Flood hazards susceptibility mapping using statistical, fuzzy logic, and MCDM methods

Akay, Hüseyın

doi:10.1007/s00500-021-05903-1

Cited by 86 publications

(25 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are studies with the joint application of the Promethee multicriteria method and Machine Learning prediction in financial decision making (Mousavi & Lin, 2020); and a new hybrid fuzzy prediction method is introduced by combining the Fuzzy Analytic Hierarchy Process (FAHP) and machine learning model (Ozdemir et al, 2021). For applications to energy or classification problems: fuzzy interval time series energy and financial forecasting model (Liu et al, 2020); flood hazards susceptibility mapping using statistical, fuzzy logic and MCDM methods (Akay, 2021); assessment of a failure prediction model in the energy sector with multicriteria discrimination approach, Promethee based classification (Angilella & Pappalardo, 2021); hybrid neurofuzzy investigation of short-term variability of wind resource (Adedeji et al, 2021); TOPSIS-ELM framework for stock index price movement prediction (Samal & Dash, 2021); cost-sensitive business failure prediction when misclassification costs are uncertain (Bock et al, 2020); multi objective optimization of crude oil supply portfolio based on interval prediction data (Sun et al, 2022); optimization of integrated fuzzy decision tree and regression models for selection of oil spill response (Mohammadiun et al, 2021); use of PairCode algorithm for ordinal classification based on pairwise comparison (Yang et al, 2020); and client profile prediction using convolutional neural networks (Nedjah et al, 2022). In addition, there are studies that show the application of the PROMETHEE-SAPEVO-M1 multi-criteria method to the analysis of OECD countries (Pereira et al, 2022) and multicriteria analysis applied to aircraft selection, case in Brazilian Navy (Maêda et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Model proposition for predicting sustainability classes using multicriteria decision support and artificial intelligence

Couto

Rangel

2022

Gest. Prod.

View full text Add to dashboard Cite

The current study proposes a novel prediction model of sustainability classes for electricity distribution companies in Brazil, based on sustainability indicators, aiming at a more effective risk management for a certain company among their competitors. Because such indicators are based on quantitative and qualitative measures and are very likely to incur imprecisions in their measures, the model to be proposed is based on a Multicriteria Decision Support, Rough Sets Theory, which allows the mathematical treatment of those imprecisions, and Artificial Intelligence, in this case, Machine Learning by rules inference. Consequently, decision tables are generated with condition attributes, sustainability indicators, and decision attributes, sustainability classes: high, medium or low. As a result, it is possible to predict sustainability classes based in temporal series of indicators and rules inference from decision tables, using RoughSets package in R and the jMAF software, demonstrating the use of five rule generation algorithms and their respective accuracies.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Model proposition for predicting sustainability classes using multicriteria decision support and artificial intelligence

Couto

Rangel

2022

Gest. Prod.

View full text Add to dashboard Cite

show abstract

“…The MCDM has been proven to be useful in resolving conflicts between tangible and intangible parts in the machine tool selection (Li et al 2020). It has been observed that various scholars used MCDM techniques in their work to delineate flood hazard zonation (Fernandez and Lutz 2010;Das 2018), flood susceptible mapping (Akay 2021;Ahmadlou et al 2021), flood vulnerability mapping (Atijosan et al 2021, Sarkar et al 2021, flood risk mapping (Radwan et al 2019), flash floods analysis Costache et al 2021), and flood forecasting (Haghizadeh et al 2017;Teh Noranis et al 2019). In contemporary studies, the MCDM technique, viz.…”

Section: Introductionmentioning

confidence: 99%

“…Analytical Hierarchy Process (AHP) (Das 2020;Das and Gupta 2021), Fuzzy Analytical Hierarchy Process (Hasanloo et al 2019), Discrete Choice Analysis (Wassenaar and Chen 2003), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) (Sari 2021), Preference Ranking Organization Method (Chen 2021), Vise Kriterijumska Optimizacijaik Ompromisno Resenje (VIKOR) (Wang et al 2019), Evaluation Based on Distance from Average Solution (EDAS) (Ghorabaee et al 2017), and Multi-objective Optimization on the basis Ratio Analysis (Karande and Chakraborty 2012), takes a dominant role to handle flood hazard susceptibility and vulnerability mapping. In this study, the researchers have attempted to manifest the flood susceptibility modelling of the region using the TOPSIS, VIKOR, and EDAS MCDM methods, which are become preferably and frequently used in regional flood studies (Arabameri et al 2019;Khosravi et al 2019;Akay 2021;Axelsson et al 2021;Zanganeh Asadi et al 2021). All the MCDM methods are selected due to their high efficiency in making the decision based on multiple criteria (Song and Chung 2016;Siregar et al 2018;Stanujkic et al 2018).…”

