Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities

TL;DR

This paper explores how satellite imagery can be used to adjust for confounding factors in causal inference, especially in settings with scarce tabular data, by formalizing the challenges and proposing methods for estimation and analysis.

Contribution

It introduces a formal framework for causal adjustment using unstructured satellite image data and demonstrates its application in evaluating anti-poverty programs in Africa.

Findings

Satellite imagery can serve as a proxy for unobserved confounders.

The methods are sensitive to image resolution and confounder misspecification.

Application to African communities shows practical utility.

Abstract

Observational studies require adjustment for confounding factors that are correlated with both the treatment and outcome. In the setting where the observed variables are tabular quantities such as average income in a neighborhood, tools have been developed for addressing such confounding. However, in many parts of the developing world, features about local communities may be scarce. In this context, satellite imagery can play an important role, serving as a proxy for the confounding variables otherwise unobserved. In this paper, we study confounder adjustment in this non-tabular setting, where patterns or objects found in satellite images contribute to the confounder bias. Using the evaluation of anti-poverty aid programs in Africa as our running example, we formalize the challenge of performing causal adjustment with such unstructured data -- what conditions are sufficient to identify causal effects, how to perform estimation, and how to quantify the ways in which certain aspects of the unstructured image object are most predictive of the treatment decision. Via simulation, we also explore the sensitivity of satellite image-based observational inference to image resolution and to misspecification of the image-associated confounder. Finally, we apply these tools in estimating the effect of anti-poverty interventions in African communities from satellite imagery.