Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco
Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution re...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/16/5/858 |
_version_ | 1797263955398230016 |
---|---|
author | Sliman Hitouri Meriame Mohajane Meriam Lahsaini Sk Ajim Ali Tadesual Asamin Setargie Gaurav Tripathi Paola D’Antonio Suraj Kumar Singh Antonietta Varasano |
author_facet | Sliman Hitouri Meriame Mohajane Meriam Lahsaini Sk Ajim Ali Tadesual Asamin Setargie Gaurav Tripathi Paola D’Antonio Suraj Kumar Singh Antonietta Varasano |
author_sort | Sliman Hitouri |
collection | DOAJ |
description | Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments. |
first_indexed | 2024-04-25T00:21:14Z |
format | Article |
id | doaj.art-80383e1311084c37b656dcad15276f41 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-04-25T00:21:14Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-80383e1311084c37b656dcad15276f412024-03-12T16:54:15ZengMDPI AGRemote Sensing2072-42922024-02-0116585810.3390/rs16050858Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern MoroccoSliman Hitouri0Meriame Mohajane1Meriam Lahsaini2Sk Ajim Ali3Tadesual Asamin Setargie4Gaurav Tripathi5Paola D’Antonio6Suraj Kumar Singh7Antonietta Varasano8Geosciences Laboratory, Department of Geology, Faculty of Sciences, University Ibn Tofail, Kenitra 14000, MoroccoConstruction Technologies Institute, National Research Council (CNR), Polo Tecnologico di San Giovanni a Teduccio, 80146 Napoli, ItalyInstitute of Geosciences and Earth Resources (IGG), National Research Council (CNR), Via Moruzzi 1, 56126 Pisa, ItalyDepartment of Geography, Faculty of Science, Aligarh Muslim University (AMU), Aligarh 202002, Uttar Pradesh, IndiaFaculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar P.O. Box 26, EthiopiaCentre for Climate Change and Water Research, Suresh Gyan Vihar University, Jaipur 302017, Rajasthan, IndiaSchool of Agricultural, Forestry, Environmental and Food Sciences, University of Basilicata, 85100 Potenza, ItalyCentre for Climate Change and Water Research, Suresh Gyan Vihar University, Jaipur 302017, Rajasthan, IndiaITC-CNR, Construction Technologies Institute, National Research Council (CNR), 70124 Bari, ItalyFlood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments.https://www.mdpi.com/2072-4292/16/5/858flood susceptibilityradar imagerandom forestCARTSVMXGBoost |
spellingShingle | Sliman Hitouri Meriame Mohajane Meriam Lahsaini Sk Ajim Ali Tadesual Asamin Setargie Gaurav Tripathi Paola D’Antonio Suraj Kumar Singh Antonietta Varasano Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco Remote Sensing flood susceptibility radar image random forest CART SVM XGBoost |
title | Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco |
title_full | Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco |
title_fullStr | Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco |
title_full_unstemmed | Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco |
title_short | Flood Susceptibility Mapping Using SAR Data and Machine Learning Algorithms in a Small Watershed in Northwestern Morocco |
title_sort | flood susceptibility mapping using sar data and machine learning algorithms in a small watershed in northwestern morocco |
topic | flood susceptibility radar image random forest CART SVM XGBoost |
url | https://www.mdpi.com/2072-4292/16/5/858 |
work_keys_str_mv | AT slimanhitouri floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT meriamemohajane floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT meriamlahsaini floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT skajimali floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT tadesualasaminsetargie floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT gauravtripathi floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT paoladantonio floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT surajkumarsingh floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco AT antoniettavarasano floodsusceptibilitymappingusingsardataandmachinelearningalgorithmsinasmallwatershedinnorthwesternmorocco |