A GIS-Based Artificial Neural Network Model for Flood Susceptibility Assessment
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
This article presents a geographic information system (GIS)-based artificial neural network (GANN) model for flood susceptibility assessment of Keelung City, Taiwan. Various factors, including elevation, slope angle, slope aspect, flow accumulation, flow direction, topographic wetness index (TWI), drainage density, rainfall, and normalized difference vegetation index, were generated using a digital elevation model and LANDSAT 8 imagery. Historical flood data from 2015 to 2019, including 307 flood events, were adopted for a comparison of flood susceptibility. Using these factors, the GANN model, based on the back-propagation neural network (BPNN), was employed to provide flood susceptibility. The validation results indicate that a satisfactory result, with a correlation coefficient of 0.814, was obtained. A comparison of the GANN model with those from the SOBEK model was conducted. The comparative results demonstrated that the proposed method can provide good accuracy in predicting flood susceptibility. The results of flood susceptibility are categorized into five classes: Very low, low, moderate, high, and very high, with coverage areas of 60.5%, 27.4%, 8.6%, 2.5%, and 1%, respectively. The results demonstrate that nearly 3.5% of the study area, including the core district of the city and an exceedingly populated area including the financial center of the city, can be categorized as high to very high flood susceptibility zones.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures









Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Studies indicate that higher TWI values are often associated with increased flood hazards [53].”
From Urban Flood Vulnerability Assessment in Freetown, Sierra Leone: AHP Approach (2024) · cites this paper as [53]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Global flood risk under climate change
Hirabayashi, Y., Mahendran, R., Koirala, S., Konoshima, L., Yamazaki, D., Watanabe, S., Kim, H., & Kanae, S. (2013) · Nature Climate Change · doi:10.1038/nclimate1911 · Cited by 3,013
Interpretation of the correlation coefficient: A basic review
Taylor, R. (1990) · Journal of Diagnostic Medical Sonography · doi:10.1177/875647939000600106 · Cited by 2,390 · cited 1×
“According to previous studies [44,45], correlation coefficients whose magnitudes are between 0.”
MethodThe correlation coefficient: its values range between +1/-1, or do they?
Ratner, B. (2009) · Journal of Targeting, Measurement and Analysis for Marketing · doi:10.1057/jt.2009.5 · Cited by 1,612 · cited 1×
“According to previous studies [44,45], correlation coefficients whose magnitudes are between 0.”
MethodA survey of machine learning for big data processing
Qiu, J., Wu, Q., Ding, G., Xu, Y., & Feng, S. (2016) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-016-0355-x · Cited by 894 · cited 1×
“The artificial neural network (ANN) is one of the most implemented machine-learning techniques in engineering risk assessment [11].”
BackgroundFlood hazard risk assessment model based on random forest
Wang, Z., Lai, C., Chen, X., Yang, B., Zhao, S., & Bai, X. (2015) · Journal of Hydrology · doi:10.1016/j.jhydrol.2015.06.008 · Cited by 822 · cited 1×
“For SVMs, it is more effective in high-dimensional spaces [16].”
An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia
Kia, M. B., Pirasteh, S., Pradhan, B., Mahmud, A. R., Sulaiman, W. N. A., & Moradi, A. (2012) · Environmental Earth Sciences · doi:10.1007/s12665-011-1504-z · Cited by 692 · cited 7×
“There are no strict rules for as‐ signing the number of hidden layers and neurons in the literature [21].”
BackgroundMethodInfluentialAnalysis of NDVI and scaled difference vegetation index retrievals of vegetation fraction
Jiang, Z., Huete, A. R., Chen, J., Chen, Y., Li, J., Yan, G., & Zhang, X. (2006) · Remote Sensing of Environment · doi:10.1016/j.rse.2006.01.003 · Cited by 665 · cited 1×
“Normalized Difference Vegetation Index (NDVI) The NDVI is one of the most extensively adopted vegetation indexes using satellite imagery, and for monitoring of global vegetation cover [32].”
