A Contributor-Focused Intrinsic Quality Assessment of OpenStreetMap in Mozambique Using Unsupervised Machine Learning

Abstract

Anyone can contribute geographic information to OpenStreetMap (OSM), regardless of their level of experience or skills, which has raised concerns about quality. When reference data is not available to assess the quality of OSM data, intrinsic methods that assess the data and its metadata can be used. In this study, we applied unsupervised machine learning for analysing OSM history data to get a better understanding of who contributed when and how in Mozambique. Even though no absolute statements can be made about the quality of the data, the results provide valuable insight into the quality. Most of the data in Mozambique (93%) was contributed by a small group of active contributors (25%). However, these were less active than the OSM Foundation’s definition of active contributorship and the Humanitarian OpenStreetMap Team (HOT) definition for intermediate mappers. Compared to other contributor classifications, our results revealed a new class: contributors who were new in the area and most likely attracted by HOT mapping events during disaster relief operations in Mozambique in 2019. More studies in different parts of the world would establish whether the patterns observed here are typical for developing countries. Intrinsic methods cannot replace ground truthing or extrinsic methods, but provide alternative ways for gaining insight about quality, and they can also be used to inform efforts to further improve the quality. We provide suggestions for how contributor-focused intrinsic quality assessments could be further refined.

Point-of-Interest (POI) Data Validation Methods: An Urban Case Study

“…Articles from the peak in 2014 generally focus on laying the frameworks for assessing volunteered geographic information (VGI) quality [18,19], along with the development of methods for assessment [20][21][22][23]. In recent years, despite the lower number of articles, the field developed in several new directions, such as in more sophisticated statistical machine learning methods for quality assessment [24,25] and POI matching [26,27]. Recent studies also explore novel data sources beyond OSM, such as LBSNs and review websites [27,28], and broader applications of POI data [10,29,30].…”

“…Machine learning methods can estimate positional accuracy based on the spatial, temporal and user characteristics of contributions [42]. Some external data will first be required to train the estimation model, although unsupervised learning methods can be used to glean insights into the characteristics of contributors [25].…”

“…Comparing Nearest Neighbour Index of D eval and D ref [28] Ex Comparing relative clustering with Cross-K function [28] In Machine learning methods on spatial, temporal and user characteristics of contributions [25,42] •…”

Towards the Integration of Authoritative and Openstreetmap Geospatial Datasets in Support of the European Strategy for Data

“…Among them Du et al (2012), Abdolmajidi et al (2014), Fan et al (2016) and Brovelli et al (2017) developed and tested methodologies to evaluate the quality of OSM data by comparing it against their authoritative counterparts, using the road network as a use case applied at the local level (city or town) in different places around Europe (UK, Sweden, Germany and Italy, respectively). Instead of comparing OSM with authoritative datasets, other studies such as Barron et al (2014), Minghini and Frassinelli (2019) and Madubedube et al (2021) assessed OSM quality through intrinsic approaches, i.e. by only looking at the history of the OSM data itself (e.g.…”

Using Vector Agents to Implement an Unsupervised Image Classification Algorithm

“…In the supervised classification, the algorithm is first trained using ground data and then applied to classify the image pixels. Unsupervised algorithms only use the information that is contained in the image to classify pixels without requiring any training data [3,4]. As the algorithm does not require training samples, it is easy to perform with minimum human intervention and cost [5,6].…”