Unsupervised Floodwater Depth Estimation

Estimates standing urban floodwater depth by coupling post-event aerial imagery with DTMs

We introduce a fully unsupervised framework that accurately estimates standing urban floodwater depth by coupling post-event aerial imagery with DTMs, completely eliminating the need for labeled training data. Extensive validation across twelve heterogeneous catchments demonstrated robust regional spatial generalization.

This code is a simple (not speed optimized) implementation of Floodwater Depth Estimation method proposed in [1].

Files:

getUFloodDet_Depth.m: function that implements Flood Detection method [1,2]

calculate_floodwater_depth.m: function that implements Floodwater Depth Estimation method [1]

runFloodwaterDepthEstimation.m: script of implemetation of the Floodwater Depth Estimation method [1]

You can find more details in

https://sites.google.com/site/costaspanagiotakis/research/flood-detection

We will appreciate if you cite our papers in your work:

[1] G. Simantiris, K. Bacharidis, and C. Panagiotakis, Unsupervised Estimation of Post-Event Standing Urban Floodwater Depth Using Aerial Imagery and Digital Terrain Models, Remote Sensing, 18(16), 2673, 2026.

[2] G. Simantiris and C. Panagiotakis, Unsupervised Color Based Flood Segmentation in UAV imagery, Remote Sensing, 16 (12), 2126, 2024.