Solomon Hsiang

Esther Rolf, Jonathan Proctor, Tamma Carleton et al.

Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use. We show that a single encoding of satellite imagery can generalize across diverse prediction tasks (e.g. forest cover, house price, road length). Our method achieves accuracy competitive with deep neural networks at orders of magnitude lower computational cost, scales globally, delivers label super-resolution predictions, and facilitates characterizations of uncertainty. Since image encodings are shared across tasks, they can be centrally computed and distributed to unlimited researchers, who need only fit a linear regression to their own ground truth data in order to achieve state-of-the-art SIML performance.

Hannah Druckenmiller, Solomon Hsiang

We develop a cross-sectional research design to identify causal effects in the presence of unobservable heterogeneity without instruments. When units are dense in physical space, it may be sufficient to regress the "spatial first differences" (SFD) of the outcome on the treatment and omit all covariates. The identifying assumptions of SFD are similar in mathematical structure and plausibility to other quasi-experimental designs. We use SFD to obtain new estimates for the effects of time-invariant geographic factors, soil and climate, on long-run agricultural productivities --- relationships crucial for economic decisions, such as land management and climate policy, but notoriously confounded by unobservables.