Flood flow forecasting using ANN, ANFIS and regression models

Basit Öğe Kaydı
dc.authoridRezaeianzadeh, Mehdi/0000-0001-8108-8515|Tabari, Hossein/0000-0003-2052-4541|Kalin, Latif/0000-0001-9562-8834
dc.contributor.authorRezaeianzadeh, M.
dc.contributor.authorTabari, H.
dc.contributor.authorYazdi, A. Arabi
dc.contributor.authorIsik, S.
dc.contributor.authorKalin, L.
dc.date.accessioned2025-10-24T18:08:49Z
dc.date.available2025-10-24T18:08:49Z
dc.date.issued2014
dc.departmentMalatya Turgut Özal Üniversitesi
dc.description.abstractFlood prediction is an important for the design, planning and management of water resources systems. This study presents the use of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), multiple linear regression (MLR) and multiple nonlinear regression (MNLR) for forecasting maximum daily flow at the outlet of the Khosrow Shirin watershed, located in the Fars Province of Iran. Precipitation data from four meteorological stations were used to develop a multilayer perceptron topology model. Input vectors for simulations included the original precipitation data, an area-weighted average precipitation and antecedent flows with one- and two-day time lags. Performances of the models were evaluated with the RMSE and the R (2). The results showed that the area-weighted precipitation as an input to ANNs and MNLR and the spatially distributed precipitation input to ANFIS and MLR lead to more accurate predictions (e.g., in ANNs up to 2.0 m(3) s(-1) reduction in RMSE). Overall, the MNLR was shown to be superior (R (2) = 0.81 and RMSE = 0.145 m(3) s(-1)) to ANNs, ANFIS and MLR for prediction of maximum daily flow. Furthermore, models including antecedent flow with one- and two-day time lags significantly improve flow prediction. We conclude that nonlinear regression can be applied as a simple method for predicting the maximum daily flow.
dc.description.sponsorshipCenter for Forest Sustainability through the Peaks of Excellence Program at Auburn University
dc.description.sponsorshipThe data used to carry out this research were provided by the Islamic Republic of Iran Meteorological Office (IRIMO) and Surface Water Office of Fars Regional Water Affair. The first author would like to especially thank Mr. Behzad Shifteh Somee, Prof. Alfred Stein, Dr. Amir AghaKouchak and Prof. Dawei Han for their gracious helps. The first author was partially funded by the Center for Forest Sustainability through the Peaks of Excellence Program at Auburn University.
dc.identifier.doi10.1007/s00521-013-1443-6
dc.identifier.endpage37
dc.identifier.issn0941-0643
dc.identifier.issn1433-3058
dc.identifier.issue1
dc.identifier.scopus2-s2.0-84902475668
dc.identifier.scopusqualityQ1
dc.identifier.startpage25
dc.identifier.urihttps://doi.org/10.1007/s00521-013-1443-6
dc.identifier.urihttps://hdl.handle.net/20.500.12899/3319
dc.identifier.volume25
dc.identifier.wosWOS:000338191300003
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer London Ltd
dc.relation.ispartofNeural Computing & Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20251023
dc.subjectMLP; Neuro-fuzzy; Regression analysis; Area-weighted precipitation; Antecedent flow; Iran
dc.titleFlood flow forecasting using ANN, ANFIS and regression models
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu