Flood Damage Assessment Geospatial Application Using Geoinformatics and Deep Learning Classification

Dublin Core

Title

Flood Damage Assessment Geospatial Application Using Geoinformatics and Deep Learning Classification

Subject

Flood damage assessment
Geoinformatics
Deep Learning Classification

Description

The data of impacts and damage caused by floods is necessary for manipulation to assist and relieve those impacts in each area. The main issue for data acquisition was acquisition methods that affect the durations, accuracy, and completeness of data obtained. Most data are currently obtained by field survey for data on impacts in each area. However, this method contains limitations, i.e., taking a long time, high cost, and no real-time data visualization. Thus, this research presented the study to develop an application for inspecting areas under impact and damage caused by floods using deep learning classification for flood classification and land use type classification in the affected areas using digital images, remote sensing data, and crowdsource data notified by users through the accuracy assessment application of classification. It was found that deep learning classification for flood classification had 97.50% accuracy, with Kappa = 0.95. Land use type classification had 93.71% accuracy, with Kappa = 0.91. Flood damage assessment process in this research was different from other previous research that used geospatial data for flood damage inspection, e.g., satellite images. In contrast, this research brought damage data notified by users for processing with flood data in each area by satellite image processing and land use types of classification. The proposed application can calculate damage in each area and visualize real-time results in maps and graphs on the dashboard via the application. Besides, the presented method can be used to verify and visualize data of areas under impact and damage caused by floods in different areas.

Creator

Puttinaovarat, Supattra
Saeliw, Aekarat
Pruitikanee, Siwipa
Kongcharoen, Jinda
Chai-Arayalert, Supaporn
Khaimook, Kanit

Source

International Journal of Interactive Mobile Technologies (iJIM); Vol. 16 No. 21 (2022); pp. 71-97
1865-7923

Publisher

International Association of Online Engineering (IAOE), Vienna, Austria

Date

2022-11-15

Rights

Copyright (c) 2022 Assoc.Prof.Dr.Supattra Puttinaovarat, Aekarat Saeliw, Siwipa Pruitikanee, Asst.Prof.Dr.Jinda Kongcharoen, Asst.Prof.Dr.Supaporn Chai-Arayalert, Assoc.Prof.Dr.Kanit Khaimook
https://creativecommons.org/licenses/by/4.0

Relation

Format

application/pdf

Language

eng

Type

info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article

Identifier

Citation

Supattra Puttinaovarat et al., Flood Damage Assessment Geospatial Application Using Geoinformatics and Deep Learning Classification, International Association of Online Engineering (IAOE), Vienna, Austria, 2022, accessed November 5, 2024, https://igi.indrastra.com/items/show/2388

Social Bookmarking