Crowdsourced-based Deep Convolutional Networks for Urban Flood Depth Mapping

TL;DR

This paper presents a deep convolutional network that analyzes crowdsourced images to produce real-time, high-resolution flood depth maps, aiding flood recovery and evacuation efforts.

Contribution

It introduces a novel approach using crowdsourced images and deep learning for accurate, real-time flood depth mapping in urban areas.

Findings

Mean absolute error of 6.978 inches in flood depth estimation

Applicable to low-cost, real-time flood risk mapping

Validated on recent floods in the U.S. and Canada

Abstract

Successful flood recovery and evacuation require access to reliable flood depth information. Most existing flood mapping tools do not provide real-time flood maps of inundated streets in and around residential areas. In this paper, a deep convolutional network is used to determine flood depth with high spatial resolution by analyzing crowdsourced images of submerged traffic signs. Testing the model on photos from a recent flood in the U.S. and Canada yields a mean absolute error of 6.978 in., which is on par with previous studies, thus demonstrating the applicability of this approach to low-cost, accurate, and real-time flood risk mapping.