Abstract
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa’s most populous country.
Highlights
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world
We find that a deep learning model trained on this imagery is able to explain ~70% of the spatial variation in ground-measured village-level asset wealth across Africa, and up to 50% of temporal variation when aggregating to the district level
We focus on asset wealth rather than other welfare measurements as asset wealth is thought to be a less-noisy measure of households’ longer-run economic wellbeing[13,14], is a common component of multi-dimensional poverty measures used by development practitioners around the world, is actively used as a means to target social programs[14,15], and is much more widely observed in publicly available georeferenced African survey data
Summary
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. At least 4 years pass between nationally representative consumption or asset wealth surveys in the majority of African countries (Fig. 1a), the key source of data for internationally comparable poverty measurements These surveys have limited repeated observation of individual locations, making it difficult to measure local changes in well-being over time, and public release of any disaggregated consumption data from African countries is very rare. While not all households need to be observed to generate accurate economic estimates, sampling enough households to generate frequent and reliable nationallevel statistics is alone likely to be expensive, requiring an estimated $1 billion USD annual investment in lower-income countries to measure a range of indicators relevant to the Sustainable Development Goals[6] Expanding these efforts to generate reliable estimates at the local level would add dramatically to these costs. Our focus is on using multiple sources of spatially coarser public imagery to infer both spatial and temporal differences in local-level economic well-being across sub-Saharan Africa, including for countries where reliable survey data do not yet exist and where survey-based interpolation methods might struggle to generate accurate estimates
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
