The Fourth Industrial Revolution (4IR) technologies are rapidly advancing with the emergence of AI, ML, IoT, and Big Data. These technologies are transforming how geospatial data is captured, managed, and generated. The challenge now is how to effectively collect, manage, produce, and share this data, as well as access new data sources.
In the second session of the National Mapping Summit, Mark Cygan, Director of National Mapping Solutions at Esri, USA, addressed these questions by discussing six architectural pillars that should be integrated into well-architected systems.
Cygan emphasized, “A well-architected Geospatial system should encompass six architectural pillars: Reliability, Integration, Performance, Scalability, Automation, Security, and Observability to ensure efficient monitoring capabilities.”
AI Infrastructure Solutions
In his keynote, Jeroen Zanen, Founder & CEO of AI-Infrasolutions, outlined his company’s focus on large-scale mobile mapping and AI-driven asset management. This comprehensive solution leverages data acquisition and enrichment with artificial intelligence to enhance Infrastructure Asset Management.
Zanen highlighted the rapid nationwide data capture capabilities of AI-Infrasolutions, stating, “With a fleet of 15 cars, we conduct annual nationwide data capture in the Netherlands. We can extract and process complex information within 24 hours, showcasing the speed and efficiency of our operations.”
Addressing operational challenges, Zanen emphasized the importance of advanced technologies like AI, ML, and IoT in optimizing processes and enhancing data security.
Chris Williams, Head of Digital Mapping at the British Geological Survey, emphasized the critical role of trust in developing and maintaining the tools and pipelines essential for geological mapping capabilities.
Accelerated Data Collection for National Mapping
Accelerated data collection is a key component of the broader geospatial ecosystem, as highlighted by Vikrant Nashine, Global Delivery Head – GIS at Tech Mahindra. Nashine stressed the importance of a well-established framework, emphasizing the need for flexibility, adaptability, and scalability in Field Data collection networks.
Brenda Alejandra MUNOZ De Luna, Head of the Department of Geosystems at the National Institute of Statistics and Geography (INEGI), underscored the significance of Big Data and Machine Learning in enhancing geospatial data for vegetation and land use mapping.
MUNOZ De Luna mentioned, “By leveraging specialized knowledge and satellite imagery, along with geospatial tools, we are seeing promising results in updating and detailing vegetation data.”
The session concluded with insights from Jasmin Catic, Senior Expert at the Spatial Data Infrastructure Geoportal in the Federal Administration for Geodetic and Real Property Affairs in Bosnia & Herzegovina, stressing the importance of capacity building, digitalization, and high-quality datasets in advancing geospatial operations.