Learning Outcomes:
On successful completion of the module the student will have:
- Theoretical and practical mastery of advanced GIS concepts, spatial problem framing, and data governance;
- Advanced working competence in ArcGIS Pro (project/data design, geodatabases, metadata, editor tracking);
- Ability to design robust attribute schemas using domains, subtypes, contingent values, defaults, and data dictionaries;
- Ability to validate and standardise attributes at scale using Attribute Rules (calculation/constraint/validation), batch validation, and field calculations (Arcade/Python);
- Ability to apply advanced machine learning and deep learning tools on spatial decision making and solving real world problems.
- Ability to apply spatial statistics and space–time analysis (e.g., Moran’s I, Gi*, space-time cube, emerging hot spots) and report diagnostics clearly;
- Ability to automate geospatial workflows with ModelBuilder and ArcPy/ArcGIS Notebooks, package tools, and manage versions for reproducibility; and
- Ability for critical, ethical, and self-directed learning—communicating limitations, geoprivacy/licensing considerations, and decision-ready insights to technical and non-technical audiences.
Indicative Module Content:
Spatial data acquisition and quality control at scale: Ingest from portals/APIs; using hosted feature layer views for safe sharing.
Spatial data management: Schema, attribute rules, filters & queries.
Advanced vector analysis: Site suitability analysis, spatio-temporal data mining, data engineering.
Spatial statistics & pattern mining: Spatial regression, global and local level auto-correlation (Global and Local Moran's I), clustering/hotspots (Getis-Ord Gi*), space time pattern mining, and the space-time cube.
Raster modeling for suitability & pathways: Raster data management; map algebra patterns; cost distance & least-cost paths; multi-criteria decision analysis (AHP); documenting uncertainty.
Image Classification using Machine Learning: Supervised image classification using ML models.
3D GIS & scenes for the web: Working with LiDAR data for 3D building storytelling
working with Deep Learning models: Tree detection using high-resolution aerial data and DL models.
Spatial Automation I: Introduction to ArcPy and ArcGIS Python for automating spatial task. Working with ArcGIS Notebook.
Spatial Automation II: ModelBuilder patterns & best practice - Designing robust, reusable models—parameters, pre/post-conditions, iterators, validation; packaging/sharing; logging.
Cartography and professional-level map making: Visual variables, typography, label engines; color-vision accessibility; uncertainty & bivariate mapping; vector tiles (benefits, styling, performance)