Development of semi-quantitative earthquake risk assessment models using machine learning, multi-criteria decision-making, and GIS

Jena, Ratiranjan

Development of semi-quantitative earthquake risk assessment models using machine learning, multi-criteria decision-making, and GIS

Jena, Ratiranjan

Permalink

Publication Type:: Thesis
Issue Date:: 2021

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (711.12 kB)

Adobe PDF

Download thesisAdobe PDF (15.14 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Jena, Ratiranjan
dc.date.accessioned	2021-10-01T03:47:39Z
dc.date.available	2021-10-01T03:47:39Z
dc.date.issued	2021
dc.identifier.uri	http://hdl.handle.net/10453/150778
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Catastrophic natural hazards, such as earthquakes, pose serious threats to properties and human lives in urban areas. Earthquake risk assessment (ERA) is specifically required for areas with complicated tectonics because of the catastrophic nature of mega-events that result in a massive death toll. Therefore, ERA is indispensable in disaster management. The prerequisite for earthquake risk estimation is probability, hazard and vulnerability assessment. Several research gaps such as failure to establish comprehensive GIS-based models, few works on small scale ERA using integrated GIS techniques, use of limited conditioning factors, and little research on optimization of factors are specified in literature. Therefore, this study aims to develop models and estimate risk in city scale that is necessary to reduce future fatalities. The study evaluates the earthquake vulnerability by using the multi-criteria decision-making approach through a novel integrated analytical hierarchy process (AHP) and VIseKriterijumska Optimizacija I Kompromisno Resenje method using a geographical information system in the first objective. This research develops an integrated model by using the artificial neural network– AHP for constructing the ERA map in the second objective. The third objective presents a novel combination of artificial neural network cross-validation (fourfold ANN-CV) with a hybrid analytic hierarchy process-Technique for Order of Preference by Similarity to Ideal Solution (AHP-TOPSIS) method to improve the ERA and applied to Aceh, Indonesia. The proposed models are transferable to other regions by localizing the input parameters that contribute to earthquake risk mitigation and prevention planning. The results obtained from this research have important implications for future large-scale risk assessment, land use planning and hazard mitigation.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/150778/2/02whole.pdf
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Development of semi-quantitative earthquake risk assessment models using machine learning, multi-criteria decision-making, and GIS	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Catastrophic natural hazards, such as earthquakes, pose serious threats to properties and human lives in urban areas. Earthquake risk assessment (ERA) is specifically required for areas with complicated tectonics because of the catastrophic nature of mega-events that result in a massive death toll. Therefore, ERA is indispensable in disaster management. The prerequisite for earthquake risk estimation is probability, hazard and vulnerability assessment. Several research gaps such as failure to establish comprehensive GIS-based models, few works on small scale ERA using integrated GIS techniques, use of limited conditioning factors, and little research on optimization of factors are specified in literature. Therefore, this study aims to develop models and estimate risk in city scale that is necessary to reduce future fatalities. The study evaluates the earthquake vulnerability by using the multi-criteria decision-making approach through a novel integrated analytical hierarchy process (AHP) and VIseKriterijumska Optimizacija I Kompromisno Resenje method using a geographical information system in the first objective. This research develops an integrated model by using the artificial neural network– AHP for constructing the ERA map in the second objective. The third objective presents a novel combination of artificial neural network cross-validation (fourfold ANN-CV) with a hybrid analytic hierarchy process-Technique for Order of Preference by Similarity to Ideal Solution (AHP-TOPSIS) method to improve the ERA and applied to Aceh, Indonesia. The proposed models are transferable to other regions by localizing the input parameters that contribute to earthquake risk mitigation and prevention planning. The results obtained from this research have important implications for future large-scale risk assessment, land use planning and hazard mitigation.

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

http://hdl.handle.net/10453/150778