View Proposal

---

Proposer

Phil Bartie

Title

GeoAI - LLM and Maps

Goal

Description

The aim of this project is to build a system which combines a natural language interface (text/spoken/map) with searching spatial datasets. It should allow the user to ask questions which can be answered via text and mapped (eg highlight results on the map, zoom+pan the map) This consists of 4 stages: Stage 1 - load spatial datasets into a suitable data management system Stage 2 - build a UI to support querying the data (eg text, speech, map GUI) Stage 3 - develop an ontology to link space to activities (idea of 'place') (eg suitable places to walk include paths, parks, beaches, etc). Stage 4 - add functions to process the data to answer more complex questioins (eg find the closest point on River A to Road B; how many post boxes in Edinburgh, etc) It would be preferred to use open/free tools rather than Google Map API etc. Suggested Tools / Data: Python - eg Geopandas PostgreSQL + PostGIS - spatial data storage and analysis QGIS - map editing OpenStreetMap / Overture Maps Ordnance Survey Data via Digimap (EDINA) Wordnet / ConceptNet / DBPedia -- to help develop an action +place ontology LM Studio / Ollama + LLM Or OpenAI API (costed) Leaflet.js / OpenLayers.js / Leafmap (Python) / Folium (Python) WhisperAI - for speech input ASR

Resources

Background

Url

Difficulty Level

High

Ethical Approval

None

Number Of Students

1

Supervisor

Phil Bartie

Keywords

Degrees

Bachelor of Science in Computer Science
Bachelor of Science in Computer Systems
Master of Engineering in Software Engineering
Master of Science in Artificial Intelligence
Master of Science in Data Science