Back to Search Start Over

An Assessment of the Effectiveness of Tree-Based Models for Multi-Variate Flood Damage Assessment in Australia

Authors :
Roozbeh Hasanzadeh Nafari
Tuan Ngo
Priyan Mendis
Source :
Water, Vol 8, Iss 7, p 282 (2016)
Publication Year :
2016
Publisher :
MDPI AG, 2016.

Abstract

Flood is a frequent natural hazard that has significant financial consequences for Australia. In Australia, physical losses caused by floods are commonly estimated by stage-damage functions. These methods usually consider only the depth of the water and the type of buildings at risk. However, flood damage is a complicated process, and it is dependent on a variety of factors which are rarely taken into account. This study explores the interaction, importance, and influence of water depth, flow velocity, water contamination, precautionary measures, emergency measures, flood experience, floor area, building value, building quality, and socioeconomic status. The study uses tree-based models (regression trees and bagging decision trees) and a dataset collected from 2012 to 2013 flood events in Queensland, which includes information on structural damages, impact parameters, and resistance variables. The tree-based approaches show water depth, floor area, precautionary measures, building value, and building quality to be important damage-influencing parameters. Furthermore, the performance of the tree-based models is validated and contrasted with the outcomes of a multi-parameter loss function (FLFArs) from Australia. The tree-based models are shown to be more accurate than the stage-damage function. Consequently, considering more parameters and taking advantage of tree-based models is recommended. The outcome is important for improving established Australian flood loss models and assisting decision-makers and insurance companies dealing with flood risk assessment.

Details

Language :
English
ISSN :
20734441
Volume :
8
Issue :
7
Database :
Directory of Open Access Journals
Journal :
Water
Publication Type :
Academic Journal
Accession number :
edsdoj.76789ac68887470e87dd60979618b0c2
Document Type :
article
Full Text :
https://doi.org/10.3390/w8070282