Flood frequency analysis at ungauged catchments with the GAM and MARS approaches in the Montreal region, Canada

Msilini, Amina; Charron, Christian; Ouarda, Taha B. M. J.; Masselot, Pierre

doi:10.1080/07011784.2022.2044385

Cited by 4 publications

(5 citation statements)

References 34 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ungauged catchments are distributed worldwide in dry and humid environments [88]. For example, the catchment of the Imjin is extended between North and South Korea, classified as one the most critical basins in Korea, and management of flood there is hard to do due to the limitation and sharing of hydrology data between North and South Korea [92]. In Russia, a large country in Asia, nearly 2.6 million streams are still recorded as ungauged or poorly observed data [93], and they developed a hydrology model Multi-Layer Conceptual Model, 3rd generation) (MLCM3) by the Russian State Hydrometeorological University.…”

Section: Ungauged Catchmentsmentioning

confidence: 99%

Investigation of Runoff and Flooding in Urban Areas based on Hydrology Models: A Literature Review

2024

IJG

View full text Add to dashboard Cite

Hydrological models significantly estimate water movements and their distribution at local and catchment sizes. They have been used to simulate the relative between rainfall and runoff. They enhance city planners and hydrology communities to investigate the complex relationship between precipitation and runoff in catchment and city sizes. Water movement is a vital matter, especially on the ground. This study reviews several hydrological modeling studies in different environments, including spatial analysis in the Watershed Modelling System (WMS). It seeks to consider only the most critical Hydrology and Hydraulic Modelling to investigate water in a watershed. Furthermore, this review gives a fundamental understanding of the empirical hydrology methods used to calculate runoff and a brief for 2D denominational. This review found that Hydrology Modelling is based on a) Loss Methods, b) Direct Run-off, and c) 2 Dimensional. This review concluded that the popular hydrology models applied in different environments are the Hydrologic Engineering Center-Hedrologic Modeling System (HEC-HMS) and Soil Water Assessment Tool (SWAT). Also, Hydrologic Engineering Center-River Analysis System (HEC-RAS) sites are at the top of the hydraulic water depth (1D) and water Distributed (2D) models to assess flood plans. Hydrological models became a postnatal application to understand flood risk in both gauged and ungauged catchments.

show abstract

Section: Ungauged Catchmentsmentioning

confidence: 99%

Investigation of Runoff and Flooding in Urban Areas based on Hydrology Models: A Literature Review

2024

IJG

View full text Add to dashboard Cite

show abstract

“…Several studies have used artificial intelligence‐based techniques to address regional flood frequency analysis issues (e.g. Alobaidi et al, 2015; Aziz et al, 2014, 2015, 2017; Dawson et al, 2006; Desai & Ouarda, 2021; Msilini et al, 2022; Ouarda & Shu, 2009 and Shu & Ouarda, 2007, 2008), and these studies have shown that nonlinear techniques usually outperform linear ones. GAMs have also recently been used in regional flood frequency analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Hydrological processes, including nonlinearity, are inherently complex in a variety of ways (Chebana et al, 2014; Desai & Ouarda, 2021; Msilini et al, 2022; Ouarda et al, 2018). In many cases, the linearity assumption in hydrology is violated; for example, larger catchments behave differently than smaller ones, and drier antecedent catchment states produce relatively less runoff for a given rainfall than wetter ones.…”

Section: Introductionmentioning

confidence: 99%

“…Many methodologies for both regionalization of dimensionality reduction and hydrological transfer techniques have been proposed (e.g. Desai & Ouarda, 2021; Hosking & Wallis, 1997; Msilini et al, 2022; Ouarda et al, 2008; Wazneh et al, 2015). Canonical correlation analysis (CCA) is one of the most widely used methods for dimension reduction in which linear combinations of variables within the same group are identified; for the first pair of canonical variates, the CCA searches for a pair of linear variates to maximize the correlation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dimensionality reduction for regional flood frequency analysis: Linear versus nonlinear methods

