A comparative assessment of multi-criteria decision-making analysis and machine learning methods for flood susceptibility mapping and socio-economic impacts on flood risk in Abela-Abaya floodplain of Ethiopia

Edamo, Muluneh Legesse; Ukumo, Tigistu Yisihak; Lohani, Tarun Kumar; Ayana, Melkamu Teshome; Ayele, Mesfin Amaru; Mada, Zerihun Makayno; Abdi, Dawit Midagsa

doi:10.1016/j.envc.2022.100629

Cited by 22 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Population growth and rapid development are also the causes of degradation in the Palapa Metropolitan area. So it is essential to identify areas vulnerable to landslides and floods [22,23]. Identification of landslide and flood areas will assist the government in making appropriate policies and strategies to reduce environmental degradation [42,43].…”

Section: Resultsmentioning

confidence: 99%

“…These natural disasters will become an essential issue in sustainable urban ecological management. As a result, it is necessary to identify locations prone to landslides and floods to plan appropriate disaster prevention [21][22][23]. This study aims to identify the spatiotemporal distribution pattern and spatial clustering of areas prone to landslides and floods in Metropolitan Palapa using Moran's Index based on Local Indicators of Spatial Association (LISA) statistics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatiotemporal Distribution Pattern and Spatial Clustering of Landslide-and Flood-Prone Areas in Metropolitan Palapa, Indonesia

Amelia¹,

Guswandi²

2023

IJSDP

View full text Add to dashboard Cite

The rapid development of urban areas is one of the driving factors for hazard exposure which causes vulnerability and environmental degradation. Environmental degradation causes vulnerability to disasters which will have implications for a decrease in economic benefits and an increase in community poverty. Landslides and floods are frequent natural disasters that cause environmental degradation. To reduce the risk of landslides and floods and formulate development policies and strategies in disaster-prone areas is necessary to identify landslides and flood areas. This study aims to identify and detect areas prone to landslides and floods in Metropolitan Palapa using GIS analysis and Moran's Local Index based on LISA statistics. The analysis results show that the northern to northeastern areas of Metropolitan Palapa (Pariaman regency and Pariaman municipal) are areas with high vulnerability to landslides, with high positive spatial associations of landslide occurrence and intensity. The area has an altitude between 350 to >1100 above sea level and a slope between 15 to >45%. Meanwhile, Padang and Pariaman municipal are areas that are vulnerable to flood hazards, and this is because these areas are lowlands/coastal areas. We can implement strategies and policies for the Palapa Metropolitan area, including a) limiting development in the northern region, b) applying engineering to areas prone to landslides by applying cut and fill techniques, c) improvement of drainage systems in areas prone to flooding; d) increase public awareness to care and provide incentives to people who care about the environment. Appropriate strategies and policies will reduce environmental degradation. We required disaster-based development planning to reduce environmental degradation, but the data is often an obstacle.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Distribution Pattern and Spatial Clustering of Landslide-and Flood-Prone Areas in Metropolitan Palapa, Indonesia

Amelia¹,

Guswandi²

2023

IJSDP

View full text Add to dashboard Cite

show abstract

“…This concept enables the creation of a synthetic global vulnerability index by computing the weights of all criteria. The integration of AHP and GIS, where factors affecting the risk of flooding, including slope, land use, distance from streams, distance from drainage lines, rainfall intensity, elevation, curvature, lithological units, and soil characteristics are incorporated, results in a strong geographical decision support system (Haokip et al, 2022;Al-Taani et al, 2023;Khosravi et al, 2019 ;Edamo et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Flash flood risk mapping using Analytic Hierarchy Process and machine learning: case of Souk-Ahras City, Northeastern Algeria

Mechentel,

Dairi,

Djebbar

et al. 2024

Preprint

View full text Add to dashboard Cite

As the frequency and severity of floods increase, owing mostly to climate change and anthropogenic activities, identifying flood-prone locations is becoming an increasingly critical task. This study applies a new modeling technique for mapping flash-flood susceptibility in the urban basin of Souk-Ahras, Northeastern Algeria. The study area has been frequently affected by flash floods triggered by torrential rains, steep slopes, and high urbanization rates. The methodology used combines the multi-criteria Analytical Hierarchy Process (AHP) with machine learning, represented by the XGBoost Algorithm. Nine flash-flood conditioning factors were considered, including Land Use Land Cover (LULC), Normalized Difference Built-up Index (NDBI), Rainfall, Topographic Wetness Index (TWI), Slope, Elevation, Curvature, distance to road, and Lithology. The model training procedure used 46 flood spots and 109 no-flood points, which were randomly chosen from sites without a flood history. Model validation, represented by the receiver operating characteristic (ROC) curve, revealed that the AHP-XGBoost model achieved an Area Under Curve (AUC) of 84.5%, compared to 80% and 83% for the standalone AHP and XGBoost models, respectively. This clearly shows an optimal performance for the hybrid model considered.

show abstract

“…Machine learning techniques with efficient predictive capabilities are also becoming applicable in different hazard susceptibility and vulnerability assessments (Antzoulatos et al 2022). Moreover, in many instances, MCDA approaches were addressed by scholars as an effective tool for examining hazard susceptibility and decision-making analysis (Erener et al 2016;Tang et al 2018;Edamo et al 2022;Mousavi et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Appraisal of Flood Susceptibility of Hooghly basin, India using Shannon Entropy (SE) and Fuzzy Analytical Hierarchy Process (FAHP)

Rehman,

Chaudhary,

Azhoni

2023

Preprint

View full text Add to dashboard Cite

Hooghly basin is one of the flood-affected areas of West Bengal in India. The basin's dense river system, topography, and geographic location make it more susceptible to flooding. Effective flood management necessitates the understating of the spatial distribution of flood susceptible areas. In this context, the present work has examined the flood susceptibility of the Hooghly basin using two significant methods of multicriteria decision making models (MCDM) i.e., Shannon Entropy (SE) and Fuzzy Analytical Hierarchy Process (FAHP) models. These two models were applied to twelve flood conditioning factors such as drainage density, elevation, LULC, normalized difference built up index (NDBI), normalized difference vegetation index (NDVI), normalized difference water index (NDWI), population density, rainfall, distance to rivers, slope, stream power index (SPI) and topographic wetness index (TWI). Binary logistic regression was also performed to identify the confounders of susceptibility in the basin. Drainage density, elevation, rainfall, and distance to rivers were identified as the major determinants of flood susceptibility. Validation of the models through the area under ROC curve (AUC) showed good predictability for SE (0.70) and FAHP (0.71) based flood susceptibility prediction. Therefore, this study may provide a base for stakeholders and planners in managing and minimizing flood susceptibility in the basin.

show abstract

A comparative assessment of multi-criteria decision-making analysis and machine learning methods for flood susceptibility mapping and socio-economic impacts on flood risk in Abela-Abaya floodplain of Ethiopia

Cited by 22 publications

References 44 publications

Spatiotemporal Distribution Pattern and Spatial Clustering of Landslide-and Flood-Prone Areas in Metropolitan Palapa, Indonesia

Spatiotemporal Distribution Pattern and Spatial Clustering of Landslide-and Flood-Prone Areas in Metropolitan Palapa, Indonesia

Flash flood risk mapping using Analytic Hierarchy Process and machine learning: case of Souk-Ahras City, Northeastern Algeria

Appraisal of Flood Susceptibility of Hooghly basin, India using Shannon Entropy (SE) and Fuzzy Analytical Hierarchy Process (FAHP)

Contact Info

Product

Resources

About