Cornell researchers are pioneering a novel method to map poverty using national surveys and advanced machine learning, addressing the United Nations' aim to eliminate extreme poverty. Their structural poverty estimates leverage Earth observation data to produce actionable insights for policymakers, particularly in southern and eastern Africa. This approach not only measures poverty levels but also indicates the number of individuals living under the critical $2.15 per day threshold. The method enhances resource allocation amidst gaps in traditional data collection, thereby aiding underserved communities more efficiently.
This new approach translates abundant Earth observations into actionable measures for policymakers, enhancing the understanding of poverty levels in regions where traditional data is sparse.
Our structural poverty estimates outperform previous monetary methods and are forward-looking, thereby providing a framework for informing programming and resource allocation effectively.
Collection
[
|
...
]