Can Human Development be Measured with Satellite Imagery?

In many developing country environments, it is difficult or impossible to obtain recent, reliable estimates of human development. Nationally representative household surveys, which are the standard instrument for determining development policy and priorities, are typically too expensive to collect with any regularity. Recently, however, researchers have shown the potential for remote sensing technologies to provide a possible solution to this data constraint. In particular, recent work indicates that satellite imagery can be processed with deep neural networks to accurately estimate the sub-regional distribution of wealth in sub-Saharan Africa. In this paper, we explore the extent to which the same approach--- of using convolutional neural networks to process satellite imagery--- can be used to measure a broader set of human development indicators, in a broader range of geographic contexts. Our analysis produces three main results: First, we successfully replicate prior work showing that satellite images can accurately infer a wealth-based index of poverty in sub-Saharan Africa. Second, we show that this approach can generalize to predicting poverty in other countries and continents, but that the performance is sensitive to the hyperparameters used to tune the learning algorithm. Finally, we find that this approach does not trivially generalize to predicting other measures of development such as educational attainment, access to drinking water, and a variety of health-related indicators. We discuss in detail whether these findings represent a fundamental limitation of this approach, or could be fixed through more concerted adaptations of the machine learning environment.