Research Group Advanced Environmental Risk and Sustainability Modelling of Cities and Regions Using AI (SITES.AI)

The DRESDEN-concept Research Group ”Advanced Environmental Risk and Sustainability Modelling of Cities and Regions Using AI” (SITES.AI) is a joint initiative of the TUD Dresden University of Technology and the Leibniz Institute of Ecological Urban and Regional Development (IOER) as part of the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), and embedded in the DRESDEN-concept alliance. It strives for fundamental and societally relevant methodological innovations in data-intensive modelling of environmental risks and the sustainability of cities and regions based on the latest and most promising approaches of artificial intelligence (AI) and data analytics. Respective methods have proven to significantly enhance the capabilities of representing systems complexity and dynamics as well as incorporating huge and heterogeneous data sets from different sources and sensors in various fields of the Earth, environmental and spatial sciences.

SITES.AI therefore aims to adopt and further develop AI and Data Analytics approaches for analysing and simulating Earth and societies interlinkages at the scale of cities and regions. The focus is on key methodological challenges of this thematic area and respective advances based on the most recent findings in the fields of computer science in general and geo- and environmental informatics in particular. Furthermore, synergies between individual research activities will allow for a more comprehensive spatiotemporal understanding and modelling of environmental risks and sustainability.

The approach especially addresses (i) spatiotemporal machine learning; (ii) emulations of models; and (iii) explainable AI. The methodologically and thematically interrelated research activities currently refer to the following tasks:

• AI applications for big data coupled model simulations
• Deep learning methods for the creation of coupled models’ emulators
• AI-based geospatial modelling approaches for advanced large-scale urban analytics
• Spatially explicit machine learning and artificial intelligence in the field of land system science and sustainability transformation science