An Aggregate Learning Approach for Interpretable Semi-Supervised Population Prediction and Disaggregation Using Ancillary Data

  title={An Aggregate Learning Approach for Interpretable Semi-Supervised Population Prediction and Disaggregation Using Ancillary Data},
  author={Guillaume Derval and Fr{\'e}d{\'e}ric Docquier and Pierre Schaus},
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… 
Aggregate Learning for Mixed Frequency Data
A Mixed-Frequency Aggregate Learning (MF-AGL) model is proposed that predicts economic indicators for the smaller areas in real-time and finds that the proposed model predicts the regional heterogeneity of the labor market condition and the rapidly changing economic status.


A Deep Learning Approach for Population Estimation from Satellite Imagery
A deep learning model is proposed for creating high-resolution population estimations from satellite imagery that aggregating the model's estimates gives comparable results to the Census county-level population projections and that the predictions made by the model can be directly interpreted, which give it advantages over traditional population disaggregation methods.
Equitable development through deep learning: The case of sub-national population density estimation
A convolutional neural network approach is proposed that addresses some of the methodological challenges, while employing a publicly available, albeit low resolution, remote sensed product, and converts satellite images into population density estimates.
Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data
This work presents a new semi-automated dasymetric modeling approach that incorporates detailed census and ancillary data in a flexible, “Random Forest” estimation technique, and outlines how this algorithm will be extended to provide freely-available gridded population data sets for Africa, Asia and Latin America.
Supervised Learning by Training on Aggregate Outputs
This work presents a new twist on supervised learning where, instead of having the training set contain an individual output value for each input vector, the output values in theTraining set are only given in aggregate over a number of input vectors.
Generating Surface Models of Population Using Dasymetric Mapping
Abstract Aggregated demographic datasets are associated with analytical and cartographic problems due to the arbitrary nature of areal unit partitioning. This article describes a methodology for
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
New Global Hydrography Derived From Spaceborne Elevation Data
To study the Earth system and to better understand the implications of global environmental change, there is a growing need for large-scale hydrographic data sets that serve as prerequisites in a