Quantifying urban flood extent using satellite imagery and machine learning

Abstract

The risk of oods from tropical storms is increasing due to climate change and human development.Maps of past ood extents can aid in planning and mitigation efforts to decrease ood risk. In 2021, Hurricane Ida slowed over the Mid-Atlantic and Northeast United States and released unprecedented rainfall. Satellite imagery and the Random Forest algorithm are a reliable combination to map ood extents. However, this combination is not usually applied to urban areas. We used Sentinel-2 imagery (10 m), along with derived indices, elevation, and land cover data, as inputs to a Random Forest model to make a new ood extent for southeastern Pennsylvania. The model was trained and validated with a dataset created with input from PlanetScope imagery (3 m) and social media posts related to the ood event. The overall accuracy of the model is 99%, and the ood class had a user's and producer's accuracy each over 99%. We then compared the ood extent to the Federal Emergency Management Agency (FEMA) ood zones at the county and tract level and found that more ooding occurred in the Minimal Hazard zone than in the 500-year ood zone. Our Random Forest model relies on publicly available data and software to e ciently and accurately make a ood extent map that can be deployed to other urban areas. Flood extent maps like the one developed here can help decision-makers focus efforts on recovery and resilience.