GeMMA Lab is one of the leaders in the region for geospatial modeling solutions, where all state-of-the-art GeMMA algorithms and solutions are being integrated into GeMMA Fusion Suite (GFS), an advanced geospatial software SDK designed and optimized for mapping of geospatial objects from heterogeneous sensory data streams and remote sensing data sources, such as ortophoto, LiDAR, DTM and satellite imagery. GFS core consists of optimized readers and writers for standard data formats that allow for efficient asynchronous data operations and large-scale processing. Initiated by a growing number of studies conducted by GeMMA Lab with its industrial partners, GFS analytic engine is being constantly enriched by advanced data fusion methodologies and new location-intelligence algorithms within ongoing and successfully completed R&D projects, such as:

• Integration and data fusion of heterogeneous geospatial data sources (PrAEctiCe, Green.DAT.AI, ELES, DARS)
• Advanced map editing tools for vector/raster data and visualization in 2D and 3D (PrAEctiCe, ELES)
• Predefined AI models for classification, object recognition, and semantic segmentation (PrAEctiCe, Green.DAT.AI, ELES, DARS)
• Real-time AI support for video streams and IoT data streams (DARS, MORS)
• Federated AI Support for federated learning of GeoAI models (Green.DAT.AI)
• Fog AI support for distributed GeoAI models over edge devices
• Environmental simulations such as renewable energy potentials (SAMPA)

GeMMA Lab is specializing in the development of new data compression paradigm (through projects like COMPROMISE and SYMMETRY that is based on the investigation of advanced prediction methods with incorporation of features and restoration methods. Furthermore, the developed data compression methodology is supposed to be largely domain independent and asymmetric.

GeMMA also supports advanced pipeline for creating virtual worlds as environments for interactive digital storytelling through augmented reality, virtual reality, and holographic applications (through projects like MAHEPA). Automatic approaches are developed for this purpose, including the generation of 3D models from LiDAR data, together with advanced storage and organization of 3D content, thus providing a holistic overview on information management within digital storytelling.