Fig 5. Overview of WorldPop-Global random forest modelling workflow.

(A) Each decision tree in the ensemble is built upon a random bootstrap sample of the log-transformed population and ancillary data by administrative unit. (B) Population density prediction for each cell y_cell(x) is based on an average of the individual trees. (C) Predicted cell densities are normalized by administrative unit and used to dasymetrically disaggregate log-transformed administrative unit population, then transformed to predict population per cell.