Fine-Grained Socioeconomic Prediction from Satellite Images with Distributional Adjustment

TL;DR

This paper introduces a deep learning method that predicts fine-grained socioeconomic indicators from satellite images by adjusting scores to match regional distribution patterns, outperforming previous models and showing robustness in diverse development contexts.

Contribution

The study presents a novel distributional adjustment technique for socioeconomic prediction from satellite images, improving accuracy at fine-grained levels and handling uneven development areas.

Findings

Outperforms previous models in predicting population and employment.

Effective in districts with uneven development.

Robust performance in data-scarce developing regions.

Abstract

While measuring socioeconomic indicators is critical for local governments to make informed policy decisions, such measurements are often unavailable at fine-grained levels like municipality. This study employs deep learning-based predictions from satellite images to close the gap. We propose a method that assigns a socioeconomic score to each satellite image by capturing the distributional behavior observed in larger areas based on the ground truth. We train an ordinal regression scoring model and adjust the scores to follow the common power law within and across regions. Evaluation based on official statistics in South Korea shows that our method outperforms previous models in predicting population and employment size at both the municipality and grid levels. Our method also demonstrates robust performance in districts with uneven development, suggesting its potential use in developing countries where reliable, fine-grained data is scarce.