A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology

Flood is regarded as common disaster which could cause serious devastation in any country. Typically, it is caused due to precipitation & river runoffs, specifically at the time of excessive rainfall season. The technology of sensor network has been used to monitor changes in landcovers and...

Full description

Saved in:
Bibliographic Details
Main Authors: Se-Jung Lim, K. Sakthidasan Sankaran, Anandakumar Haldorai
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10959713/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849313522911019008
author Se-Jung Lim
K. Sakthidasan Sankaran
Anandakumar Haldorai
author_facet Se-Jung Lim
K. Sakthidasan Sankaran
Anandakumar Haldorai
author_sort Se-Jung Lim
collection DOAJ
description Flood is regarded as common disaster which could cause serious devastation in any country. Typically, it is caused due to precipitation &amp; river runoffs, specifically at the time of excessive rainfall season. The technology of sensor network has been used to monitor changes in landcovers and water level fluctuations. Moreover, effective disaster monitoring &amp; notification system in real-time becomes a crucial part which needs to be overcome. For this reason, the proposed methodology is designed aiming at developing natural disaster prediction and monitoring system for alerting that aids in offering right decision at right time. At first, remote sensing image data are collected and preprocessed using Frequency Ratio and Multi-collinearity test (MCT) to ensure noise removal and image augmentation by enhancing their quality. A feature extraction process is carried with the use of Deep Convolution VGGNet-16 from which optimal features are selected using Improved Harris Hawks Optimization algorithm (IHHOA). Then, a Flexible Spatio-temporal image fusion (F-SPTF) approach is employed to fuse images. After this, Deep cascaded RNN classifier is employed for predicting flood occurrence and to map flood susceptibility areas. This, in turn, classifies the normal and abnormal condition of flood occurrence thus giving alerts in case of natural disaster occurrences which could be visualized through digital twin technologies. The suggested scheme offers an accuracy rate of about (99.89%), precision (99.37%), recall (99.82%), and <italic>F</italic>1-score (99.74%). The error rates estimated like RMSE (0.784), MAE (0.764), and MAPE (0.102) also seems to be lower than other existing models compared.
format Article
id doaj-art-e1abe8a7b6f74d038cb409b373a8e493
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-e1abe8a7b6f74d038cb409b373a8e4932025-08-20T03:52:43ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118115471156010.1109/JSTARS.2025.355920510959713A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin TechnologySe-Jung Lim0K. Sakthidasan Sankaran1https://orcid.org/0000-0002-5905-0809Anandakumar Haldorai2School of Electrical and Computer Engineering, Yeosu Campus, Chonnam National University, Yeosu-si, South KoreaDepartment of Electronics and Communication Engineering, Hindustan Institute of Technology and Science, Chennai, IndiaDepartment of Computer Science and Engineering, Sri Eshwar College of Engineering, Coimbatore, IndiaFlood is regarded as common disaster which could cause serious devastation in any country. Typically, it is caused due to precipitation &amp; river runoffs, specifically at the time of excessive rainfall season. The technology of sensor network has been used to monitor changes in landcovers and water level fluctuations. Moreover, effective disaster monitoring &amp; notification system in real-time becomes a crucial part which needs to be overcome. For this reason, the proposed methodology is designed aiming at developing natural disaster prediction and monitoring system for alerting that aids in offering right decision at right time. At first, remote sensing image data are collected and preprocessed using Frequency Ratio and Multi-collinearity test (MCT) to ensure noise removal and image augmentation by enhancing their quality. A feature extraction process is carried with the use of Deep Convolution VGGNet-16 from which optimal features are selected using Improved Harris Hawks Optimization algorithm (IHHOA). Then, a Flexible Spatio-temporal image fusion (F-SPTF) approach is employed to fuse images. After this, Deep cascaded RNN classifier is employed for predicting flood occurrence and to map flood susceptibility areas. This, in turn, classifies the normal and abnormal condition of flood occurrence thus giving alerts in case of natural disaster occurrences which could be visualized through digital twin technologies. The suggested scheme offers an accuracy rate of about (99.89%), precision (99.37%), recall (99.82%), and <italic>F</italic>1-score (99.74%). The error rates estimated like RMSE (0.784), MAE (0.764), and MAPE (0.102) also seems to be lower than other existing models compared.https://ieeexplore.ieee.org/document/10959713/Deep cascaded RNN (DC-RNN)deep convolution VGGNet-16 (DCVGGNet16)flexible-spatiotemporal image fusion (F-SPTF)floodimproved Harris Hawks optimization algorithm (IHHOA)natural disaster
spellingShingle Se-Jung Lim
K. Sakthidasan Sankaran
Anandakumar Haldorai
A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep cascaded RNN (DC-RNN)
deep convolution VGGNet-16 (DCVGGNet16)
flexible-spatiotemporal image fusion (F-SPTF)
flood
improved Harris Hawks optimization algorithm (IHHOA)
natural disaster
title A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
title_full A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
title_fullStr A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
title_full_unstemmed A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
title_short A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology
title_sort framework for flood disaster detection from remote sensing images using spatiotemporal fusion with digital twin technology
topic Deep cascaded RNN (DC-RNN)
deep convolution VGGNet-16 (DCVGGNet16)
flexible-spatiotemporal image fusion (F-SPTF)
flood
improved Harris Hawks optimization algorithm (IHHOA)
natural disaster
url https://ieeexplore.ieee.org/document/10959713/
work_keys_str_mv AT sejunglim aframeworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology
AT ksakthidasansankaran aframeworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology
AT anandakumarhaldorai aframeworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology
AT sejunglim frameworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology
AT ksakthidasansankaran frameworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology
AT anandakumarhaldorai frameworkforflooddisasterdetectionfromremotesensingimagesusingspatiotemporalfusionwithdigitaltwintechnology