# An aggregate learning approach for interpretable semi-supervised population prediction and disaggregation using ancillary data

## TL;DR

This paper introduces an aggregate learning approach for high-resolution population mapping that leverages coarse census data and ancillary information, achieving competitive or superior results with a simple, interpretable model.

## Contribution

It presents a novel aggregate learning framework for population disaggregation that outperforms complex models using a simple, interpretable approach.

## Key findings

- The method achieves comparable or better accuracy than state-of-the-art models.
- A simple model can effectively disaggregate population data using aggregate labels.
- The approach enhances interpretability and performance in population prediction tasks.

## Abstract

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.