<italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow

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 techniques, have shown significant prom...

Full description

Saved in:
Bibliographic Details
Main Authors: Lasith Niroshan, James D. Carswell
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11045930/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428273674584064
author Lasith Niroshan
James D. Carswell
author_facet Lasith Niroshan
James D. Carswell
author_sort Lasith Niroshan
collection DOAJ
description 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 techniques, have shown significant promise in automating aspects of the volunteered geographic information (VGI) map updating process. This article 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 to freely available spatial datasets, such as OpenStreetMap, DeepMapper enhances the accuracy and completeness of VGI maps. <italic>DeepMapper</italic> 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 nontechnical challenges related to geometric accuracy and the adoption of AI-based mapping by communities, such as OpenStreetMap.
format Article
id doaj-art-1822554dec66449f997d4e527031f83f
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-1822554dec66449f997d4e527031f83f2025-08-20T03:28:44ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118161621617510.1109/JSTARS.2025.358149911045930<italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping WorkflowLasith Niroshan0https://orcid.org/0000-0002-9868-8338James D. Carswell1https://orcid.org/0000-0002-4766-7297University College Dublin, Dublin, IrelandTechnological University Dublin, Dublin, IrelandAI-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 techniques, have shown significant promise in automating aspects of the volunteered geographic information (VGI) map updating process. This article 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 to freely available spatial datasets, such as OpenStreetMap, DeepMapper enhances the accuracy and completeness of VGI maps. <italic>DeepMapper</italic> 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 nontechnical challenges related to geometric accuracy and the adoption of AI-based mapping by communities, such as OpenStreetMap.https://ieeexplore.ieee.org/document/11045930/Automated mappinggeospatial artificial intelligence (GeoAI)OpenStreetMapvolunteered geographic information (VGI)
spellingShingle Lasith Niroshan
James D. Carswell
<italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Automated mapping
geospatial artificial intelligence (GeoAI)
OpenStreetMap
volunteered geographic information (VGI)
title <italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
title_full <italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
title_fullStr <italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
title_full_unstemmed <italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
title_short <italic>DeepMapper:</italic> A GeoAI Approach to Automate the VGI Mapping Workflow
title_sort italic deepmapper italic a geoai approach to automate the vgi mapping workflow
topic Automated mapping
geospatial artificial intelligence (GeoAI)
OpenStreetMap
volunteered geographic information (VGI)
url https://ieeexplore.ieee.org/document/11045930/
work_keys_str_mv AT lasithniroshan italicdeepmapperitalicageoaiapproachtoautomatethevgimappingworkflow
AT jamesdcarswell italicdeepmapperitalicageoaiapproachtoautomatethevgimappingworkflow