|Paper title||UrbAIn – Developing Digital Twin Solutions Linking EO and Sensors to Improve Urban Living|
|Form of presentation||Poster|
At the heart of the UrbAIn project is the integration of different types of data in order to develop novel Digital Twin services that can be integrated into the daily functions of urban living: for both public authorities as well as citizens. Urban planning today is subject to numerous challenges including changes in demographics, urban-rural migration, rapid urbanisation, limited space, traffic, environmental degradation, pollution, and climate changes are only some of the aspects that influence the planning and development of the future city. By creating digital data that can be visualized in virtual environments and supported by modeling tools make it possible to support these processes and create digital twins that are not only synchronized with the real world but can be used to test alternate futures based on choosing different scenarios. Earth observations (EO) can provide important foundations for urban planning both on the ground and in the atmosphere.
The digital twin is a virtual construct of a city in digital space that can be visualized and manipulated. In order to achieve this however, the associated real world information and infrastructure must be available in the form of digital maps or models combined with dynamic real-time data generated by sensors across the city. This enables users to quickly record and evaluate current situations, as well as simulate future measures and test their effects. Due to the heterogeneous, complex data and the large amounts of data, artificial intelligence (AI) algorithms are an important prerequisite for the implementation of digital urban twins. The first "AI revolution" also offers options for remote sensing in order to fully exploit the potential of the rapidly growing amounts of data. For the valorization of spatial, temporal and spectral properties of the remote sensing data, AI algorithms are particularly powerful, because they offer the possibility of a largely automated and scalable data evaluation, which is necessary in the age of big EO data. The prerequisites for this are extensive training data, development environments and cloud computing.
In the UrbAIn Project, supported through a grant from the German Federal Ministry for Economic Affairs and Energy, new EO and AI processes for evaluating, merging and displaying various data in the context of Digital Twins are being developed in order to make cities more livable and sustainable. Specifically, we will showcase our latest results related to the methods for the acquisition, processing and reproduction of spatial data in a public context, taking into account AI techniques and state of the art environmental sensors.