Our research combines data science, Geographic Information Systems (GIS), remote sensing, machine learning, software development and optimisation to analyse sustainability systems across space and time.
The aim is to create more detailed, scalable and decision-relevant assessments, and to translate methods into digital workflows and tools that can be used in research and practice.
Digital Twins and Dynamic System Models
We develop digital representations of material and energy systems that connect stocks, flows, technologies and environmental impacts.
These models help analyse how systems evolve over time, explore future scenarios and assess how changes in technology, infrastructure or resource use may influence environmental performance.
Spatiotemporal Sustainability Assessment
Location and timing can strongly influence sustainability outcomes.
We combine GIS, remote sensing and spatial data with life cycle and material-flow methods to analyse where resources and impacts occur, how systems develop, and when future material or infrastructure changes may take place.
Environmental Data Engineering, AI and Digital Tools
Environmental assessment often depends on fragmented and heterogeneous information.
We develop methods for data integration, automated information extraction, machine learning and software-based analysis. The focus is on creating structured and traceable data, improving analytical workflows and developing reusable digital tools.
Decision Support and Optimisation
We connect sustainability assessment with scenario analysis, spatial optimisation and decision-support methods.
These approaches help compare alternatives under practical constraints such as transport, infrastructure capacity, resource availability and uncertainty, providing a transparent basis for planning and implementation.