Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach

Flooding is one of the most severe natural hazards, causing widespread environmental, economic, and social disruption. If not managed properly, it can lead to human losses, property damage, and the destruction of livelihoods. The ability to rapidly assess such damages is crucial for emergency manage...

Full description

Saved in:
Bibliographic Details
Main Authors: Hadi Farhadi, Hamid Ebadi, Abbas Kiani, Ali Asgary
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4454
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060324624924672
author Hadi Farhadi
Hamid Ebadi
Abbas Kiani
Ali Asgary
author_facet Hadi Farhadi
Hamid Ebadi
Abbas Kiani
Ali Asgary
author_sort Hadi Farhadi
collection DOAJ
description Flooding is one of the most severe natural hazards, causing widespread environmental, economic, and social disruption. If not managed properly, it can lead to human losses, property damage, and the destruction of livelihoods. The ability to rapidly assess such damages is crucial for emergency management. Near Real-Time (NRT) spatial information on flood-affected areas, obtained via remote sensing, is essential for disaster response, relief, urban and industrial reconstruction, insurance services, and damage assessment. Numerous flood mapping methods have been proposed, each with distinct strengths and limitations. Among the most widely used are machine learning algorithms and spectral indices, though these methods often face challenges, particularly in threshold selection for spectral indices and the sampling process for supervised classification. This study aims to develop an NRT flood mapping approach using supervised classification based on spectral features. The method automatically generates training samples through masks derived from spectral indices. More specifically, this study uses FWEI, NDVI, NDBI, and BSI indices to extract training samples for water/flood, vegetation, built-up areas, and soil, respectively. The Otsu thresholding technique is applied to create the spectral masks. Land cover classification is then performed using the Random Forest algorithm with the automatically generated training samples. The final flood map is obtained by subtracting the pre-flood water class from the post-flood image. The proposed method is implemented using optical satellite images from Sentinel-2, Landsat-8, and Landsat-9. The proposed method’s accuracy is rigorously evaluated and compared with those obtained from spectral indices and machine learning techniques. The suggested approach achieves the highest overall accuracy (OA) of 90.57% and a Kappa Coefficient (KC) of 0.89, surpassing SVM (OA: 90.04%, KC: 0.88), Decision Trees (OA: 88.64%, KC: 0.87), and spectral indices like AWEI (OA: 84.12%, KC: 0.82), FWEI (OA: 88.23%, KC: 0.86), NDWI (OA: 85.78%, KC: 0.84), and MNDWI (OA: 87.67%, KC: 0.85). These results underscore the superior accuracy and effectiveness of the proposed approach for NRT flood detection and monitoring using multi-sensor optical imagery.
format Article
id doaj-art-1acfe3d232594cfeadf3784950cd6fd6
institution DOAJ
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-1acfe3d232594cfeadf3784950cd6fd62025-08-20T02:50:36ZengMDPI AGRemote Sensing2072-42922024-11-011623445410.3390/rs16234454Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification ApproachHadi Farhadi0Hamid Ebadi1Abbas Kiani2Ali Asgary3Faculty of Geodesy and Geomatics Engineering, K.N Toosi University of Technology, Tehran 15418-49611, IranFaculty of Geodesy and Geomatics Engineering, K.N Toosi University of Technology, Tehran 15418-49611, IranFaculty of Civil Engineering, Babol Noshirvani University of Technology, Babol 47148-71167, IranFaculty of Liberal Arts and Professional Studies, York University, North York, ON M3J1P3, CanadaFlooding is one of the most severe natural hazards, causing widespread environmental, economic, and social disruption. If not managed properly, it can lead to human losses, property damage, and the destruction of livelihoods. The ability to rapidly assess such damages is crucial for emergency management. Near Real-Time (NRT) spatial information on flood-affected areas, obtained via remote sensing, is essential for disaster response, relief, urban and industrial reconstruction, insurance services, and damage assessment. Numerous flood mapping methods have been proposed, each with distinct strengths and limitations. Among the most widely used are machine learning algorithms and spectral indices, though these methods often face challenges, particularly in threshold selection for spectral indices and the sampling process for supervised classification. This study aims to develop an NRT flood mapping approach using supervised classification based on spectral features. The method automatically generates training samples through masks derived from spectral indices. More specifically, this study uses FWEI, NDVI, NDBI, and BSI indices to extract training samples for water/flood, vegetation, built-up areas, and soil, respectively. The Otsu thresholding technique is applied to create the spectral masks. Land cover classification is then performed using the Random Forest algorithm with the automatically generated training samples. The final flood map is obtained by subtracting the pre-flood water class from the post-flood image. The proposed method is implemented using optical satellite images from Sentinel-2, Landsat-8, and Landsat-9. The proposed method’s accuracy is rigorously evaluated and compared with those obtained from spectral indices and machine learning techniques. The suggested approach achieves the highest overall accuracy (OA) of 90.57% and a Kappa Coefficient (KC) of 0.89, surpassing SVM (OA: 90.04%, KC: 0.88), Decision Trees (OA: 88.64%, KC: 0.87), and spectral indices like AWEI (OA: 84.12%, KC: 0.82), FWEI (OA: 88.23%, KC: 0.86), NDWI (OA: 85.78%, KC: 0.84), and MNDWI (OA: 87.67%, KC: 0.85). These results underscore the superior accuracy and effectiveness of the proposed approach for NRT flood detection and monitoring using multi-sensor optical imagery.https://www.mdpi.com/2072-4292/16/23/4454remote sensingflood mappingmulti-sensor flood detectionclassificationautomatic training
spellingShingle Hadi Farhadi
Hamid Ebadi
Abbas Kiani
Ali Asgary
Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
Remote Sensing
remote sensing
flood mapping
multi-sensor flood detection
classification
automatic training
title Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
title_full Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
title_fullStr Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
title_full_unstemmed Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
title_short Near Real-Time Flood Monitoring Using Multi-Sensor Optical Imagery and Machine Learning by GEE: An Automatic Feature-Based Multi-Class Classification Approach
title_sort near real time flood monitoring using multi sensor optical imagery and machine learning by gee an automatic feature based multi class classification approach
topic remote sensing
flood mapping
multi-sensor flood detection
classification
automatic training
url https://www.mdpi.com/2072-4292/16/23/4454
work_keys_str_mv AT hadifarhadi nearrealtimefloodmonitoringusingmultisensoropticalimageryandmachinelearningbygeeanautomaticfeaturebasedmulticlassclassificationapproach
AT hamidebadi nearrealtimefloodmonitoringusingmultisensoropticalimageryandmachinelearningbygeeanautomaticfeaturebasedmulticlassclassificationapproach
AT abbaskiani nearrealtimefloodmonitoringusingmultisensoropticalimageryandmachinelearningbygeeanautomaticfeaturebasedmulticlassclassificationapproach
AT aliasgary nearrealtimefloodmonitoringusingmultisensoropticalimageryandmachinelearningbygeeanautomaticfeaturebasedmulticlassclassificationapproach