Successive-station monthly streamflow prediction using neuro-wavelet technique

Mehr, Ali Danandeh; Kahya, Ercan; Bagheri, Farzaneh; Deliktas, Ekin

doi:10.1007/s12145-013-0141-3

Cited by 39 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected from the performance of hybrid models in previous works for monthly forecasting (Partal 2009, Mehr et al 2013, the hybrid approach using only approximations as inputs outperformed the classical ANN model for all forecasting horizons tested for the Sobradinho Dam, São Francisco River basin in Brazil. Specifically, for 1 and 3 months ahead, the hybrid model considerably reduced the oscillations of the forecasts, fixed the lags, and correctly predicted the streamflow peaks.…”

Section: Discussionsupporting

confidence: 71%

“…They decomposed the time series eight times, used all details and approximations as inputs for the models, and concluded that the hybrid model is a promising tool for nonperennial rivers in semi-arid regions. Mehr et al (2013) investigated the WT-ANN technique for monthly predictions in the Çoruh River in the Black Sea Region using a downstream-upstream approach, and they compared it with the classical ANN. The results showed that, while both models performed well, the WT-ANN performed slightly better.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monthly streamflow forecasting using neuro-wavelet techniques and input analysis

Honorato

Silva

Santos

2018

Hydrological Sciences Journal

View full text Add to dashboard Cite

Combinations of low-frequency components (also known as approximations) resulting from the wavelet decomposition are tested as inputs to an artificial neural network (ANN) in a hybrid approach, and compared to classical ANN models for flow forecasting for 1, 3, 6 and 12 months ahead. In addition, the inputs are rewritten in terms of the flow, revealing what type of information was being provided to the network, in order to understand the effect of the approximations on the forecasting performance. The results show that the hybrid approach improved the accuracy of all tested models, especially for 1, 3 and 6 months ahead. The input analyses show that high-frequency components are more important for shorter forecast horizons, while for longer horizons, they may worsen the model accuracy.

show abstract

Section: Discussionsupporting

confidence: 71%

Section: Introductionmentioning

confidence: 99%

Monthly streamflow forecasting using neuro-wavelet techniques and input analysis

Honorato

Silva

Santos

2018

Hydrological Sciences Journal

View full text Add to dashboard Cite

show abstract

“…It has recently been employed as a classic method in data mining to validate the superiority of artificial intelligence methods, such as ANFIS, extreme learning machine (ELM), ANN, etc. [26,[41][42][43][44][45]. The classic FFNN is trained with a backpropagation algorithm.…”

Section: Introductionmentioning

confidence: 99%

A Non-Tuned Machine Learning Technique for Abutment Scour Depth in Clear Water Condition

Bonakdari

Moradi

Ebtehaj

et al. 2020

Water

View full text Add to dashboard Cite

Abutment scour is a complex three-dimensional phenomenon, which is one of the leading causes of marine structure damage. Structural integrity is potentially attainable through the precise estimation of local scour depth. Due to the high complexity of scouring hydrodynamics, existing regression-based relations cannot make accurate predictions. Therefore, this study presented a novel expansion of extreme learning machines (ELM) to predict abutment scour depth (ds) in clear water conditions. The model was built using the relative flow depth (h/L), excess abutment Froude number (Fe), abutment shape factor (Ks), and relative sediment size (d50/L). A wide range of experimental samples was collected from the literature, and data was utilized to develop the ELM model. The ELM model reliability was evaluated based on the estimation results and several statistical indices. According to the results, the sigmoid activation function (correlation coefficient, R = 0.97; root mean square error, RMSE = 0.162; mean absolute percentage error, MAPE = 7.69; and scatter index, SI = 0.088) performed the best compared with the hard limit, triangular bias, radial basis, and sine activation functions. Eleven input combinations were considered to investigate the impact of each dimensionless variable on the abutment scour depth. It was found that ds/L = f (Fe, h/L, d50/L, Ks) was the best ELM model, indicating that the dimensional analysis of the original data properly reflected the underlying physics of the problem. Also, the absence of one variable from this input combination resulted in a significant accuracy reduction. The results also demonstrated that the proposed ELM model significantly outperformed the regression-based equations derived from the literature. The ELM model presented a fundamental equation for abutment scours depth prediction. Based on the simulation results, it appeared the ELM model could be used effectively in practical engineering applications of predicting abutment scour depth. The estimated uncertainty of the developed ELM model was calculated and compared with the conventional and artificial intelligence-based models. The lowest uncertainty with a value of ±0.026 was found in the proposed model in comparison with ±0.50 as the best uncertainty of the other models.

show abstract

“…In this study, the Çoruh river basin, located in eastern Black Sea region in Turkey (see Figure 1), was selected as the area of interest. The Çoruh river originates from Mescit Mountains in the Bayburt Province and flows through the East Anatolia into the Black Sea near Batumi City in Georgia, after its main course of 431 km [27]. The total drainage area of the basin is about 21,000 km 2 , and 91% of this area is located in Turkey, and the remaining is in Georgia [28].…”

Section: Study Area and Datamentioning

confidence: 99%

Multivariate Assessment of Low-Flow Hazards via Copulas: The Case Study of the Çoruh Basin (Turkey)

Tosunoğlu

Salvadori

Yılmaz

2020

Water

View full text Add to dashboard Cite

Bivariate modeling and hazard assessment of low flows are performed exploiting copulas. 7-day low flows observed, respectively, in the upper, middle and lower parts of the Çoruh basin (Turkey) are examined, considering three pairs of certified stations located in different sub-basins. A thorough statistical analysis indicates that the GEV distribution can be used to model the marginal behavior of the low-flow. The joint distributions at each part are modeled via a dozen of copula families. As a result, the Husler–Reiss copula adequately fits the joint low flows in the upper part, while the t-Student copula turns out to best fit the other parts. In order to assess the low-flow hazard, these copulas are then used to compute joint return periods and failure probabilities under a critical bivariate “AND” hazard scenario. The results indicate that the middle and lower parts of the Çoruh basin are likely to experience the largest drought hazards. As a novelty, the statistical tools used allow to objectively quantify drought threatening in a thorough multivariate perspective, which involves distributional analysis, frequency analysis (return periods) and hazard analysis (failure probabilities).

show abstract

Successive-station monthly streamflow prediction using neuro-wavelet technique

Cited by 39 publications

References 57 publications

Monthly streamflow forecasting using neuro-wavelet techniques and input analysis

Monthly streamflow forecasting using neuro-wavelet techniques and input analysis

A Non-Tuned Machine Learning Technique for Abutment Scour Depth in Clear Water Condition

Multivariate Assessment of Low-Flow Hazards via Copulas: The Case Study of the Çoruh Basin (Turkey)

Contact Info

Product

Resources

About