Urban Geo Analytics

Spatial Analysis, GeoAI & Machine Learning

Welcome to Urban Geo Analytics

Urban Geo Analytics brings together geography, machine learning, and AI to help cities make sense of the data that shapes them. Founded by Joan Perez, a geographer and researcher specializing in spatial analysis and geospatial AI, UGA develops open-source tools — from vision-language pipelines for streetscape analysis to population and accessibility models — used in Horizon Europe research consortia and international consulting assignments, including for the World Bank. Our mission: give planners, researchers, and policymakers scalable, transparent, data-driven ways to understand and improve the urban environment.

Welcome to Urban Geo Analytics

Urban Geo Analytics brings together geography, machine learning, and AI to help cities make sense of the data that shapes them. Founded by Joan Perez, a geographer and researcher specializing in spatial analysis and geospatial AI, UGA develops open-source tools — from vision-language pipelines for streetscape analysis to population and accessibility models — used in Horizon Europe research consortia and international consulting assignments, including for the World Bank. Our mission: give planners, researchers, and policymakers scalable, transparent, data-driven ways to understand and improve the urban environment.

Our Expertise & Services

AI & Vision-Language Models

Urban Geo Analytics harnesses generative AI to interpret complex urban imagery and generate structured insights. With tools like SAGAI, we enable zero-shot visual assessments of walkability, commercial density, and streetscape quality using street-level images and natural language prompts.

Read More

Generative Image, Video & Scene Editing

Generate realistic urban design concepts, streetscape visualizations, and planning scenarios from sketches, maps, or text prompts. Our diffusion models can help you create, edit, and visualize future urban environments, public spaces, and development scenarios.

Read More

Geospatial Analysis & Urban Intelligence

Transform complex spatial data into actionable urban intelligence through advanced GIS, network analysis, accessibility modelling, urban morphometrics, and AI-powered geospatial workflows.

Read More

IoT, Blockchain & Geospatial Interoperability

We are pioneering the convergence of geospatial data and blockchain technologies. By designing decentralized protocols for urban data sharing and validation, we help ensure data security, traceability, and interoperability across stakeholders and platforms.

Read More

Training & Knowledge Sharing

Urban Geo Analytics also offers tailored training and consulting services to empower professionals and organizations with the skills to lead in geospatial innovation:

Workshops & Custom Trainings

We provide learning experiences on core topics including geospatial AI, urban data workflows, blockchain for spatial systems, and urban accessibility modeling. Whether for universities, public institutions, or private firms, our trainings adapt to your strategic goals.

Read More

Academic & Institutional Partnerships

Our collaborations span disciplines and sectors. We work with academic partners on methodological innovation and with cities and NGOs on applied projects addressing sustainability, mobility, and resilience.

Read More

Open Source Development

We believe in the power of transparent, reproducible science. Our tools are open-source and designed for easy deployment on global datasets. Whether you’re working on local zoning issues or international urban comparisons, our modular Python workflows scale with your needs.

Check our Software

Research & Consulting Projects

Discover how Urban Geo Analytics applies geospatial AI, spatial analysis, and urban science to solve real-world challenges through international research and consulting projects.

Check our Projects

Check the Last Posts of our Scientific Blog

Do Open-Weight LLMs Reason From the Spatial Context They Are Given?

October 1, 2026|Comments Off on Do Open-Weight LLMs Reason From the Spatial Context They Are Given?

A new paper asks a question geographic evaluation has mostly skipped: once a language model is handed the right local data, does it reason from it, or fall back on what it already believes about the place? Sixteen open-weight configurations, three cities, ten seeds, and one planted false premise per case.