Regional Flood Frequency Analysis Through Some Machine Learning Models in Semi-arid Regions

Allahbakhshian-Farsani, Pezhman; Vafakhah, Mehdi; Khosravi-Farsani, Hadi; Hertig, Elke

doi:10.1007/s11269-020-02589-2

Cited by 32 publications

(11 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Jingi and Hall [23] compared the results of ANN with several linear methods and reported that the ANN-based method outperformed the linear methods. Since 2004, AI-based methods have gained popularity among hydrologists such as support vector machine (SVM) and ANN methods [25,26]. Different combinations of ANN and SVM have been proposed for countries such as Iran, Canada and Australia [27,28].…”

Section: Introductionmentioning

confidence: 99%

Comparing Performance of ANN and SVM Methods for Regional Flood Frequency Analysis in South-East Australia

Zalnezhad

Rahman

Nasiri³

et al. 2022

Water

Self Cite

View full text Add to dashboard Cite

Design flood estimations at ungauged catchments are a challenging task in hydrology. Regional flood frequency analysis (RFFA) is widely used for this purpose. This paper develops artificial intelligence (AI)-based RFFA models (artificial neural networks (ANN) and support vector machine (SVM)) using data from 181 gauged catchments in South-East Australia. Based on an independent testing, it is found that the ANN method outperforms the SVM (the relative error values for the ANN model range 33–54% as compared to 37–64% for the SVM). The ANN and SVM models generate more accurate flood quantiles for smaller return periods; however, for higher return periods, both the methods present a higher estimation error. The results of this study will help to recommend new AI-based RFFA methods in Australia.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparing Performance of ANN and SVM Methods for Regional Flood Frequency Analysis in South-East Australia

Zalnezhad

Rahman

Nasiri³

et al. 2022

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, Weierbach et al (2020) compared the performance of SVM, RF, and multiple linear regression in predicting monthly water stream temperature and found that SVM performed well overall, although RF struggled with predicting extreme values. Allahbakhshian‐Farsani et al (2020) applied SVM, MARS, and boosted regression tree in regional frequency analysis and demonstrated that the SVM model with a radial basis function (RBF) kernel had the best performance. Quan et al (2022) employed both SVM and the genetic algorithm (GA) to predict the water temperature of large high‐altitude reservoirs in western China, providing insights into predicting vertical water temperature at different depths.…”

Section: Introductionmentioning

confidence: 99%

Machine‐learning modeling of hourly potential thermal refuge area: A case study from the Sainte‐Marguerite River (Quebec, Canada)

Hani

St‐Hilaire

Ouarda

2023

River Research & Apps

View full text Add to dashboard Cite

To understand the temporal and spatial variability of thermal refuges, this study focused on modeling potential thermal refuge area (PTRA) at a sub‐daily time‐step in two tributary confluences of the Sainte‐Marguerite River (Canada) during the summers of 2020 and 2021. Aquatic ectotherm species, such as Atlantic salmon (Salmo salar), seek these refuges to avoid heat stress during high summer river temperatures. To investigate the temporal variability of these PTRA, we employed inverse weighted distance interpolation to delineate the hourly area available at both confluences. We then analyzed the impact of the atypical low flow conditions of summer 2021 on the diel cycle of PTRA extremes using the coefficient of variation and the generalized additive model (GAM). Finally, we used four supervised machine‐learning regression models and three to five hydrometeorological predictors to estimate hourly PTRA availability: multivariate adaptive splines regression (MARS), GAM, support vector machine regression (SVM), and random forest regression (RF). The results showed that tree‐based and kernel‐based regression models, RF and SVM, outperformed GAM and MARS. RF had the highest accuracy at both sites, with a relative root mean square error and Nash–Sutcliffe efficiency coefficient (Nash) of 13% and 93%, respectively. Our study discovered that under warm conditions in August 2021, small perennial tributary inflows in combination with low mainstem discharge could create high and constant PTRA at confluences, potentially providing vital thermal refuges for cold‐water taxa. These refuges may be especially important at the local level, within a specific stretch or section of the river. Given the decreasing availability of thermal refuges for salmonids, it is crucial to monitor stream temperatures at small spatial and temporal scales using data‐driven techniques in order to understand stream temperature heterogeneity at tributary confluences.

show abstract

“…The data are then analysed to find a projection that reflects the structure or features of the original high-dimensional data. It has been widely used in EGE assessment because of its strong resistance to anthropogenic disturbance, good robustness, and high accuracy (Allahbakhshian et al, 2020). Nevertheless, the integration of catastrophe theory with PPM has scarcely been applied to EES evaluation.…”

Section: Introductionmentioning

confidence: 99%

A method for spatio-temporal process assessment of eco-geological environmental security in mining areas using catastrophe theory and projection pursuit model

Shao

Sun

Lin

et al. 2021

Progress in Physical Geography: Earth and Environment

View full text Add to dashboard Cite

It is a universal problem that the eco-geological environment has been damaged by mineral resources exploitation. The accurate evaluation of eco-geological environmental security (EES) in mining areas is essential for restoring the environment of the mining area. However, a robust approach to obtaining an accurate evaluation of ESS has not yet been produced due to the complex spatio-temporal process of EES. Here, we developed a new method for enabling the quantitative evaluation of the EES spatio-temporal process. The EES evaluation index system of mining areas was established from both natural and anthropogenic aspects. The EES evaluation method was developed by combining the catastrophe theory and projection pursuit model (PPM). Then, with the support of remote sensing (RS) and a geographic information system (GIS), the method was applied to evaluate the spatio-temporal process of EES in Panxi mining area. The bifurcation curve and receiver operating characteristic curve were used to verify the developed method. The results showed that this method could accurately evaluate the spatio-temporal process of EES in a mining area and could successfully recognise the threshold value to distinguish the safe status and unsafe status. Strong spatio-temporal variations of EES in Panxi area were found, which may be the result of the combined effect of multiple factors (e.g. mineral resource exploitation, soil erosion, and ecological restoration). In summary, the combination of catastrophe theory and PPM with RS and GIS to quantitatively evaluate the spatio-temporal process of EES in mining areas is a robust method.

show abstract

Regional Flood Frequency Analysis Through Some Machine Learning Models in Semi-arid Regions

Cited by 32 publications

References 61 publications

Comparing Performance of ANN and SVM Methods for Regional Flood Frequency Analysis in South-East Australia

Comparing Performance of ANN and SVM Methods for Regional Flood Frequency Analysis in South-East Australia

Machine‐learning modeling of hourly potential thermal refuge area: A case study from the Sainte‐Marguerite River (Quebec, Canada)

A method for spatio-temporal process assessment of eco-geological environmental security in mining areas using catastrophe theory and projection pursuit model

Contact Info

Product

Resources

About