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
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:
Check the Last Posts of our Scientific Blog
The AI Reading Series · From Perceptrons to Agents · Lecture 1: Where Machine Learning Came From — Reading Cardon’s Neurons Spike Back
The first in a reading series taking you from the artificial neuron of 1943 to today's transformers, mixture-of-experts models and agents. Lecture 1 is a preparatory guide to Cardon, Cointet and Mazières' sociological history of AI, with reading strategy and glossary.
Deploy Your Own Local LLM on Low VRAM in 30 Minutes — A Private Chat Assistant in Jupyter
Run a capable large language model entirely on your own machine — private, offline, and with as little as 8 GB of GPU memory. This hands-on guide sets up a clean Python environment, gets CUDA working even on the newest NVIDIA Blackwell cards, loads a 4-bit quantized model from Hugging Face, and builds an interactive chat widget with conversation memory and a live VRAM gauge in JupyterLab. No cloud, no API keys, no data leaving your computer.
SAGAI v2.0 — A Unified Multi-Model Notebook for Streetscape Analysis
SAGAI v2.0 consolidates the full streetscape analysis pipeline into a single Google Colab notebook and replaces the inline LLaVA-only inference code with the UVLM package, enabling multi-model benchmarking across 11 VLM checkpoints. New features include a multi-task prompt builder, consensus validation with majority voting, chain-of-thought reasoning, truncation detection, interactive Folium maps, view-direction filtering, and support for loading existing polygons as study area boundaries.