BackgroundWang, L., Zeng, Y., & Chen, T. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.08.018 · Cited by 631
Application of Remote Sensing in Flood Management with Special Reference to Monsoon Asia: A Review
Sanyal, J., & Lu, X. X. (2004) · Natural Hazards · doi:10.1023/b:nhaz.0000037035.65105.95 · Cited by 526 · cited 7×
“DEM: Digital elevation model.”
BackgroundInfluentialFlood maps in Europe – methods, availability and use
de Moel, H., van Alphen, J., & Aerts, J. C. J. H. (2009) · Natural Hazards and Earth System Sciences · doi:10.5194/nhess-9-289-2009 · Cited by 503
Memristor-based neural networks
Thomas, A. (2013) · Journal of Physics D: Applied Physics · doi:10.1088/0022-3727/46/9/093001 · Cited by 471 · cited 3×
“Artificial Neural Network The ANN is considered a quantitative black‐box approach that tries to simulate the functional human biological nervous system [12].”
BackgroundMethodInfluentialMapping flood susceptibility in mountainous areas on a national scale in China
Zhao, G., Pang, B., Xu, Z., Yue, J., & Tu, T. (2018) · Science of The Total Environment · doi:10.1016/j.scitotenv.2017.10.037 · Cited by 389 · cited 2×
“Mapping flood susceptibility could be the first step toward mitigating flooding, because flood susceptibility identifies the most vulnerable locations and provides sufficient lead time for an individual to re‐ spond to flooding in an anticipatory rather than reactive manner [46].”
BackgroundFotovatikhah, F., Herrera, M., Shamshirband, S., Chau, K.-W., Faizollahzadeh Ardabili, S., & Piran, M. J. (2018) · Engineering Applications of Computational Fluid Mechanics · doi:10.1080/19942060.2018.1448896 · Cited by 342 · cited 1×
“Nowadays, ANNs and computational intelligence (CI) methods are often used for flood disaster modeling [13].”
Gridded population projections for the coastal zone under the Shared Socioeconomic Pathways
Merkens, J.-L., Reimann, L., Hinkel, J., & Vafeidis, A. T. (2016) · Global and Planetary Change · doi:10.1016/j.gloplacha.2016.08.009 · Cited by 334 · cited 1×
“Coastal areas are vulnerable to climate change, particularly sea-level rises and floods related to extreme rainfall [1,2].”
BackgroundMulti-Criteria Analysis Framework for Potential Flood Prone Areas Mapping
Papaioannou, G., Vasiliades, L., & Loukas, A. (2015) · Water Resources Management · doi:10.1007/s11269-014-0817-6 · Cited by 315 · cited 1×
“The flood susceptibility map was analyzed qualitatively using natural breaks (jenks) classification schemes [47,48].”
MethodBack Propagation Neural Networks
Buscema, M. (1998) · Substance Use & Misuse · doi:10.3109/10826089809115863 · Cited by 307
Assessment of urban flood susceptibility using semi-supervised machine learning model
Zhao, G., Pang, B., Xu, Z., Peng, D., & Xu, L. (2019) · Science of The Total Environment · doi:10.1016/j.scitotenv.2018.12.217 · Cited by 278 · cited 1×
“For logistic regression, this algorithm is easier to implement and interpret, and more efficient to train [14].”
MethodDas, S. (2019) · Remote Sensing Applications: Society and Environment · doi:10.1016/j.rsase.2019.02.006 · Cited by 235
Dou, J., Yamagishi, H., Pourghasemi, H. R., Yunus, A. P., Song, X., Xu, Y., & Zhu, Z. (2015) · Natural Hazards · doi:10.1007/s11069-015-1799-2 · Cited by 234
Artificial neural network approach to flood forecasting in the River Arno
CAMPOLO, M., SOLDATI, A., & ANDREUSSI, P. (2003) · Hydrological Sciences Journal · doi:10.1623/hysj.48.3.381.45286 · Cited by 218 · cited 1×
“[43], who trained the variables with 20, 25, 30, 35, and 40 hidden layers, and Islam [35] as a comparison, with 15, 20, 25, 30, and 35 hidden layers.”