Haddad

Rahman

2023

Hydrological Processes

View full text Add to dashboard Cite

Regional flood frequency analysis is still an important area of hydrology research as there are many ungauged catchments. The majority of hydrological methods in regional flood frequency analysis involve complex non‐linear relationships between predictor variables and flood characteristics. In the past, dimensionality reduction techniques based on linear methods such as canonical correlation analysis (CCA) were used in regional flood frequency analysis to delineate hydrological clusters. Non‐linear dimensionality reduction techniques, such as KCCA and multidimensional scaling (MDS), have been used in several fields of science, but not explicitly in regional flood frequency analysis. To determine hydrologically similar clusters, the approaches considered in this article use CCA, KCCA, and MDS as dimensionality reduction techniques in conjunction with Gaussian mixture models (GMM). Log‐linear regression and generalized additive models are then applied to the hydrological clusters to evaluate regional flood frequency analysis. A comparison of linear and non‐linear (NL) methods is performed using data from Victoria, Australia, to demonstrate the benefit of these methods. It has been found that the non‐linear frameworks of multi‐dimensional scaling with Gaussian mixture model‐non‐linear (MDSGMM‐NL) and KCCA with Gaussian mixture model‐non‐linear (KCCAGMM‐NL), as well as the mixed frameworks (i.e. KCCA and Gaussian mixture model‐non‐linear [CCAGMM‐NL]), can be used to represent the non‐linear complexities of hydrological processes in regional flood frequency analysis.

show abstract

“…This is problematic for our application as typical hydrologic data sets used in regional analyses contain a large number of candidate variables, many of which are highly correlated. For these reasons, current applications of GAMs to flood quantiles commonly rely on backwards stepwise selection (Chebana et al, 2014;Rahman et al, 2018;Noor et al, 2022;Msilini et al, 2022) sometimes coupled with a pre-selection step as in Dubos et al (2022). Backward selection approach used for GAMs has the potential to select appropriate covariates at the same rate as shrinkage approaches, but only when the information content of the data is high (Marra and Wood, 2011).…”

Section: Introductionmentioning

confidence: 99%

Regional index flood estimation at multiple durations with generalized additive models

Barna,

Engeland,

Kneib

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Estimation of flood quantiles at ungauged basins is often achieved through regression based methods. In situations where flood retention is important, e.g. floodplain management and reservoir design, flood quantile estimates are often needed at multiple durations. This poses a problem for regression-based models as the form of the functional relationship between catchment descriptors and the response may not be constant across different durations. A particular type of regression model that is well-suited to this situation is a generalized additive model (GAM), which allows for flexible, semi-parametric modeling and visualization of the relationship between predictors and the response. However, in practice, selecting predictors for such a flexible model can be challenging, particularly given the characteristics of available catchment descriptor datasets. We employ a machine learning-based variable pre-selection tool which, when combined with domain knowledge, enhances the practicality of constructing GAMs. In this study, we develop a GAM for index (median) flood estimation with the primary objective of investigating duration-specific differences in how catchment descriptors influence the median flood. As the accuracy of this explainable approach is dependent on the fitted GAM being adequate, the secondary objective of our study is prediction of the median flood at ungauged locations and multiple durations, where predictive performance and reliability at ungauged locations are used as proxies for adequacy of the GAM. Predictive performance of the GAM is compared to two benchmark models: the existing log-linear model for median flood estimation in Norway and a fully data-driven machine learning model (an extreme gradient boosting tree ensemble, XGBoost). We find that the predictive accuracy and reliability of the GAM matched or exceeded that of the benchmark models at both durations studied. Within the predictor set selected for this study, we observe duration-specific differences in the relationship between the median flood and the two catchment descriptors effective lake percentage and catchment shape. Ignoring these differences results in a statistically significant decline in predictive performance. This suggests that models developed and estimated for prediction of the index flood at one duration may have reduced performance when applied directly to situations outside of that specific duration.

show abstract

Flood frequency analysis at ungauged catchments with the GAM and MARS approaches in the Montreal region, Canada

Abstract: Flood frequency analysis at ungauged catchments with the GAM and MARS approaches in the Montreal region, Canada

Cited by 4 publications

References 34 publications

Investigation of Runoff and Flooding in Urban Areas based on Hydrology Models: A Literature Review

Investigation of Runoff and Flooding in Urban Areas based on Hydrology Models: A Literature Review

Dimensionality reduction for regional flood frequency analysis: Linear versus nonlinear methods

Regional index flood estimation at multiple durations with generalized additive models

Contact Info

Product

Resources

About