Enhancing Digital Road Networks for Better Operations in Developing Countries

Data scarcity in developing countries often significantly complicates the use of analytics to address development challenges. One of the most fundamental data structures needed in operations management is digitized road data; e.g., a poorly digitized road network significantly reduces our ability to optimize trade of micro-enterprises (SDG 8) and placement of hospitals (SDG 3). Unfortunately, current methods to extend or create digital road networks are not well-adapted to regions with sparse geospatial data and, as a result, road networks are often poorly represented digitally in less-developed regions such as rural areas of developing countries. To address this, we propose a novel method to create digital road networks in regions with sparse geospatial data, by adapting existing methods to ensure they extract as much information as possible from the limited available data. Our proposed method combines projection-based incremental insertion methods that incrementally add new information to existing road networks when it becomes available, with a simple edge adjustment procedure that allows edge geometries to be improved when more information becomes available. This method is well-suited to either incrementally adjust a large existing road network (e.g., OSM) or combine multiple sources of road networks in regions with sparse data (e.g., OSM and eStrada, a dataset provided by the World Bank). Our method significantly improves the digital road network for smallholder farmers in Indonesia, where only 40% of the origin-destination pairs in our dataset were previously digitized. In a case study of optimizing geospatial accessibility to healthcare in Timor-Leste, we find that the improved road network detects an additional 5% of people to be in the vicinity of a hospital.