Enhancing flood risk assessment through integration of ensemble learning approaches and physical-based hydrological modeling

Saber, Mohamed; Boulmaiz, Tayeb; Guermoui, Mawloud; Abdrabo, Karim I.; Kantoush, Sameh A.; Takemon, Yasuhiro; Boutaghane, Hamouda; Hori, Toshitaka; Binh, Doan Van; Nguyen, Binh X.; Bui, Thao Thi Phuong; Vo, Ngoc Duong; Habib, Emad; Mabrouk, Emad

doi:10.1080/19475705.2023.2203798

Cited by 27 publications

(5 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the same way, outputs from all models could be averaged to a single output. There are plenty of examples where ensemble learning improves network performance: predicting the functional brain connectome [ 79 ], detection of Alzheimer’s disease [ 80 ], flood prediction [ 81 ] and change point estimation [ 82 ].…”

Section: Results and Discussionmentioning

confidence: 99%

Improving Structural MRI Preprocessing with Hybrid Transformer GANs

Grigas,

Maskeliūnas,

Damaševičius

2023

Life

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is a technique that is widely used in practice to evaluate any pathologies in the human body. One of the areas of interest is the human brain. Naturally, MR images are low-resolution and contain noise due to signal interference, the patient’s body’s radio-frequency emissions and smaller Tesla coil counts in the machinery. There is a need to solve this problem, as MR tomographs that have the capability of capturing high-resolution images are extremely expensive and the length of the procedure to capture such images increases by the order of magnitude. Vision transformers have lately shown state-of-the-art results in super-resolution tasks; therefore, we decided to evaluate whether we can employ them for structural MRI super-resolution tasks. A literature review showed that similar methods do not focus on perceptual image quality because upscaled images are often blurry and are subjectively of poor quality. Knowing this, we propose a methodology called HR-MRI-GAN, which is a hybrid transformer generative adversarial network capable of increasing resolution and removing noise from 2D T1w MRI slice images. Experiments show that our method quantitatively outperforms other SOTA methods in terms of perceptual image quality and is capable of subjectively generalizing to unseen data. During the experiments, we additionally identified that the visual saliency-induced index metric is not applicable to MRI perceptual quality assessment and that general-purpose denoising networks are effective when removing noise from MR images.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

Improving Structural MRI Preprocessing with Hybrid Transformer GANs

Grigas,

Maskeliūnas,

Damaševičius

2023

Life

View full text Add to dashboard Cite

show abstract

“…informed decision-making based on the best available flood and flood damage reduction data, allowing for anticipatory planning and preparation [114,138,173,174]. A multi-layered FR strategy.…”

Section: Urban Flood Resilience (Fr)mentioning

confidence: 99%

“…These master plans collect data on historical and forecasted flooding conditions, conduct risk and vulnerability analyses, and identify strategies for reducing vulnerability and bolstering resilience. Prevention also involves informed decision-making based on the best available flood and flood damage reduction data, allowing for anticipatory planning and preparation [114,138,173,174].…”

Section: Screening and Preliminary Analysismentioning

confidence: 99%

Revisiting Urban Resilience: A Systematic Review of Multiple-Scale Urban Form Indicators in Flood Resilience Assessment

Mabrouk,

Han,

Mahran

et al. 2024

Sustainability

Self Cite

View full text Add to dashboard Cite

Despite the increasing number of flood studies, the interrelationships between urban form indices (UFIs) and flood resilience (FR) have received little attention and hold miscellaneous perspectives. Consequentially, this study identifies how UFIs at various spatial scales affect FR by synthesizing article findings and proposing insights for future research. Scientometric analysis has been used to analyze the gathered peer-reviewed articles from nine research engines without time restrictions. One hundred and eighteen relevant articles were included and thoroughly investigated using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol. Our findings indicate that divergent and dialectical perspectives about the efficacy of UFIs are due to multiple disciplines, methodologies, and different case study contexts. The included studies were classified according to urban scale as macro (citywide), meso (districts), micro (block), and multi-scalar analysis by 80.5%, 6.8%, 10.2%, and 2.4%, respectively. Furthermore, the included studies were categorized based on analysis type into realistic case studies, literature reviews, modeling, and hybrid analysis, with 74.6%, 7.6%, 14.4%, and 3.4%, respectively. At the macroscale, city density and spatial distribution degree have the most significant effect on FR. At the same time, mixed uses, connectivity, coverage ratio, block arrangements, and street characteristics are on the meso and micro scales. Further studies on the trade-offs and commonality between UFIs, FR, and overall urban resilience are required to shape climate-adaptive, sustainable communities.

show abstract

“…Floods can be quantified in a variety of methods, including simple empirical procedures [21], the rational method [22], the flood frequency method [23], simplified conceptual models [24], multi-criteria decision analysis [25,26], and numerical and geographic information system (GIS)-based hydrodynamic modelling [7,16,27,28]. Hydrodynamic models are frequently employed in thorough flood dynamics simulations and are primarily associated with flood forecasting, mapping, and scenario analysis [29].…”

Section: Introductionmentioning

confidence: 99%

Integrated Hydrological Modeling for Watershed Analysis, Flood Prediction, and Mitigation Using Meteorological and Morphometric Data, SCS-CN, HEC-HMS/RAS, and QGIS

El-Bagoury,

Gad

2024

Water

View full text Add to dashboard Cite

Flooding is a natural disaster with extensive impacts. Desert regions face altered flooding patterns owing to climate change, water scarcity, regulations, and rising water demands. This study assessed and predicted flash flood hazards by calculating discharge volume, peak flow, flood depth, and velocity using the Hydrologic Engineering Centre-River Analysis System and Hydrologic Modelling System (HEC-HMS and HEC-RAS) software. We employed meteorological and morphological data analyses, incorporating the soil conservation service (SCS) curve number method for precipitation losses and the SCS-Hydrograph for runoff transformation. The model was applied to two drainage basins (An-Nawayah and Al-Rashrash) in southeastern Cairo, Egypt, which recently encountered several destructive floods. The applied model revealed that 25-, 50-, and 100-year storms produced runoff volumes of 2461.8 × 103, 4299.6 × 103, and 5204.5 × 103 m3 for An-Nawayah and 6212 × 103, 8129.4 × 103, and 10,330.6 × 103 m3 for Al-Rashrash, respectively. Flood risk levels, categorised as high (35.6%), extreme (21.9%), and medium (21.12%) were assessed in low- and very-low-hazard areas. The study highlighted that the areas closer to the Nile River mouth faced greater flood impacts from torrential rain. Our findings demonstrate the effectiveness of these methods in assessing and predicting flood risk. As a mitigation measure, this study recommends the construction of five 10 m high dams to create storage lakes. This integrated approach can be applied to flood risk assessment and mitigation in comparable regions.

show abstract

Enhancing flood risk assessment through integration of ensemble learning approaches and physical-based hydrological modeling

Cited by 27 publications

References 123 publications

Improving Structural MRI Preprocessing with Hybrid Transformer GANs

Improving Structural MRI Preprocessing with Hybrid Transformer GANs

Revisiting Urban Resilience: A Systematic Review of Multiple-Scale Urban Form Indicators in Flood Resilience Assessment

Integrated Hydrological Modeling for Watershed Analysis, Flood Prediction, and Mitigation Using Meteorological and Morphometric Data, SCS-CN, HEC-HMS/RAS, and QGIS

Contact Info

Product

Resources

About