Modelling hybrid and backpropagation adaptive neuro-fuzzy inference systems for flood forecasting

The ability of the adaptive neuro-fuzzy inference algorithm architecture to simulate floods is explored in this research. The development of models for flood forecasting has been centered on two adaptive neuro-fuzzy inference (ANFIS) algorithms. The Takagi–Sugeno fuzzy inference systems (FIS) genera...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Natural hazards (Dordrecht) Ročník 108; číslo 1; s. 519 - 566
Hlavní autoři: Tabbussum, Ruhhee, Dar, Abdul Qayoom
Médium: Journal Article
Jazyk:angličtina
Vydáno: Dordrecht Springer Netherlands 01.08.2021
Springer Nature B.V
Témata:
Adaptive algorithms
Adaptive systems
Algorithms
Artificial neural networks
Back propagation
Civil Engineering
Clustering
Earth and Environmental Science
Earth Sciences
Environmental Management
Flood forecasting
Flood predictions
Floods
Fuzzy logic
Fuzzy systems
Geophysics/Geodesy
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Inference
Mathematical models
Mean square errors
Natural Hazards
Original Paper
Performance evaluation
River discharge
Root-mean-square errors
Training
Gaussian membership function
Takagi–Sugeno fuzzy inference system
Hybrid learning algorithm
Backpropagation learning algorithm
Subtractive clustering
Adaptive neuro-fuzzy inference system
ISSN:0921-030X, 1573-0840
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The ability of the adaptive neuro-fuzzy inference algorithm architecture to simulate floods is explored in this research. The development of models for flood forecasting has been centered on two adaptive neuro-fuzzy inference (ANFIS) algorithms. The Takagi–Sugeno fuzzy inference systems (FIS) generated through subtracted clustering were trained using hybrid and backpropagation training algorithms. Multiple statistical performance evaluators were used to assess the performability of the established models. The validity and predictive power of the models are evaluated by estimating a flood occurrence in the study area. In designing the models, a total of 12 inputs were employed. The best performability was found for the ANFIS model created utilizing a hybrid training algorithm with mean square error (MSE) of 0.00034, co-efficient of correlation ( R 2 ) of 97.066%, root mean square error (RMSE) of 0.018, Nash–Sutcliffe model efficiency (NSE) of 0.968, mean absolute error (MAE) of 0.0073 and combined accuracy (CA) of 0.018, indicating the possible usage of exploiting the established model for prediction of floods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0921-030X
1573-0840
DOI:10.1007/s11069-021-04694-w