CARTO AI Lab: working at the frontier of geospatial AI

CARTO has launched the CARTO AI Lab to combine Agentic GIS and geospatial foundation models for faster, more accessible spatial analysis and real-world decision-making. The lab researches and develops models that learn reusable representations of places, analytics that make embedding-based insights usable without machine-learning expertise, and AI agent skills for advanced spatial methods such as geographically weighted regression, spatial autocorrelation, and composite scoring. Its first model, PlacePulse, created with Applied Geographic Solutions, produces 256-dimensional embeddings for roughly 1.06 million populated H3 cells across the United States using demographic, economic, commuting, and climate-risk data, supporting applications including market selection, demand estimation, risk modeling, and infrastructure planning. The initiative also collaborates with academic, research, and industry partners to evaluate models, develop new analytical approaches, and address unresolved geospatial AI challenges.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.