Enabling Decision-Support Systems through Automated Cell Tower Detection

TL;DR

This paper presents a partially automated deep learning workflow that detects cell towers in African regions using satellite imagery and OpenStreetMap data, significantly improving the accuracy of telecommunications infrastructure maps.

Contribution

The study introduces a novel method combining OSM features and high-resolution satellite images to train an effective cell tower detection model across diverse African geographies.

Findings

Model achieves 81.2% AP@50 in cell tower detection

Effective across multiple African countries and out-of-sample data

Enables more accurate cell coverage mapping for decision support

Abstract

Cell phone coverage and high-speed service gaps persist in rural areas in sub-Saharan Africa, impacting public access to mobile-based financial, educational, and humanitarian services. Improving maps of telecommunications infrastructure can help inform strategies to eliminate gaps in mobile coverage. Deep neural networks, paired with remote sensing images, can be used for object detection of cell towers and eliminate the need for inefficient and burdensome manual mapping to find objects over large geographic regions. In this study, we demonstrate a partially automated workflow to train an object detection model to locate cell towers using OpenStreetMap (OSM) features and high-resolution Maxar imagery. For model fine-tuning and evaluation, we curated a diverse dataset of over 6,000 unique images of cell towers in 26 countries in eastern, southern, and central Africa using automatically generated annotations from OSM points. Our model achieves an average precision at 50% Intersection over Union (IoU) (AP@50) of 81.2 with good performance across different geographies and out-of-sample testing. Accurate localization of cell towers can yield more accurate cell coverage maps, in turn enabling improved delivery of digital services for decision-support applications.