Mesh-Wise Prediction of Demographic Composition from Satellite Images Using Multi-Head Convolutional Neural Network

TL;DR

This paper introduces a multi-head CNN model utilizing transfer learning from ResNet50 to predict detailed demographic compositions across regions in Japan using satellite imagery, enabling high-resolution demographic monitoring.

Contribution

It presents a novel multi-head CNN approach with transfer learning for mesh-wise demographic prediction from satellite images, addressing data scarcity and resolution issues.

Findings

Achieved at least 0.8914 R^2 score across demographic groups

Successfully visualized 2022 demographic compositions from satellite data

Demonstrated feasibility of high-resolution demographic estimation using deep learning

Abstract

Population aging is one of the most serious problems in certain countries. In order to implement its countermeasures, understanding its rapid progress is of urgency with a granular resolution. However, a detailed and rigorous survey with high frequency is not feasible due to the constraints of financial and human resources. Nowadays, Deep Learning is prevalent for pattern recognition with significant accuracy, with its application to remote sensing. This paper proposes a multi-head Convolutional Neural Network model with transfer learning from pre-trained ResNet50 for estimating mesh-wise demographics of Japan as one of the most aged countries in the world, with satellite images from Landsat-8/OLI and Suomi NPP/VIIRS-DNS as inputs and census demographics as labels. The trained model was performed on a testing dataset with a test score of at least 0.8914 in $\text{R}^2$ for all the demographic composition groups, and the estimated demographic composition was generated and visualised for 2022 as a non-census year.