Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery

TL;DR

This paper introduces SCALAE, a spatially conditional GAN based on ALAE, capable of generating satellite imagery conditioned on population distributions, aiding land use change analysis and visualization under climate change scenarios.

Contribution

The paper presents SCALAE, an extension of ALAE that explicitly disentangles population data from latent space, enabling controlled generation of satellite images conditioned on population forecasts.

Findings

Model accurately captures population distributions.

Generates realistic satellite imagery with controllable population inputs.

Provides a tool for land cover change estimation and visualization.

Abstract

Climate change is expected to reshuffle the settlement landscape: forcing people in affected areas to migrate, to change their lifeways, and continuing to affect demographic change throughout the world. Changes to the geographic distribution of population will have dramatic impacts on land use and land cover and thus constitute one of the major challenges of planning for climate change scenarios. In this paper, we explore a generative model framework for generating satellite imagery conditional on gridded population distributions. We make additions to the existing ALAE architecture, creating a spatially conditional version: SCALAE. This method allows us to explicitly disentangle population from the model's latent space and thus input custom population forecasts into the generated imagery. We postulate that such imagery could then be directly used for land cover and land use change estimation using existing frameworks, as well as for realistic visualisation of expected local change. We evaluate the model by comparing pixel and semantic reconstructions, as well as calculate the standard FID metric. The results suggest the model captures population distributions accurately and delivers a controllable method to generate realistic satellite imagery.