Modeling Urban Food Insecurity with Google Street View Images

TL;DR

This paper investigates using Google Street View images to model urban food insecurity, aiming to provide a scalable alternative to traditional survey methods for policymakers and urban planners.

Contribution

It introduces a novel two-step process combining feature extraction and gated attention for aggregating street-level images to predict food insecurity.

Findings

Model performs comparably to existing methods.

Interpretability of learned weights offers insights.

Potential to supplement traditional survey data.

Abstract

Food insecurity is a significant social and public health issue that plagues many urban metropolitan areas around the world. Existing approaches to identifying food insecurity rely primarily on qualitative and quantitative survey data, which is difficult to scale. This project seeks to explore the effectiveness of using street-level images in modeling food insecurity at the census tract level. To do so, we propose a two-step process of feature extraction and gated attention for image aggregation. We evaluate the effectiveness of our model by comparing against other model architectures, interpreting our learned weights, and performing a case study. While our model falls slightly short in terms of its predictive power, we believe our approach still has the potential to supplement existing methods of identifying food insecurity for urban planners and policymakers.