Fuzzy neural networks for water level and discharge forecasting with uncertainty

Alvisi, Stefano; Franchini, Marco

doi:10.1016/j.envsoft.2010.10.016

Cited by 106 publications

(69 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies have used all of their wavelet sub-series [ADA- MOWSKI, SUN 2010;NOURANI et al 2009;WANG, DING 2003] whereas others have removed the db1 sub-series and added the remaining series, considering the former series as noise due to its low correlation with their original data [KISI, CIMEN 2011;PARTAL, KIŞI 2007;RAJAEE et al 2010]. However, in some studies, new wavelet time-series were developed by adding up the effective DWCs based on regression correlation [TIWARI, CHATTERJEE 2010b;2011]. As it is wise not to completely rely on a model based on a particular wavelet series that captures some phenomena at the expense of others [RATHINASAMY et al 2013], we considered each wavelet function in terms of its own strengths in capturing stochastic characteristics and physical structure of the hydrological dataset.…”

Section: Elm Elm B and Elm W Model Developmentmentioning

confidence: 99%

“…In earlier studies [ADAMOWSKI, SUN 2010;KIŞI 2010;TIWARI, CHATTERJEE 2010a;2011], the significant wavelet sub-time series of a particular time series was used and added to generate a new time series, becoming new inputs with which to develop the ANN W model. In this study, a threshold allowable correlation level of 0.1 was used in determining the inclusion and use of all DWCs in the model development process.…”

Section: Ann B and Ann W Model Developmentmentioning

confidence: 99%

“…Other hybrid methods proposed in the hydrological forecasting literature are the bootstrap-based ANN (ANN B ) [TIWARI, CHATTERJEE 2010a, b], fuzzy neural networks [ALVISI, FRANCHINI 2011], and grey neural networks [ALVISI, FRANCHINI 2012]. Besides reducing uncertainty in the variance by mimicking randomness [EFRON, TIBSHIRANI 1993], ANN B models are simpler and easier to use in addressing uncertainty in an operational setting compared to Bayesian approaches [ISUKAPALLI, GEOR-GOPOULOS 2001].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Water demand forecasting using extreme learning machines

Tiwari¹,

Adamowski²,

Adamowski³

2016

Journal of Water and Land Development

View full text Add to dashboard Cite

The capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELM W , ELM B ), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANN W , ANN B ). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELM B and ANN B models provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANN W and ELM W models provided greater accuracy, with the ELM W model outperforming the ANN W model. Significant improvement in peak urban water demand prediction was only achieved with the ELM W model. The superiority of the ELM W model over both the ANN W or ANN B models demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.

show abstract

Section: Elm Elm B and Elm W Model Developmentmentioning

confidence: 99%

Section: Ann B and Ann W Model Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Water demand forecasting using extreme learning machines

Tiwari¹,

Adamowski²,

Adamowski³

2016

Journal of Water and Land Development

View full text Add to dashboard Cite

show abstract

“…It is done to understand the future hydrological regimes, then further guide various practical water activities, such as safe yield computations, hydrological and hydraulic designs, and water resources planning and management [1,2]. Currently, there have been a great number of relevant studies, and many methods and models, generally called data-driven models, can be used for the topic [3][4][5]. The basic idea of data-driven models is to use certain mathematical tools to describe correlations of hydrological variables, without requiring modeling of the internal structure of a watershed system [4,6,7].…”

Section: Introductionmentioning

confidence: 99%

Discussion on the Choice of Decomposition Level for Wavelet Based Hydrological Time Series Modeling

Sang

Liu

Wang

2016

Water

View full text Add to dashboard Cite

Abstract:The combination of wavelet analysis methods with data-driven models is a prevalent approach to conducting hydrological time series forecasting, but the results are affected by the accuracy of the wavelet decomposition of the series. The choice of decomposition level is one of the key factors for the wavelet decomposition. In this paper, the data of daily precipitation and streamflow time series measured in the upper reach of the Heihe River Basin in Northwest China were used as an example, and the influence of the decomposition level on wavelet-based hydrological time series forecasting was investigated. The true components of the precipitation series were identified, and the modeling results using 10 decomposition levels and two decomposition types were compared. The results affirmed that the wavelet-based modeling performance is sensitive to the choice of decomposition level, which is determined by the time series analyzed, but has no relation with the decomposition type used. The essence of the choice of decomposition level is to reveal the complex variability of hydrological time series under multi-temporal scales, and first knowing the true components of series could guide the choice of decomposition level. Through this study, the relationship among original series' characteristics, the choice of decomposition level, and the accuracy of wavelet-based hydrological time series forecasting can be more clearly understood, and it can be an improvement for wavelet-based data-driven modeling.

show abstract

“…Their approach is more effective in the training of RBFNN leading to improved performance with respect to other clustering algorithms. Alvisi and Franchini [2] proposed an approach under uncertainty using NN for water level (or discharge) forecasting. The parameters of the NN, i.e., the weights and biases, are represented by fuzzy numbers.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy radial basis function network for fuzzy regression with fuzzy input and fuzzy output

Pehlivan

Apaydin

2016

Complex Intell. Syst.

View full text Add to dashboard Cite

In this study, fuzzy regression (FR) models with fuzzy inputs and outputs are discussed. Some of the FR methods based on linear programming and fuzzy least squares in the literature are explained. Within this study, we propose a Fuzzy Radial Basis Function (FRBF) Network to obtain the estimations for FR model in the case that inputs and outputs are symmetric/nonsymmetric triangular fuzzy numbers. Proposed FRBF Network approach is a fuzzification of the inputs, outputs and weights of traditional RBF Network and it can be used as an alternative to FR methods. The FRBF Network approach is constructed on the basis of minimizing the square of the total difference between observed and estimated outputs. A simple training algorithm from the cost function of the FRBF Network through Backpropagation algorithm is developed in this study. The advantage of our proposed approach is its simplicity and easy computation as well as its performance. To compare the performance of the proposed method with those given in the literature, three numerical examples are presented.

show abstract

Fuzzy neural networks for water level and discharge forecasting with uncertainty

Cited by 106 publications

References 44 publications

Water demand forecasting using extreme learning machines

Water demand forecasting using extreme learning machines

Discussion on the Choice of Decomposition Level for Wavelet Based Hydrological Time Series Modeling

Fuzzy radial basis function network for fuzzy regression with fuzzy input and fuzzy output

Contact Info

Product

Resources

About