In the Geo-Intelligence group, advanced methods and tools for semi-automatic sensor data-based production of geotypical, geospecific and photorealistic simulation data are researched and developed. The group develops multispectral simulations and appropriate vision system simulation modules. The core competence of the Geo-Intelligence group includes the provision of methods and procedures to generate fused source data from 3D data of various characteristics and origins - such as 3D data derived photogrammetrically from image and video data, results of laser scans, or conserved geodata from geographic information systems (GIS) - to support multispectral simulations with high realism and environmental detail. With the help of simulation, in addition to products of 3D reconstruction, land use classification, etc., the issue of automated decision-making is increasingly coming to the fore. A digital representation of real objects, a so-called digital twin, can provide numerical results for both real and imaginary scenarios. From a multitude of configurations, the best ones are selected and made available to a human decision maker.