Water Resources Management Through Flood Spreading Project Suitability Mapping Using Frequency Ratio, k-nearest Neighbours, and Random Forest Algorithms

Naghibi, SA; Vafakhah, M; Hashemi, H; Pradhan, B; Alavi, SJ

Water Resources Management Through Flood Spreading Project Suitability Mapping Using Frequency Ratio, k-nearest Neighbours, and Random Forest Algorithms

Naghibi, SA Vafakhah, M Hashemi, H Pradhan, B

Alavi, SJ

Permalink

Publisher:: SPRINGER
Publication Type:: Journal Article
Citation:: Natural Resources Research, 2020, 29, (3), pp. 1915-1933
Issue Date:: 2020-06-01

Closed Access

	Filename	Description	Size
	Naghibi2020_Article_WaterResourcesManagementThroug.pdf	Published version	14.09 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Naghibi, SA
dc.contributor.author	Vafakhah, M
dc.contributor.author	Hashemi, H
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054
dc.contributor.author	Alavi, SJ
dc.date.accessioned	2021-04-10T02:04:18Z
dc.date.available	2021-04-10T02:04:18Z
dc.date.issued	2020-06-01
dc.identifier.citation	Natural Resources Research, 2020, 29, (3), pp. 1915-1933
dc.identifier.issn	1520-7439
dc.identifier.issn	1573-8981
dc.identifier.uri	http://hdl.handle.net/10453/147986
dc.description.abstract	Lack of water resources is a common issue in many countries, especially in the Middle East. Flood spreading project (FSP) is an artificial recharge technique, which is generally suggested for arid and semi-arid areas with two major aims including (1) flood mitigation and (2) artificial recharge of groundwater. This study implemented three state-of-the-art popular models including frequency ratio (FR), k-nearest neighbours (KNN), and random forest (RF) for determining the suitability of land for FSP. At the first step, suitable areas for FSP were identified according to the national guidelines and the literature. The identified areas were then verified by multiple field surveys. To produce FSP land suitability maps, several FSP conditioning factors such as topographical (i.e. slope, plan curvature, and profile curvature), hydrogeological (i.e. transmissivity, aquifer thickness, and electrical conductivity), hydrological (i.e. rainfall, distance from rivers, river density, and permeability), lithology, and land use were considered as input to the models. For the FR modelling, classified layers of the aforementioned variables were used, while their continuous layers were implemented in the KNN and RF algorithms. At the last step, receiver operating characteristic (ROC) curve was used to assess the ability and accuracy of the applied algorithms. Based on the findings, the area under the curve of ROC for the RF, KNN, and FR models was 97.1, 94.6, and 89.2%, respectively. Furthermore, transmissivity, slope, aquifer thickness, distance from rivers, rainfall, and electrical conductivity were recognized as the most influencing factors in the modelling procedure. The findings of this study indicated that the application of RF, KNN, and FR can be suggested for identification of suitable areas for FSP establishment in other regions.
dc.language	English
dc.publisher	SPRINGER
dc.relation.ispartof	Natural Resources Research
dc.relation.isbasedon	10.1007/s11053-019-09530-4
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0502 Environmental Science and Management, 0914 Resources Engineering and Extractive Metallurgy
dc.subject.classification	Geochemistry & Geophysics
dc.title	Water Resources Management Through Flood Spreading Project Suitability Mapping Using Frequency Ratio, k-nearest Neighbours, and Random Forest Algorithms
dc.type	Journal Article
utslib.citation.volume	29
utslib.for	0909 Geomatic Engineering
utslib.for	0502 Environmental Science and Management
utslib.for	0502 Environmental Science and Management
utslib.for	0914 Resources Engineering and Extractive Metallurgy
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Information, Systems and Modelling
utslib.copyright.status	closed_access	*
dc.date.updated	2021-04-10T02:04:02Z
pubs.issue	3
pubs.publication-status	Published
pubs.volume	29
utslib.citation.issue	3

Abstract:

Lack of water resources is a common issue in many countries, especially in the Middle East. Flood spreading project (FSP) is an artificial recharge technique, which is generally suggested for arid and semi-arid areas with two major aims including (1) flood mitigation and (2) artificial recharge of groundwater. This study implemented three state-of-the-art popular models including frequency ratio (FR), k-nearest neighbours (KNN), and random forest (RF) for determining the suitability of land for FSP. At the first step, suitable areas for FSP were identified according to the national guidelines and the literature. The identified areas were then verified by multiple field surveys. To produce FSP land suitability maps, several FSP conditioning factors such as topographical (i.e. slope, plan curvature, and profile curvature), hydrogeological (i.e. transmissivity, aquifer thickness, and electrical conductivity), hydrological (i.e. rainfall, distance from rivers, river density, and permeability), lithology, and land use were considered as input to the models. For the FR modelling, classified layers of the aforementioned variables were used, while their continuous layers were implemented in the KNN and RF algorithms. At the last step, receiver operating characteristic (ROC) curve was used to assess the ability and accuracy of the applied algorithms. Based on the findings, the area under the curve of ROC for the RF, KNN, and FR models was 97.1, 94.6, and 89.2%, respectively. Furthermore, transmissivity, slope, aquifer thickness, distance from rivers, rainfall, and electrical conductivity were recognized as the most influencing factors in the modelling procedure. The findings of this study indicated that the application of RF, KNN, and FR can be suggested for identification of suitable areas for FSP establishment in other regions.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/147986