funded by following partners
Dense and Deep Geographic Virtual Knowledge Graphs for Visual Analysis
Total Duration: 1 doctoral candidate for 3 years
The DFG project has the goal to effectively integrate and analyze heterogeneous geodata sources by bridging two research fields – Virtual Knowledge Graphs (VKG) and Geovisual Analytics. In the project we will develop on the one hand a set of methodologies and software tools to create densely and deeply linked geospatial knowledge graphs, and on the other hand a set of intuitive visualizations and explainable analytical services over them. The project will provide a complete solution covering the whole life-cycle from the construction and enrichment of GeoVKGs, to their visualization and analysis over them. The developed methodology and software tools will be demonstrated in two real-world use cases. The first one demonstrates climate change in Bavaria, while the second one deals with tourism and mobility data in South Tyrol, managed by NOI Techpark in Bolzano. Although the two use cases have different characteristics, they both represent common and intricate cases of geodata management, and thus require the ability to effectively combine the underlying datasets and to perform complex analytical tasks over them.
OpenStreetMap Boosting using Simulation-Based Remote Sensing Data Fusion - OSMSim
Total Duration: 2 doctoral candidates for 3 years
This DFG project aims to improve building information in OpenStreetMap (OSM) using a simulation-based fusion of heterogeneous remote sensing data and the updated OSM data for follow-up applications. The simulation environment SimGeoI provides the starting point. It is used to compare geometric OSM information with remote sensing data produced under different sensor configurations and at different acquisition times, and to enrich OSM with geometric corrections (position, height) and attributes (e.g. building type, roof structure) gained from a fusion of the different remote sensing data. Three core themes are addressed: First, a methodical framework will be developed, which allows the geometric correction of OpenStreetMap data based on the prediction and comparison of building shapes, using a pair of remote sensing images (optical, SAR or mixed). In a second step, geometrically improved OSM information will be used to extract building-related attributes from multi-modal remote sensing data. Finally, the transferability of the developed methods will be experimentally analyzed and interfaces to follow-up applications will be investigated. The methodology will be accompanied by validation in order to evaluate the positional, thematic and temporal accuracy of derived results.
Guided Unlearning of Cognitive Pitfalls in Georeferenced Social Sensing
Total Duration: 1 postdoc researcher or 1 doctoral candidate for three years
This DFG project addresses bias-induced cognitive pitfalls in social sensing. For selected application scenarios, an interactive platform for guided unlearning of cognitive biases will be developed and prototypically implemented. Unlearning is a radical method of learning. Unlike conventional learning or knowledge accumulation, which is based on the addition of what is new to the learner, an unlearning process is based on the conscious subtraction of something undesirable that already exists, either innately or learned. The project has three objectives: to improve the transparency with regard to the value chain of georeferenced social sensing; to support users’ holistic understanding of cognitive biases in georeferenced social sensing; and to assess users’ capacity of critical reasoning after the training of guided unlearning. A number of guided unlearning experiments will be designed and implemented with biased data for selected real-world scenarios. We will collect preliminary findings and/or raise new questions, relying on two kinds of comparison: between untrained user solutions and benchmark solutions, and between untrained and trained user solutions.