Foundation Digital Twin Auto Feature Extraction (FDT AFE)

The National Geospatial-Intelligence Agency (NGA) is seeking information on acquiring an innovative solution to automate the identification, extraction, and attribution of geospatial features. The Automated Feature Extraction (AFE) capability will be a critical enabler for modernizing FG processes and will be provided as a service, accessible by key NGA systems, including FDT, via APIs. Key features of the AFE capability include: * Automatically detecting and extracting geospatial features from various sources, including imagery and raster maps * Attributing extracted features based on observable characteristics in accordance with NGA domain standards * Preserving feature geometry, spatial relationships, and metadata from the source data * Providing confidence metrics to guide and prioritize data validation * Utilizing standardized data formats, such as GeoDatabase (GDB), Shapefile, and TDS 7.1, to ensure compatibility with NGA systems * Implementing robust access controls based on user roles and clearances The NGA envisions this initiative to leverage the use of artificial intelligence and machine learning (AI/ML) to transform geospatial intelligence production, significantly reducing manual processing time, increasing data accuracy, and enabling the rapid delivery of intelligence to decision-makers. • The AFE capability should be able to handle individual and batch processing with varying levels of feature detail over multiple geographical areas of interest • The solution should be capable of monoscopic and/or stereoscopic feature extraction • The solution should be able to support multiple file formats, including EO, SAR, HS, and MS, and raster maps • The solution should provide a user interface for analysts to efficiently review, validate, and correct extracted features • The solution should be fully compliant with all applicable security directives, including DNI ICD 503, and implement robust access controls based on user roles and clearances