Comparison of Rainfall Interpolation Methods in a Mountainous Region of a Tropical Island
Mair, A., & Fares, A. (2011) · Journal of Hydrologic Engineering · doi:10.1061/(asce)he.1943-5584.0000330 · Cited by 203 · cited 1×
“Preparation of a rainfall map in this study used the pixel-based highest hourly rainfall data of several decades, spread around four rain gauge stations around Keelung City, with the Kriging interpolation method [31].”
MethodChen, J., Li, Q., Wang, H., & Deng, M. (2019) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17010049 · Cited by 189
Land subsidence modelling using tree-based machine learning algorithms
Rahmati, O., Falah, F., Naghibi, S. A., Biggs, T., Soltani, M., Deo, R. C., Cerdà, A., Mohammadi, F., & Tien Bui, D. (2019) · Science of The Total Environment · doi:10.1016/j.scitotenv.2019.03.496 · Cited by 179 · cited 2×
“Slope Aspect This aspect recognizes the downslope direction, and is also thought of as the slope orientation [24].”
BackgroundBajabaa, S., Masoud, M., & Al-Amri, N. (2014) · Arabian Journal of Geosciences · doi:10.1007/s12517-013-0941-2 · Cited by 176 · cited 1×
“The aspect is one of the significant factors in producing flood susceptibility maps [25].”
BackgroundFlood hazard mapping in Jamaica using principal component analysis and logistic regression
Nandi, A., Mandal, A., Wilson, M., & Smith, D. (2016) · Environmental Earth Sciences · doi:10.1007/s12665-016-5323-0 · Cited by 174 · cited 2×
“Areas with a high wetness index occur where there is a combination of low slope and high flow accumulation and, therefore, may indicate locations that are at greater flood risk [27].”
BackgroundEakin, H. C., Lerner, A. M., & Murtinho, F. (2009) · Global Environmental Change · doi:10.1016/j.gloenvcha.2009.08.005 · Cited by 140
Aziz, K., Rahman, A., Fang, G., & Shrestha, S. P. (2013) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-013-0771-5 · Cited by 140 · cited 3×
“This is despite the fact that several researchers used only one hidden layer in their ANN architecture, or a small value of hidden layers from 1 to 7 [29,40].”
BackgroundMethodA Climate Change Vulnerability Index and Case Study in a Brazilian Coastal City
Zanetti, V. B., de Sousa, W. C., & Freitas, D. D. (2016) · Sustainability · doi:10.3390/su8080811 · Cited by 93 · cited 1×
“Coastal areas are vulnerable to climate change, particularly sea-level rises and floods related to extreme rainfall [1,2].”
BackgroundRisk Assessment of Flood Disaster Induced by Typhoon Rainstorms in Guangdong Province, China
Zhang, J., & Chen, Y. (2019) · Sustainability · doi:10.3390/su11102738 · Cited by 92
Latt, Z. Z., & Wittenberg, H. (2014) · Water Resources Management · doi:10.1007/s11269-014-0600-8 · Cited by 90 · cited 5×
“This is despite the fact that several researchers used only one hidden layer in their ANN architecture, or a small value of hidden layers from 1 to 7 [29,40].”
BackgroundMethodInfluentialFlood forecasting within urban drainage systems using NARX neural network
Rjeily, Y. A., Abbas, O., Sadek, M., Shahrour, I., & Chehade, F. H. (2017) · Water Science & Technology · doi:10.2166/wst.2017.409 · Cited by 87 · cited 2×
“The GANN model of flood susceptibility used 10 hidden layers, as at that point the model starts to reach the mini‐ mum requirement for the correlation coefficient, according to some research [8,28,42].”
