Convolutional Neural Network for Flood-Risk Assessment and Detection within a Metropolitan Area

The extraction of hydrological characteristics from a particular geographical region through remote sensing data processing allows the generation of electronic signature maps, which are the basis to create a high -resolution collection atlas processed in time for a particular geographical zone. The...

Full description

Saved in:
Bibliographic Details
Main Author: Villalon-Turrubiates, Ivan E.
Format: Conference Proceeding
Language:English
Subjects:
Convolutional neural networks
Data mining
Data processing
Deep learning
Hazards
Image resolution
Urban areas
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The extraction of hydrological characteristics from a particular geographical region through remote sensing data processing allows the generation of electronic signature maps, which are the basis to create a high -resolution collection atlas processed in time for a particular geographical zone. The use of remote sensing technologies combined with deep learning techniques offers an opportunity for flood-risk assessment and detection using the signature maps applied to a metropolitan area within an image. This can be achieved using a multispectral image classification approach based on convolutional neural networks, this is referred to as the Convolutional Flood Assessment method. This paper presents the prospective study for flood-risk assessment and detection using multispectral remote sensing data provided by SPOT-5 imagery and applied to a particular metropolitan area. The results provided probe the efficiency of the developed technique for applications in detection of natural hazards.
ISSN:2153-7003
DOI:10.1109/IGARSS47720.2021.9553808