An aggregate learning approach for interpretable semi-supervised population prediction and disaggregation using ancillary data
This provides a more interpretable solution for creating high-resolution population maps needed for assessing climate shocks, disasters, and policy impacts.
The paper tackles the problem of disaggregating coarse census data into fine-grained population maps by framing it as an aggregate learning problem where only regional totals are known during training. They demonstrate that their simple, interpretable model matches or outperforms state-of-the-art methods on some metrics.
Census data provide detailed information about population characteristics at a coarse resolution. Nevertheless, fine-grained, high-resolution mappings of population counts are increasingly needed to characterize population dynamics and to assess the consequences of climate shocks, natural disasters, investments in infrastructure, development policies, etc. Dissagregating these census is a complex machine learning, and multiple solutions have been proposed in past research. We propose in this paper to view the problem in the context of the aggregate learning paradigm, where the output value for all training points is not known, but where it is only known for aggregates of the points (i.e. in this context, for regions of pixels where a census is available). We demonstrate with a very simple and interpretable model that this method is on par, and even outperforms on some metrics, the state-of-the-art, despite its simplicity.