Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning

TL;DR

This paper presents a deep learning approach using satellite imagery to assess infrastructure quality in Africa, enabling cost-effective monitoring aligned with sustainable development goals.

Contribution

It introduces a CNN-based method trained on satellite data and survey labels, achieving high accuracy and generalizability for infrastructure quality prediction in developing regions.

Findings

Achieved AUROC scores above 0.86 for electricity and sewerage.

Outperformed models using OpenStreetMap and nighttime lights.

Effective transfer learning for unseen countries with limited data.

Abstract

The UN Sustainable Development Goals allude to the importance of infrastructure quality in three of its seventeen goals. However, monitoring infrastructure quality in developing regions remains prohibitively expensive and impedes efforts to measure progress toward these goals. To this end, we investigate the use of widely available remote sensing data for the prediction of infrastructure quality in Africa. We train a convolutional neural network to predict ground truth labels from the Afrobarometer Round 6 survey using Landsat 8 and Sentinel 1 satellite imagery. Our best models predict infrastructure quality with AUROC scores of 0.881 on Electricity, 0.862 on Sewerage, 0.739 on Piped Water, and 0.786 on Roads using Landsat 8. These performances are significantly better than models that leverage OpenStreetMap or nighttime light intensity on the same tasks. We also demonstrate that our trained model can accurately make predictions in an unseen country after fine-tuning on a small sample of images. Furthermore, the model can be deployed in regions with limited samples to predict infrastructure outcomes with higher performance than nearest neighbor spatial interpolation.