Comparative analysis of fuzzy inference systems for water consumption time series prediction

Fırat, Mahmut; Turan, Mustafa Erkan; Yurdusev, Mehmet Ali

doi:10.1016/j.jhydrol.2009.06.013

Cited by 89 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In adaptive neuro-fuzzy inference system (ANFIS) the membership functions (MFs) parameters are fitted to a dataset through a hybrid learning algorithm (George & Ioana, 2007). ANFIS eliminates the problem of defining the membership function (MF) parameters and design of if-then rules in fuzzy system design by using the learning capability of ANN for automatic fuzzy rule generation and parameter optimization (Firat, Turan, & Yurdusev, 2009). Besides, ANFIS has the advantage of allowing the extraction of fuzzy rules from numerical data.…”

Section: Anfis Techniquementioning

confidence: 99%

“…More recently, literature has found the application of ANFIS in many fields, such as, regional electricity loads, ophthalmology, reservoir operation, wind speed, evaporation, river flow prediction, etc. (Galavi & Shui, 2012), (Altunkaynak, Ozger, & Cakmakci, 2005), (Firat, Turan, & Yurdusev, 2009), (Bushara & Abraham, 2015), (Kuamr & Kalavathi, 2016) and (Dastorani, Afkhami, Sharifidarani, & Dastorani, 2010). Many successful applications demonstrate that, with the advantages of good generality and predict accuracy; ANFIS is an efficient and promising approach in hydrological forecasting.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hydrological Time Series Forecasting Using Anfis Models With Aid of Wavelet Transform

Ibrahim

Mustafa

Rashid

2017

juod

View full text Add to dashboard Cite

The precise and accurate models of hydrological time series that are embedded with high complexity, nonstationarity, and non-linearity in both spatial and temporal scales can provide important information for decision-making in water resources management and environmental related issues. Hybrid wavelet transform (WT) and adaptive neuro-fuzzy inference system (ANFIS) has been used in this study to improve the forecasting capability of ANFIS model by decomposing the time series into sub-time series (approximation and details) using wavelet transform then combining the effective and significant time lags of sub-time series to form a set of input variables. The present study attempts to add the effective and significant time lags of original time series as extra variables to the input variables set. In addition, different combinations of variables, 1-3, from the set of input variables as inputs to the ANFIS model were used to forecast the time series.To examine the potential of the approach for practical applications, the model is applied to forecast, one step-ahead, the monthly data of hydrological time series (rainfall, evaporation, minimum and maximum temperature, average wind speed and reservoir inflow) for Kirkuk, Sulaimani, Dokan and Darbandikhan meteorological stations in Iraq. The best fit models were selected using the coefficient of determination ( ) and root mean square error ( ). Based on the results, the proposed model has high performance in forecasting the monthly minimum and maximum temperature, evaporation and reservoir inflow with values ranged from 0.93 to 0.99 and relatively good performances in forecasting the monthly rainfall and average wind speed with values ranged from 0.77 to 0.93.

show abstract

Section: Anfis Techniquementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hydrological Time Series Forecasting Using Anfis Models With Aid of Wavelet Transform

Ibrahim

Mustafa

Rashid

2017

juod

View full text Add to dashboard Cite

show abstract

“…During the last decade or so, fuzzy logic approach has been used in hydrological applications (e.g. Liong et al, 2000;Şen and Altunkaynak, 2006;Firat et al, 2009;Turan and Yurdusev, 2014;Jayawardena et al, 2014). More recently, adaptive neuro-fuzzy system, or ANFIS (Jang, 1993) which has the advantages of both neural networks and fuzzy reasoning techniques has found applications in hydrology including river flow forecasting (Chiang et al, 2004;Vernieuwe, 2005;Chang and Chang, 2006;Aqil et al, 2007;Firat et al, 2009;Keskin et al, 2006;Nayak et al, 2004;Talei et al, 2010;Sanikhani and Kisi, 2012;Badrzadeh et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Hourly runoff forecasting for flood risk management: Application of various computational intelligence models

Badrzadeh

Sarukkalige

Jayawardena

2015

Journal of Hydrology

View full text Add to dashboard Cite

“…To overcome this shortcoming, using the fuzzy logic in water resources problems under uncertainty is highly recommended (Araghinejad 2014). There have been numerous studies in the literature using fuzzy logic for the solution of such water problems like prioritization of restoring strategies for facing Lake Urmia shrinkage (Azarnivand et al 2014), groundwater pollution assessment (Aryafar et al 2013), monthly runoff forecasting (Ren et al 2013), rainfall-runoff modelling (Wang and Altunkaynak 2012;Casper et al 2007), prediction of water consumption time series (Firat et al 2009), evaporation estimation (Terzi et al 2006;Moghaddamnia et al 2009), regional flood frequency analysis (Shu and Ouarda 2008), and prediction of water level in reservoirs (Chang and Chang 2006).…”

Section: Introductionmentioning

confidence: 99%

Groundwater quality assessment with respect to fuzzy water quality index (FWQI): an application of expert systems in environmental monitoring

2015

View full text Add to dashboard Cite

Water quality degradation affects socio-economic development inappropriately and has dire effects on human health too. Water quality indexes (WQIs) are the methods widely used for modelling water quality status. However, using these indexes is limited by some constraints like deficiency of necessary database or uncertainty of decision-making. Throughout the ongoing research, fuzzy water quality indexes (FWQIs) were developed based on the Mamdani fuzzy inference system (FIS) to overcome the above-mentioned limitations. In other words, seven FWQIs models with different water quality parameters have been developed based on triangular and trapezoidal membership functions. Later, the developed indexes were employed to evaluate the water quality of 17 wells in Saveh Plain, Iran. Compared to the conventional WQI, the results showed that the elimination of some needed parameters in development of FWQI did not decrease the accuracy of water quality classification. However, omitting some other parameters with undesirable values made the classification of water quality unreliable. According to the results, some 35 % of wells benefitted from proper drinking water quality, while approximately 30 and 35 % of them suffered from unsuitable and very poor drinking water quality, respectively.

show abstract

Comparative analysis of fuzzy inference systems for water consumption time series prediction

Cited by 89 publications

References 16 publications

Hydrological Time Series Forecasting Using Anfis Models With Aid of Wavelet Transform

Hydrological Time Series Forecasting Using Anfis Models With Aid of Wavelet Transform

Hourly runoff forecasting for flood risk management: Application of various computational intelligence models

Groundwater quality assessment with respect to fuzzy water quality index (FWQI): an application of expert systems in environmental monitoring

Contact Info

Product

Resources

About