Mapping has entered a transformative era driven by artificial intelligence. Traditional geospatial workflows often manual, time consuming, and resource-intensive are being fundamentally reimagined through GeoAI, the integration of geospatial data, science, and artificial intelligence techniques including machine learning, deep learning, and large language models (Esri, n.d.; Wang et al., 2024). This shift is particularly significant for Africa, where rapid urbanization, climate resilience needs, infrastructure development, and humanitarian response demand faster, more accurate, and scalable mapping solutions. GeoAI automates and augments core mapping tasks such as feature extraction from satellite and aerial imagery, land cover classification, change detection, object detection, and predictive spatial modeling (Song et al., 2023). By reducing reliance on exhaustive manual digitization, these technologies help address persistent challenges in data-scarce environments: limited high-resolution imagery coverage, sparse ground-truth data, and the need for rapid updates in dynamic contexts like informal settlements, disaster-affected areas, and growing cities.

Esri has embedded mature, production-ready AI capabilities throughout the ArcGIS platform, making advanced GeoAI accessible to GIS professionals, government agencies, NGOs, and community mappers without requiring deep AI expertise. ArcGIS Pro includes the dedicated GeoAI toolbox with tools for training, fine-tuning, and deploying models on imagery, point
clouds, video, and tabular data. A growing library of over 75 pretrained deep learning models in the ArcGIS Living Atlas enables immediate application for common tasks such as building footprint extraction, road network detection, vegetation analysis, and image segmentation — dramatically accelerating base map creation and update cycles (Esri, n.d.).

A major recent advancement is the introduction of AI Assistants across the platform. The ArcGIS Pro Assistant (currently in beta) allows users to interact with the software using natural language. It can generate ArcPy code, SQL and Arcade expressions, guide users through complex workflows, automate repetitive tasks, and surface relevant documentation. Complementary assistants in ArcGIS Online and Enterprise support metadata enhancement, item discovery, and conversational data exploration. These capabilities lower the barrier to advanced analysis and make GIS more intuitive for a broader range of users, including those in resource-constrained settings.

Importantly, these technologies can complement and strengthen open mapping initiatives such as OpenStreetMap (OSM). AI-powered feature extraction from imagery can pre-process data to suggest candidate features for community mappers to verify and incorporate into OSM, improving efficiency and coverage. Change detection models can help prioritize areas requiring updates, while quality assurance tools can flag potential inconsistencies. This hybrid approach combining the strengths of automated GeoAI with human local knowledge and community validation, offers a powerful pathway for accelerating authoritative and community-driven mapping across Africa (Iyer et al., 2025).

Esri emphasizes Trusted AI principles transparency, fairness, security, privacy, and accountability ensuring that models are responsibly developed and deployed. Pretrained models are battle-tested, and the platform supports fine-tuning on local datasets to improve accuracy for African contexts (e.g., diverse building types, vegetation, or informal settlement patterns).

Looking ahead, Esri is advancing geospatial foundation models, vision-language models GeoVLM), and location embeddings that further reduce the need for large labeled datasets while improving generalization across regions and sensors. These developments hold significant promise for the African mapping community (Esri, n.d.).

This presentation will demonstrate practical ArcGIS GeoAI workflows, share examples relevant to African use cases (urban mapping, disaster preparedness, infrastructure monitoring, and agricultural monitoring), and explore opportunities for collaboration between commercial GIS platforms and open mapping communities. By combining the scalability and analytical power of ArcGIS AI with the ground-truth richness of community mapping, we can collectively accelerate progress toward more complete, current, and actionable geospatial data for the continent.