AI-powered mapping technologies are uniquely positioned to address the challenges of keeping online maps up-to-date in dynamic urban environments. Modern Geospatial Artificial Intelligence (GeoAI) approaches, particularly those utilizing advanced Deep Learning (DL) techniques, have shown significant promise in automating aspects of the Volunteered Geographic Information (VGI) map updating process. This paper introduces DeepMapper, an open-source, GeoAI-based mapping platform designed to automate the VGI mapping workflow with minimal human intervention. By applying Generative Adversarial Networks (GANs) to freely available spatial datasets like OpenStreetMap, DeepMapper enhances the accuracy and completeness of VGI maps. As a web-based tool, DeepMapper is a web-based mapping tool that streamlines/automates much of the traditional VGI map updating workflow. Experiments demonstrate that DeepMapper achieves an accuracy of 92.8%, precision of 90.3%, and recall of 92.0%. The platform also shows potential for testing new GeoAI models, facilitating continuous improvements in how contemporary VGI maps are created and maintained. Despite its successes, challenges remain, particularly in adapting DeepMapper to real-world settings and different architectural styles. Further work will explore the integration of diffusion models for building detection and address non-technical challenges related to geometric accuracy and the adoption of AI-based mapping by communities like OpenStreetMap.

Geospatial Artificial Intelligence (GeoAI) offers a scalable solution for automating the generation and updating of volunteered geographic information (VGI) maps—addressing the limitations of manual contributions to crowd-source mapping platforms such as OpenStreetMap (OSM). This study evaluates the accuracy of GeoAI-generated buildings specifically, using two Generative Adversarial Network (GAN) models. These are OSM-GAN—trained on OSM vector data and Google Earth imagery—and OSi-GAN—trained on authoritative “ground truth” Ordnance Survey Ireland (OSi) vector data and aerial orthophotos. Altogether, we assess map feature completeness, shape accuracy, and positional accuracy and conduct qualitative visual evaluations using live OSM database features and OSi map data as a benchmark. The results show that OSi-GAN achieves higher completeness (88.2%), while OSM-GAN provides more consistent shape fidelity (mean HD: 3.29 m; σ = 2.46 m) and positional accuracy (mean centroid distance: 1.02 m) compared to both OSi-GAN and the current OSM map. The OSM dataset exhibits moderate average deviation (mean HD 5.33 m) but high variability, revealing inconsistencies in crowd-source mapping. These empirical results demonstrate the potential of GeoAI to augment manual VGI mapping workflows to support timely downstream applications in urban planning, disaster response, and many other location-based services (LBSs). The findings also emphasize the need for robust Quality Assurance (QA) frameworks to address “AI slop” and ensure the reliability and consistency of GeoAI-generated data.