In the age of big data, geographic information has become a central means for data scientists of various disciplines to embed their analysis into a spatio-temporal context, from human mobility patterns and social inequality to the investigation of personal health. However, as the variety of data sources and software available on the web increases, it becomes more and more impossible to comprehend and utilize all tools and data available to answer geo-analytical questions. Hence, whenever a functionality is needed but not available in one tool, analysts are forced to reformulate their questions in terms of technicalities of another tool or other datasets. This procedure does not scale with the increasing variety of geo-analytic sources on the web, preventing analysts from tapping its full potential. Consider, in contrast, how easy it is for a user of a digital smartphone assistant such as Amazon’s Alexa to ask a question like 'What is the weather today?' and receive a response from the web. It would mean a tremendous breakthrough if analysts could similarly ask questions in order to get the tools and data required to answer them. Unfortunately, geo-analytic technology currently cannot handle questions.
To realize this vision, it is necessary to understand how geo-analytic resources can be captured with the questions they answer. The QuAnGIS project, a 5-year research project at the University of Utrecht that started in January 2019 funded by the European Research Commission (ERC), develops a theory about interrogative spatial concepts needed to turn geo-analytical questions into machine-readable workflows using Semantic Web, Workflow synthesis and Question-Answering (QA) technology. The focus is on 'core concepts of spatial information', field, object, network, event (Kuhn 2012), and related analytical concepts such as accessibility, exposure, density, distance and aggregation. Based on these concepts, questions can be matched with the capacity of major analytical GIS tools and data sources on the web.
QuAnGIS is highly interdisciplinary at the intersection of Human Geography, GIScience, GIS, Information Science, Semantic Web (ontologies), Computational Linguistics and Ontologies. It involves both empirical and computational studies as well as formal/ontological design. The theoretical outcomes of this research will be implemented in a working QA system. Hence, software engineering and development are also relevant to this project. Following the interdisciplinary nature of the project, collaboration with outside investigators is a noticeable part of the project. Current collaborations include investigators from Eindhoven University of Technology (Netherlands), the University of California, Santa Barbara (USA), and the University of Melbourne (Australia).
The new PhD position in this project should focus on the information theory and technology needed to enable GIS analysts to translate (1) geographic questions into analytic workflows and (2) to retrieve corresponding resources for analysis. The main research question is: How can the analytic potential of geo-analytical resources (data and tools) be described in terms of potential workflows and be linked to the questions they answer? This involves an investigation into GIS tools and their functionality in terms of semantic concepts, as well as standard web data sources, and how both can be linked. Furthermore, it involves developing a transformation language that can be used to search over GIS workflows using question concepts. Both will be a basis for building an integrated extensible web repository about analytical tools and data sources that can be queried using questions.
Tasks of the PhD-student consist of (but are not limited to):
- conducting scientific research in the fields of Geospatial Semantics, Geographic Information Science, Ontology Engineering, and Semantic Web relevant to handling spatial questions and analytic resources;
- the collection and semantic description of GIS scenarios for developing a gold standard of questions and workflows. In particular, describing analytic (web) resources for geospatial analysis (tools and data) in a semantic database (MarkLogic);
- the development of workflow synthesis technology and a transformation language for matching questions with workflows composed from resources;
- helping perform user studies for testing the tool/data repository with geospatial analysts;
- publishing results in scientific journals and presentation in high-quality international conferences in these fields;
- collaboration with outside investigators in joint studies;
- organizing multi-stakeholder meetings and workshops to test and discuss the technology;
- developing teaching skills, students are expected to contribute to the teaching programme of the Department of Human Geography and Spatial Planning to a limited degree (up to 10%). It may also involve the supervision of Master projects.
Your responsibilities:
- start the project preferably in May or later in 2020 upon negotiations;
- meet the goals/deadlines as set out in the project proposal;
- complete a PhD thesis within the 4-year contract period.
The project team is part of a new Geographic Information Methods (GIM) interest group within the Social Urban Transitions (SUT) research programme in the Department of Human Geography and Spatial Planning, Faculty of Geosciences, Utrecht University. It is linked to the Healthy Urban Living research group comprising a wide variety of researchers, for instance with backgrounds in transport geography, epidemiology, urban geography, and health sciences. It is also linked to the Vitality Data Centre, a project involving data scientists and researchers interested in methods for assessing physical activity and health. Currently, the core research team consists of the principal investigator (supervisor), a postdoc, and a PhD student.