Modeling Urban Food Insecurity with Google Street View Images
This work addresses food insecurity identification for urban planners and policymakers, offering a scalable supplement to survey-based methods, though it is incremental in nature.
The paper tackled modeling urban food insecurity by using Google Street View images at the census tract level, proposing a two-step feature extraction and gated attention method, but it fell slightly short in predictive power compared to other models.
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.