Evaluation of regional flood quantiles at ungauged sites by employing nonlinearity-based clustering approaches

Gnanaprakkasam, Shiyamalagowri; Ganapathy, Ganapathy Pattukandan

doi:10.1007/s11356-019-05473-8

Cited by 6 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been numerous ANN techniques developed to date, each of which may befit a specific application (e.g., self-organizing maps, recurrent neural networks, and feed-forward back-propagation neural networks). However, ANN is more commonly employed in predictive algorithms [54,56,57] and pattern recognition applications [23,36,55,58]. For the study presented herein, SOM was utilized using the Deep Learning Toolbox in MATLAB, where the Kohonen rule was adopted [55,59].…”

Section: Unsupervised Learning: Clusteringmentioning

confidence: 99%

Data-Driven Community Flood Resilience Prediction

Abdel-Mooty

El‐Dakhakhni

Coulibaly

2022

Water

View full text Add to dashboard Cite

Climate change and the development of urban centers within flood-prone areas have significantly increased flood-related disasters worldwide. However, most flood risk categorization and prediction efforts have been focused on the hydrologic features of flood hazards, often not considering subsequent long-term losses and recovery trajectories (i.e., community’s flood resilience). In this study, a two-stage Machine Learning (ML)-based framework is developed to accurately categorize and predict communities’ flood resilience and their response to future flood hazards. This framework is a step towards developing comprehensive, proactive flood disaster management planning to further ensure functioning urban centers and mitigate the risk of future catastrophic flood events. In this framework, resilience indices are synthesized considering resilience goals (i.e., robustness and rapidity) using unsupervised ML, coupled with climate information, to develop a supervised ML prediction algorithm. To showcase the utility of the framework, it was applied on historical flood disaster records collected by the US National Weather Services. These disaster records were subsequently used to develop the resilience indices, which were then coupled with the associated historical climate data, resulting in high-accuracy predictions and, thus, utility in flood resilience management studies. To further demonstrate the utilization of the framework, a spatial analysis was developed to quantify communities’ flood resilience and vulnerability across the selected spatial domain. The framework presented in this study is employable in climate studies and patio-temporal vulnerability identification. Such a framework can also empower decision makers to develop effective data-driven climate resilience strategies.

show abstract

Section: Unsupervised Learning: Clusteringmentioning

confidence: 99%

Data-Driven Community Flood Resilience Prediction

Abdel-Mooty

El‐Dakhakhni

Coulibaly

2022

Water

View full text Add to dashboard Cite

show abstract

“…Additionally, a relationship was drawn between the log function of the stream density of each district in Karnataka and the number of check dams (r2= 0.93, Figure 5). The stream density is characterised by Equation 2 [72].…”

Section: Data Acquisitionmentioning

confidence: 99%

Modelling Small-scale Storage Interventions in Semi-Arid India at the Basin Scale

Horan¹,

Wable²,

Srinivasan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, there has been renewed interest in the performance, functionality, and sustainability of traditional small-scale storage interventions (check dams, farm bunds and tanks) used across India for the improvement of local water security. The Central Groundwater Board of India is en-couraging the construction of such interventions for the alleviation of water scarcity. It is of critical importance to understand the hydrological effect of these interventions at basin scales to maximise their effectiveness. The quantification of small-scale interventions in hydrological modelling is often neglected, especially in large-scale modelling exercises. A bespoke version of the GWAVA model was developed to assess the impact of interventions on the water balance of the Cauvery Basin and two smaller sub-catchments. Model results demonstrate that farm bunds appear to have a negligible effect on the estimated average annual simulated streamflow at the outlets of the two sub-catchments and the basin whereas tanks and check dams have a more significant effect. In-terventions generally were found to increase evaporation losses across the catchment. The model adaption used in this study provides a step-change in the conceptualisation and quantification of the consequences of small-scale storage interventions in large- or basin-scale hydrological models.

show abstract

“…In recent decades, there is an increase in the use of cluster analysis procedures for regionalization of watersheds. The procedures include variants of hard (e.g., Burn & Goel, 2000; Rao & Srinivas, 2006a) and fuzzy K‐means partitional clustering (e.g., Basu & Srinivas, 2014; Jingyi & Hall, 2004; Rao & Srinivas, 2006b; Sadri & Burn, 2011), hierarchical (e.g., Chiang et al., 2002; Gnanaprakkasam & Ganapathy, 2019; Isik & Singh, 2008; Rao & Srinivas, 2006a; Wazneh et al., 2015), hybrid of hierarchical‐partitional (e.g., Isik & Singh, 2008; Rao & Srinivas, 2006a), neural network (e.g., Abdi et al., 2017; Razavi & Coulibaly, 2013; Srinivas & Tripathi, 2006), hybrid of neural network‐fuzzy partitional (e.g., Srinivas et al., 2008), entropy (e.g., Basu & Srinivas, 2016; Tongal & Sivakumar, 2017), and Gaussian mixture model (GMM)‐based clustering (e.g., Ahani et al., 2020). The procedures facilitate delineation of watersheds into the aforementioned three types of regions by discerning patterns in multidimensional space of watershed related characteristics/attributes (Rao & Srinivas, 2008).…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Ensemble Clustering Approach to Address Regionalization Uncertainties in Flood Frequency Analysis

Kiran

Srinivas

2021

Water Resources Research

View full text Add to dashboard Cite

Estimates of flood quantiles are necessary at various locations/hotspots in river basins for applications related to hydrological design and risk assessment of water resources systems. Desired flood quantiles could be estimated by frequency analysis of the available at-site data for locations having sufficient historical information on flows. However, for an ungauged or sparsely gauged location, the flood quantiles' prediction remains one of the challenging problems in hydrology. A variety of regional flood frequency analysis (RFFA) approaches are available for addressing this challenge. The approaches generally involve (i) regionalization, which refers to identification of a group of watersheds (i.e., region) resembling the target site's watershed in terms of attributes/characteristics influencing flood, and (ii) regional frequency analysis (RFA), which involves pooling of flood-related information from sites in the region and using it to estimate desired flood quantile(s) at the target site. Approaches to watershed regionalization for RFFA include those based on regression analysis (method of residuals), canonical correlation analysis (CCA), region of influence (ROI) and its extensions, hierarchical approach, and cluster analysis. Several articles and books provide an overview of the literature on regionalization of watersheds and issues related to RFA (e.g.,

show abstract

Evaluation of regional flood quantiles at ungauged sites by employing nonlinearity-based clustering approaches

Cited by 6 publications

References 29 publications

Data-Driven Community Flood Resilience Prediction

Data-Driven Community Flood Resilience Prediction

Modelling Small-scale Storage Interventions in Semi-Arid India at the Basin Scale

Fuzzy Ensemble Clustering Approach to Address Regionalization Uncertainties in Flood Frequency Analysis

Contact Info

Product

Resources

About