High Resolution Flood Extent Detection Using Deep Learning with Random Forest Derived Training Labels

TL;DR

This paper presents a scalable deep learning framework for flood extent detection using high-resolution optical imagery and topographic data, with training labels generated by a Random Forest model, demonstrated on Hurricane Ida flood data.

Contribution

It introduces a novel method combining ML and DL with label generation from RF models, enabling effective flood mapping with limited labeled data.

Findings

Topographic features provide marginal improvement over optical imagery alone.

U-Net models achieved high accuracy with F1=0.92 and IoU=0.85.

Framework is scalable and effective in data-scarce flood scenarios.

Abstract

Validation of flood models, used to support risk mitigation strategies, remains challenging due to limited observations during extreme events. High-frequency, high-resolution optical imagery (~3 m), such as PlanetScope, offers new opportunities for flood mapping, although applications remain limited by cloud cover and the lack of labeled training data during disasters. To address this, we develop a flood mapping framework that integrates PlanetScope optical imagery with topographic features using machine learning (ML) and deep learning (DL) algorithms. A Random Forest model was applied to expert-annotated flood masks to generate training labels for DL models, U-Net. Two U-Net models with ResNet18 backbone were trained using optical imagery only (4 bands) and optical imagery combined with Height Above Nearest Drainage (HAND) and topographic slope (6 bands). Hurricane Ida (September 2021), which caused catastrophic flooding across the eastern United States, including the New York City metropolitan area, was used as an example to evaluate the framework. Results demonstrate that the U-Net model with topographic features achieved very close performance to the optical-only configuration (F1=0.92 and IoU=0.85 by both modeling scenarios), indicating that HAND and slope provide only marginal value to inundation extent detection. The proposed framework offers a scalable and label-efficient approach for mapping inundation extent that enables modeling under data-scarce flood scenarios.