Sen1Floods11: A Georeferenced Dataset to Train and Test Deep Learning Flood Algorithms for Sentinel-1

Derrick Bonafilia, Beth Tellman, Tyler Anderson, Erica Issenberg; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 210-211

Accurate flood mapping at global scales can support disaster relief and recovery efforts. Improving flood relief with more accurate data is of great importance due to expected increases in the frequency and magnitude of flood events with climatic and demographic changes. To assist efforts to operationalize deep learning algorithms for flood mapping at global scales, we introduce Sen1Floods11, a surface water data set including classified permanent water, flood water, and raw Sentinel-1 imagery. This dataset consists of 4,831 512x512 chips covering 120,406 km\textsuperscript 2 and spans all 14 biomes, 357 ecoregions, and 6 continents of the world across 11 flood events. We used Sen1Floods11 to train, validate, and test fully convolutional neural networks (FCNN) to segment permanent and flood water. We compare results of classifying permanent, flood, and total surface water from training four FCNN models: i) 446 hand labeled chips of surface water from flood events; ii) 814 chips of publicly available permanent water data labels from Landsat (JRC surface water dataset); iii) 4385 chips of surface water classified from Sentinel-2 images from flood events and iv) 4385 chips of surface water classified from Sentinel-1 imagery from flood events. We compare these four models to a common remote sensing approach of thresholding radar backscatter to identify surface water. Future research to operationalize computer vision approaches to mapping flood and surface water could build new models from Sen1Floods11 and expand this dataset to include additional sensors and flood events. We provide Sen1Floods11, as well as our training and evaluation code at: https://github.com/cloudtostreet/Sen1Floods11