Graph based data analytics and visualization on multi-dimensional settlement characteristics
Objective:
Keywords:
Description:
Motivation:
- Producing analytics on multidimensional settlement characteristics (intensity, size, access) are pre-requisite for evidence-based policy making for spatial sustainability transition where applied geoinformatics and digital visualization can have the major contribution
- Graph base knowledge graph can present the complex topic with enhanced readability and visualization
- Using graph-based data science algorithm (GDS) even can be adapted to explore multi-dimensional parameters
- GDS approaches have the scope of combining with ML/AI workflow
Specific Tasks:
- Conducting a brief literature review to conceptualize on graph-based data science algorithm (GDS) and applications
- Feasibility study in the adoption of GDSA (centrality, similarity, community detection) using Neo4J
- Using an open multi-temporal database on large cities in Germany
- Publish the results in an open web interface – e.g. GeoNode framework
Expected Output:
- Collection of key concepts, methods, tools, and application in focus of adoption of GDS in dealing with settlement-related geodata
- Prototype analytics and visualization applications for exploring settlement characteristics
- A written master thesis
Key Requirements:
- Familiar and interested in spatial science topics among others human settlement systems and built environment
- Knowledge of scripting language SQL, R/Python
- Skills in the English language to researching international literature
Staff involved: Dr. Sujit Sikder (s.sikder@ioer.de)
References:
Graph data science with neo4j: https://neo4j.com/docs/graph-data-science/current
Graph Algorithms: https://neo4j.com/docs/graph-data-science/current/algorithms
Domain(s):
Study Program(s):
- MSc. Cartography (EXCLUSIVELY externally advertised)