MethodDang, V.-H., Bui, D. T., Tran, X.-L., & Hoang, N. (2018) · Bulletin of Engineering Geology and the Environment · doi:10.1007/s10064-018-1273-y · Cited by 84 · cited 2×
“The GANN model of flood susceptibility used 10 hidden layers, as at that point the model starts to reach the mini‐ mum requirement for the correlation coefficient, according to some research [8,28,42].”
MethodFlood mapping in the lower Mekong River Basin using daily MODIS observations
Fayne, J. V., Bolten, J., Doyle, C. S., Fuhrmann, S., Rice, M. T., Houser, P. R., & Lakshmi, V. (2017) · International Journal of Remote Sensing · doi:10.1080/01431161.2017.1285503 · Cited by 66 · cited 1×
“The NDVI, developed by Rouse in 1973, is used to monitor vegetation health, and to compare outputs across sensors with slightly different specifications [33].”
MethodSpatial heterogeneity of local flood vulnerability indicators within flood-prone areas in Taiwan
Chang, H., & Chen, T.-L. (2016) · Environmental Earth Sciences · doi:10.1007/s12665-016-6294-x · Cited by 64 · cited 2×
“In Taiwan, extreme weather conditions, such as heavy precipitation and typhoons generated by climate change, strengthen the phenomenon of flood disasters [3].”
BackgroundRisk analysis for flood-control structure under consideration of uncertainties in design flood
Wu, S., Yang, J., & Tung, Y. (2010) · Natural Hazards · doi:10.1007/s11069-010-9653-z · Cited by 56
Flood risk assessment for urban water system in a changing climate using artificial neural network
Abdellatif, M. E., Atherton, W., Alkhaddar, R. M., & Osman, Y. Z. (2015) · Natural Hazards · doi:10.1007/s11069-015-1892-6 · Cited by 52
Hsu, T., Shih, D.-S., Li, C., Lan, Y., & Lin, Y.-C. (2017) · Water · doi:10.3390/w9060390 · Cited by 50
A Historical Record of Coastal Floods in Britain: Frequencies and Associated Storm Tracks
Zong, Y., & Tooley, M. J. (2003) · Natural Hazards · doi:10.1023/a:1022942801531 · Cited by 38 · cited 1×
“The flood history, also known as the disaster experience, assumes that such areas have higher adaption ability, but also a high probability of flood occurrence in the future [3,34].”
BackgroundHsieh, L., Hsu, M., & Li, M. (2006) · Natural Hazards · doi:10.1007/s11069-005-4660-1 · Cited by 34 · cited 2×
“Keelung City is one of the major coastal cities in Northern Taiwan which has become highly urbanized and densely populated in the last few years [4].”
BackgroundLee, K. T., Ho, Y.-H., & Chyan, Y.-J. (2006) · Journal of Hydraulic Engineering · doi:10.1061/(asce)0733-9429(2006)132:3(319 · Cited by 30
Flood Disaster Risk Assessment of Rural Housings — A Case Study of Kouqian Town in China
Zhang, Q., Zhang, J., Jiang, L., Liu, X., & Tong, Z. (2014) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph110403787 · Cited by 28 · cited 1×
“Spatial analysis is applied to define the relationship between flood factors in hazards, vulnerability, and risk through the map, without focusing on complex hydrological modeling [20].”
BackgroundImproving flood forecasting in Bangladesh using an artificial neural network
Islam, A. K. M. S. (2009) · Journal of Hydroinformatics · doi:10.2166/hydro.2009.085 · Cited by 27 · cited 4×
“Furthermore, the ANN has been considered as an alternative to physically‐based models due to its simplicity regarding the minimum requirements for collecting detailed data [35].”
