Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood

Darabi, Hamid ; Rahmati, Omid ; Naghibi, Seyed Amir LU ; Mohammadi, Farnoush ; Ahmadisharaf, Ebrahim ; Kalantari, Zahra ; Haghighi, Ali Torabi ; Soleimanpour, Seyed Masoud ; Tiefenbacher, John P. and Tien Bui, Dieu (2022) In Geocarto International 37(19). p.5716-5741
Abstract
In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive... (More)
In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Geocarto International
volume
37
issue
19
pages
26 pages
publisher
Taylor & Francis
external identifiers
  • scopus:85106309036
ISSN
1010-6049
DOI
10.1080/10106049.2021.1920629
language
English
LU publication?
yes
id
3ef2509c-9f4a-4027-b4d8-c881d2b9fc0a
date added to LUP
2021-06-11 00:14:55
date last changed
2023-10-10 20:50:40
@article{3ef2509c-9f4a-4027-b4d8-c881d2b9fc0a,
  abstract     = {{In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models.}},
  author       = {{Darabi, Hamid and Rahmati, Omid and Naghibi, Seyed Amir and Mohammadi, Farnoush and Ahmadisharaf, Ebrahim and Kalantari, Zahra and Haghighi, Ali Torabi and Soleimanpour, Seyed Masoud and Tiefenbacher, John P. and Tien Bui, Dieu}},
  issn         = {{1010-6049}},
  language     = {{eng}},
  number       = {{19}},
  pages        = {{5716--5741}},
  publisher    = {{Taylor & Francis}},
  series       = {{Geocarto International}},
  title        = {{Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood}},
  url          = {{http://dx.doi.org/10.1080/10106049.2021.1920629}},
  doi          = {{10.1080/10106049.2021.1920629}},
  volume       = {{37}},
  year         = {{2022}},
}