F2
Module F2 of 10

AI Territory

Reading and producing geographic intelligence with AI

3 ECTSOne fortnight6 sessionsOnline, live and recorded

The module

Every project is a response to a place. Before a single line is drawn, the site has already set the terms: topography and orientation, the grain of the surrounding fabric, what the regulation permits, how people move through it, where water goes, what the climate is doing. A design that reads those conditions well starts from a position of advantage; one that ignores them spends the rest of the process correcting itself. The quality of the initial reading of the context largely determines the quality of everything built on top of it. In practice this phase is the one most often rushed or skipped because of the mechanical processes:, reprojecting, cleaning attribute tables, redrawing the same context by hand, repeating all of it from scratch on the next commission.

Objectives

  1. Query and combine public territorial data sources.
  2. Automate the production of a site analysis.
  3. Produce an interpretive reading, not only a set of maps.
  4. Generate a 3D context model ready for the design environment.

What you will be able to do

Learning outcomes

The student learns to automate the access, download, cleaning, organization and combination of heterogeneous data sources that will inform the first steps of the project.

Professional outcomes

Cuts the time of the first project phase and turns site analysis into a service the studio can offer on its own. The analytic workflow provides valuable information that will root the future project in its context, informing future decisions and setting the best start for data-driven design. Preparing and modelling context used to be a mechanical process that takes time and no thought. AI orchestration changes this step into a powerful research process that ends with a high definition tridimensional output that embeds physical territorial layers (terrain, water, vegetation, other buildings) as well as dunamic layers (social and economic dynamics, weather,) in a relational model that will interact with the design from the first moment.

Methodology

Learn by doing, on the student's own real project. No software tutorials: a pre-built starting package is provided and base resources are given apart. Sessions combine a short input, guided practice and critique.

Concepts

remote sensingterritorial geometrysite analysisOpenStreetMapenvironmental conditionsSpatial statisticscontext modelinterpretive report

Session by session

  1. Reading the territory: sources and limits. The power of geospstial analysis and open data stack.
  2. Data Infrastructure. Querying public APIs of different scales, cleaning and selectincnresults, managing reusable databases.
  3. Processing and cross-referencing territorial data. Orchestrating processes and analysis (I)
  4. Processing and cross-referencing territorial data. Orchestrating processes and analysis (II)
  5. Analyzing results and producing the interpretative report. Preparing and selecting exportes data.
  6. Building the 3D context model

Deliverable

Deliverable F2: An automated territorial analysis pipeline on a real site: covering database management, geoprocessing scripts, map visualization and combination with environmental and social variables, data visualization and export options. An AI-generated interpretive report that integrates all the analysis in a coherent way, includes secondary data display (charts, diagram) together with resulting maps.
Sources correctly chosen in relation to their use in the analysis, then queried and credited.
Analysis pipeline is reproducible on another site. The project works with raster and vector data and addresses environmental, social and regulatory)economic topics in the analysis.
Report reads as interpretation, not description.
Context model usable in design.
Analysis pipeline is reproducible on another site. The project works with rastrr and vector data and adresses environmental, social and regulatory)economic topics in the analysis.

Faculty and resources

Module Faculty

Learn this in MIAWS

This module is part of the 18-week postgraduate program. Work with your own real project from week 1. First cohort February 2027.

Talk to MIAWS AI →