Project Grant 2537872

Iseechange Inc. received a $304,018 Small Business Innovation Research (SBIR) Phase I Project Grant from the National Science Foundation's (NSF) Directorate for Technology, Innovation, and Partnerships (CFDA 47.084) awarded on July 15, 2026, with completion targeted for December 31, 2026. The project delivers a deep learning framework and associated artificial intelligence (AI) computer vision technology that automatically converts unstructured smartphone photographs and videos of flood events into georeferenced flood extent maps in near-real-time. The core technical innovation addresses the critical challenge of automatically identifying stable ground control points and reference features in noisy, unstructured flood imagery—a process historically requiring manual intervention—and matching these features to existing geospatial data to generate precise, location-specific flood maps.

The solution provides emergency responders, city planners, infrastructure managers, utilities, and insurance companies with a scalable, cost-effective service for rapid flood situational awareness and response coordination. By automating image segmentation for flooded areas and developing deep learning models for visual feature detection, the technology enables faster and more accurate flood response decisions that improve emergency management outcomes, save lives, and reduce property damage. This Phase I research focuses on overcoming the primary technical barrier of automating reference feature identification and matching in unstructured flood imagery to establish feasibility and validate the approach for potential commercialization.