Visimo proposes a feasibility study for the development of floodwise, an AI decision-support tool that will enable professionals to effectively prepare, adapt, and respond to flooding events

Floodwise will autonomously scrape and geotag social media images of flooding events to produce flood depth estimation maps in real time. Visimo will create a custom algorithm that will geotag social media images and videos in the absence of exif data. Unlike current models, visimos model will pinpoint image locations with latitude/longitude coordinates, accurate to 20 meters, within narrow regions. Visimo will seek to enhance and refine the custom flood depth estimation algorithm utilized in the blupix flood response APP. The blupix model is not fully automated, and only estimates water depth using stop signs; visimo will expand this algorithm to apply to additional objects and process images containing reflections accurately. Visimos study will determine (1) the ability to autonomously geotag social media data; (2) the expansion and refinement of the blupix flood depth estimation algorithm; and (3) the overall feasibility of the proposed final architecture. Visimo will produce a demonstration that will show, for five locations, the pipelines ability to accurately geotag social media images and videos as new observations for actionable flood intelligence. End users such as federal emergency management agency (FEMA) federal coordinating officers, national guard emergency management officers, emergency management professionals in state and local departments of public safety and emergency management, geospatial information analysis, and geospatial intelligence (geoint) analysts may use visimos tool to (1) respond to flooding in real-time using visimos mobile APP; (2) prepare optimally for future events using historic data saved within the APP to visualize how flooding impacted their region during similar events; and (3) adapt to future flooding events using our tools historic data to inform potential adaptation strategies, such as improving aging water infrastructure, modifying land use, and repairing and retrofitting facilities. Floodwise will include a voice activation feature for hands-free manipulation. Through geotagging social media images and videos, floodwise will create an entirely new data source from previously unusable content. Datasets produced by the tool may also serve as potential sources of input data for physically based water modeling tools and fully coupled earth models to increase the accuracy of water modeling. Visimos custom geotagging model may also be modified and trained for further use cases, including geotagging social media images and videos for disease spread monitoring, urban planning, and natural disaster response and mitigation.