Frequency analysis of extreme flows using an Artificial Neural Network (ANN) model case Western High Atlas - Morocco

被引：0
作者：
Abdelhafid El Alaoui El Fels
NourEddine Alaa
Ali Bachnou
Oussama El Barrimi
机构：
[1] Cadi Ayyad University,Department of Earth Sciences, Faculty of Science and Technics Gueliz, Laboratory of Geosciences and Environnement
[2] Cadi Ayyad University,Department of Math and informatics, Faculty of Science and Technics Gueliz, Laboratory Applied Mathematics and informatics
[3] Sidi Mohamed Ben Abdellah University,LAMA Laboratory, Faculty of Sciences Dhar El Mahraz
来源：
Earth Science Informatics | 2022年 / 15卷
关键词：
Flood; Frequency analysis; Artificial neural networks; Western high atlas;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The definition of flood protection plans in semi-arid mountain environments requires awareness of the hazard, its assessment and the analysis of its probabilities of occurrence. The study carried out made it possible to highlight the use of artificial neural networks (ANN) in the frequency analysis of extreme flows. This is made possible by a comparative approach between 14 Probability Distributions and the ANN model. The results of the frequency analysis according to the two models shows a predictive priority of the ANN with an average performance criterion of Nash that exceeds 0.9 in the different basins studied. The study reveals that the specificities of the use of ANN compared to the deterministic models in the frequency analysis is that ANN highlights the sensitivity of the extreme river flood to the physiographic variations of each watershed. This feature allows to include the predictions of extreme events in the different basins studied into a single model and makes them more accurate.
引用
收藏
页码：965 / 978
页数：13
相关论文
共 138 条
  • [1] Adamowski J(2010)Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semiarid watersheds J Hydrol 390 85-91
  • [2] Sun K(1988)Log-logistic flood frequency analysis J Hydrol 98 205-224
  • [3] Ahmad MI(1974)A new look at the statistical model identification IEEE Trans Autom Control 19 716-723
  • [4] Sinclair CD(1952)Asymptotic theory of certain “goodness of fit” criteria based on stochastic processes Ann Math Stat 23 193-212
  • [5] Werrity A(2006)Fitting the log-logistic distribution by generalized moments Journal of Hydrology 328 694-703
  • [6] Akaike H(2011)How reliable are projections of future flood damage? Nat Hazards Earth Syst Sci 11 3293-3306
  • [7] Anderson TW(2014)Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature Geosci Model Dev 7 1247-1250
  • [8] Darling DA(2008)Understanding hydrological processes with scarce data in a mounain environment Hydrol Process 22 1908-1921
  • [9] Ashkar F(2017)Entropy-based derivation of generalized distributions for hydrometeorological frequency analysis J Hydrol 557 699-712
  • [10] Mahdi S(2018)The rise of deep learning in drug discovery Drug Discov Today 23 1241-1250
12345678910