The Use of Geospatial Artificial Intelligence Technologies (GeoAI) within National Mapping Agencies: A Review

Abstract

Abstract. The field of geospatial artificial intelligence (GeoAI) has brought transformative opportunities to the geospatial domain. Technological advances in machine learning and deep learning, the proliferation of big geospatial data of different sources, computing power capabilities, and the expansion of geographic information systems (GIS) have all contributed to the impact of GeoAI technological trends. National mapping agencies (NMAs) represent a promising and ongoing area for the implementation of GeoAI, enabling them to fully leverage its advantages given the nationwide data infrastructures managed, the missions accomplished, and the challenges faced. However, the implementation of the GeoAI solution also involves technical and ethical constraints that must be taken into account. This paper reviews the integration of GeoAI within NMAs, focusing on practical applications, technical challenges, and ethical considerations. Based on recent scientific literature and institutional reports, the study defines four main application domains: geospatial data extraction, change detection, 3D point cloud classification and standardization of geographical names. The study present how NMAs are leveraging GeoAI to improve efficiency, data quality, and the automation of mapping workflows, while addressing challenges related to data availability, AI infrastructure, and human expertise. The article also discusses key aspects of trustworthy GeoAI, such as explainability, bias and geoprivacy. By bridging applied scientific research and the practical applications, this paper provides a structured overview of a transformative emerging technology, GeoAI, within the context of organizations as specific as NMAs and presents the future trends, such as the development of geofoundational models and agentic AI.