Investigating the digital divide in OpenStreetMap: spatio-temporal analysis of inequalities in global urban building completeness

Abstract

OpenStreetMap (OSM) has evolved as a popular geospatial dataset for global studies, such as monitoring progress towards the Sustainable Development Goals (SDGs). However, many global applications turn a blind eye on its uneven spatial coverage. We utilized a regression model to infer OSM building completeness within 13,189 urban agglomerations home to 50% of the global population. Our results reveal that for 1,510 cities OSM building footprint data exceeds 80% completeness. Humanitarian mapping efforts have significantly improved completeness, especially in low SHDI regions. The digital divide in OSM has receded, but a strong spatial bias associated with subnational human development index, city size and World Bank region remains. In consequence, global studies will provide misleading results if the biases in OSM's coverage are not accounted for. We recommend combining completeness maps with socio-demographic information to guide mapping to ensure that "nobody is left behind" as encouraged by the SDGs.

Assessing Completeness of OpenStreetMap Building Footprints Using MapSwipe

“…For the second approach, we used the results from a machine learning model that predicts building footprint areas based on OSM road network data and larger-scale data [13].…”

“…where y represents the building count for the region at a given point in time, Asmp represents the saturation to which the curve converges, t represents time, t mid represents the mid point of the logistic curve-at which half the saturation level is attained-and scale describes the steepness of the logistic curve. Herfort et al [13] trained a machine learning model to predict building footprint areas for urban areas based on the Microsoft building footprint datasets and administrative data. The model used the Global Human Settlement Layer Population, the Subnational Human Development Index, OSM road length as well as night-time lights and land-cover information as predictors.…”

“…We compared the estimates of the model with the aggregated MapSwipe assessments for Taipei, Tokyo and Medellin. For Sirios, no predictions were available as Herfort et al [13] focused on urban areas. Without modifications, the model would presumably also not be suitable for a rural region.…”

“…For example, the completeness of highly populated urban areas is often higher than that of remote and rural areas [10,12]. There are also differences between developed and developing countries [11,13]. These disparities depend on social factors, such as population distribution and population density, as well as the location of contributing users [14].…”

“…For land-cover OSM objects, Schott et al [18] demonstrated the potential of noise-robust deep-learning approaches used on satellite imagery to detect potential errors in OSM land-use information. For building footprints, datasets such as the Microsoft building footprints layer [19] are a potential reference for an increasing-but still limited-number of countries and have been used to assess the completeness of building footprints for 13,189 urban agglomerations by fitting a machine learning model to them [13]. Research by Herfort et al [13] has shown that crowd-sourcing approaches, such as the one presented here, and deep-learning approaches might complement each other.…”