MethodInfluentialA Study on Coastal Flooding and Risk Assessment under Climate Change in Mid-Western Coast of TaiwanPreprint
Hsu, T., Shih, D.-S., Li, C., et al. (2017) · Preprints.org · doi:10.20944/preprints201703.0172.v1 · Cited by 17
Estimation of flood risk index considering the regional flood characteristics: a case of South Korea
Jung, Y., Shin, Y., Jang, C. H., Kum, D., Kim, Y. S., Lim, K. J., Kim, H. B., Park, T. S., & Lee, S. O. (2014) · Paddy and Water Environment · doi:10.1007/s10333-014-0430-6 · Cited by 11
Liu, Y., Feng, G., Xue, Y., Zhang, H., & Wang, R. (2014) · Natural Hazards · doi:10.1007/s11069-014-1420-0 · Cited by 9
Research works printed but not linked: 3
- Vos, F., Rodriguez, J., Below, R., and Guha-Sapir, D. (2010). Annual Disaster Statistical Review 2009: The Numbers and Trends, Center of Research on the Epidemiology of Disasters (CRED).
- Karlik, 2011, Performance analysis of various activation functions in generalized MLP architectures of neural networks, Int. J. Artif. Intell. Expert Syst., 1, 111
- Sibi, 2013, Analysis of different activation functions using back propagation neural networks, J. Theor. Appl. Inf. Technol., 47, 1264
Cited by
Bentivoglio, R., Isufi, E., Jonkman, S. N., & Taormina, R. (2022) · Hydrology and Earth System Sciences · doi:10.5194/hess-26-4345-2022 · Cited by 453
Islam, T., Zeleke, E. B., Afroz, M., & Melesse, A. M. (2025) · Remote Sensing · doi:10.3390/rs17030524 · Cited by 174
Flood Susceptibility Assessment with Random Sampling Strategy in Ensemble Learning (RF and XGBoost)
Ren, H., Pang, B., Bai, P., Zhao, G., Liu, S. Q., Liu, Y., & Li, M. (2024) · Remote Sensing · doi:10.3390/rs16020320 · Cited by 144
Saravanan, S., Abijith, D., Reddy, N. M., Sundar, P. K. S., Niraimathi, J., Sathiyamurthi, S., & Sivakumar, V. (2023) · Urban Climate · doi:10.1016/j.uclim.2023.101503 · Cited by 112
Rahman, Z. U., Ullah, W., Bai, S., Ullah, S., Jan, M. A., Khan, M. A., & Tayyab, M. (2023) · Frontiers in Environmental Science · doi:10.3389/fenvs.2023.1178540 · Cited by 107
Metadata
- Authors
- Khoirunisa, N., Ku, C.-Y., & Liu, C.-Y.
- Affiliations
- National Taiwan Ocean University (TW)
- Corresponding author
- Ku, Cheng-Yu
- Liu, Chih-Yu
- Venue
- International Journal of Environmental Research and Public Health
- Publisher
- MDPI AG
- Published
- 2021-01-26
- Volume
- 18
- Issue
- 3
- Pages
- 1072
- ISSN
- 1660-4601 (ISSN-L)
- PMC
- PMC7908221
- OpenAlex
- W3122286376
- Cited by
- 111
- References
- 44
- Citations by year
- 2026: 19 · 2025: 20 · 2024: 23 · 2023: 22 · 2022: 23 · 2021: 4
- FWCI
- 7.38
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- International Journal of Environmental Research and Public Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Ministry of Science and Technology, Taiwan (MOST109-2625-M019-007)
- Topics
- Physical Sciences › Environmental Science › Global and Planetary Change › Flood Risk Assessment and Management
- Physical Sciences › Environmental Science › Management, Monitoring, Policy and Law › Landslides and related hazards
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Keywords
- artificial neural networks, BP neural network, GIS-based flood modeling, topographic wetness index, flow accumulation, NDVI, historical flood records, urban flood risk
- MeSH terms
- Cities, Taiwan, Neural Networks, Computer, Geographic Information Systems, Floods
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.