
Abstract
Urban food deserts are a serious systemic vulnerability at the nexus of data-driven mobility planning and public health. In order to maximize supply chain logistics and spatial accessibility for community food infrastructure, this article presents an urban intelligence framework. We examine a spatial development project in Baltimore, Maryland, using a multi-method computational framework that combines descriptive statistics, multi-variable regressions, travel demand modeling, and Monte Carlo simulations. Predictive systems measure multi-modal transit results, estimate network traffic generation, and assess accessibility gaps. According to empirical results, the suggested smart logistics node increases transit-accessible food coverage from 31% to 74%, creates 1,240 daily trips, and shortens home journey times by 14.7 minutes. Using an 8% discount rate, system-level transportation benefits result in a Net Present Value of $3.82 million over a five-year period. In the end, this research offers a highly reproducible, data-driven approach for utilizing smart city engineering and predictive analytics to improve urban food security.