Section: Introductionmentioning

confidence: 99%

A comparative assessment of flood susceptibility modelling of GIS-based TOPSIS, VIKOR, and EDAS techniques in the Sub-Himalayan foothills region of Eastern India

Mitra

Das²

2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

In the Sub-Himalayan foothills region of eastern India, floods are considered the most powerful annually occurring natural disaster, which causes severe losses to the socio-economic life of the inhabitants. The present study tested three comprehensive and systematic MCDM techniques such as Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), Vise Kriterijumska Optimizacijaik Ompromisno Resenje (VIKOR), and Evaluation Based on Distance from Average Solution (EDAS) in Koch Bihar district for comparative assessment of the flood susceptible zones.The 21 indicators, i.e., elevation, slope, drainage density, geomorphology, rainfall deviation, aspect, curvature, lineament density, lithology, long-term annual rainfall, land use land cover, modified fournier index, modified normalized difference water index, normalized difference vegetation index, roughness, soil, sediment transport index, stream power index, topographic positioning index, terrain ruggedness index, and topographic wetness index were considered as the essential flood conditioning parameters. The multicollinearity statistics were employed to erase the issues regarding highly correlated parameters (i.e., MFI and long-term annual rainfall). The Spearman's rank (𝑟ₛ) tests among the three models revealed that TOPSIS-EDAS persisted in a high correlation (𝑟ₛ = 0.714) in contrast to the relationships between VIKOR-EDAS (𝑟ₛ = 0.651) and TOPSIS-VIKOR (𝑟ₛ = 0.639). The model's efficiency was statistically judged by applying the Receiver Operating Characteristic-Area Under the Curve (ROC-AUC), Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE) techniques to recognize the better-suited models for mapping the flood susceptibility. The performance of all techniques is found good enough (ROC-AUC = >0.700 and MAE, MSE and RMSE = <0.300). However, TOPSIS and VIKOR have manifested an excellent outcome and are highly recommended for identifying flood susceptibility in such active flood-prone areas.

show abstract

“…Currently, commonly used RS techniques used to determine flood extents include histogram thresholding to generate binary maps (di Baldassarre et al, 2011), change detection (Huang & Jin, 2020), change detection and thresholding (CDAT) (Long et al, 2014), principal component analysis and statistical and hybrid methods (Akay, 2021). Determination of flood depth involves the fusion of surface extent with elevation data (di Baldassarre et al, 2011; Schumann et al, 2007), while flow velocity is a function of slope: a derivative of elevation data.…”

Section: Introductionmentioning

confidence: 99%

The use of remote sensing indices to understand flood‐recharged soil moisture impacts on trees in semi‐arid floodplains: A review

et al. 2022

View full text Add to dashboard Cite

Remote sensing indices (RSIs) are essential for detection, mapping and monitoring of floods, soil moisture and tree characteristics. An understanding of the nexus between flood-recharged soil moisture (FRSM) and endangered biodiversity tree hotspots in semi-arid floodplains is critical. Specifically, the influence of FRSM on biophysical characteristics of keystone tree species with social, economic, ecological and environmental functions is crucial. However, the use of RSIs to understand the link between episodic floods, FRSM and trees, as well as their respective spatiotemporal dynamics within the semi-arid floodplains, remains largely unexplored. Hence, this study reviewed literature on the adoption of RSIs in understanding short-term phenological and long-term tree structural changes arising from flood-related infiltration. The reviewed literature shows the predominance of the normalised difference water index, the land surface water index and normalised difference vegetation index for flood, FRSM and tree mapping. The review also shows the emergence of SAR-based normalised difference flood index for understanding the impacts of FRSM on riparian trees. Although the review identified an increase in data availability, however, there are high costs of active commercial remote sensing data of superior quality and computing resources. Furthermore, available free data are incapable of penetrating canopies and have coarse spatial resolution constraining the use of RSIs to understand the impacts of FRSM on trees. In view of increasing free SAR data and cloudbased computing resources, application of emerging deep learning algorithms offers prospects for the use of RSIs to understand the impacts of FRSM on riparian trees.

show abstract

Flood hazards susceptibility mapping using statistical, fuzzy logic, and MCDM methods

Cited by 86 publications

References 48 publications

Model proposition for predicting sustainability classes using multicriteria decision support and artificial intelligence

Model proposition for predicting sustainability classes using multicriteria decision support and artificial intelligence

A comparative assessment of flood susceptibility modelling of GIS-based TOPSIS, VIKOR, and EDAS techniques in the Sub-Himalayan foothills region of Eastern India

The use of remote sensing indices to understand flood‐recharged soil moisture impacts on trees in semi‐arid floodplains: A review

Contact Info

Product

Resources

About