Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design

Shaghaghi, Saba; Bonakdari, Hossein; Gholami, Azadeh; Ebtehaj, Isa; Zeinolabedini, Maryam

doi:10.1016/j.amc.2017.06.012

Cited by 60 publications

(28 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In an attempt to address the issue of model bias faced by ANN, group method of data handling (GMDH), automatically synthesize network from the database of inputs and outputs. This process which is called self-organization of input models removes the user from specifying the network architecture in advance and hence removes biases in the model [22][23][24]. Reduced computational time is another advantage of the GMDH method as compared to the standard ANN.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

et al. 2020

View full text Add to dashboard Cite

Permeability is an important petrophysical parameter that controls the fluid flow within the reservoir. Estimating permeability presents several challenges due to the conventional approach of core analysis or well testing, which are expensive and time-consuming. On the contrary, artificial intelligence has been adopted in recent years in predicting reliable permeability data. Despite its shortcomings of overfitting and low convergence speed, artificial neural network (ANN) has been the widely used artificial intelligent method. Based on this, the present study conducted permeability prediction using the group method of data handling (GMDH) neural network from well log data of the West arm of the East African Rift Valley. Comparative analysis of GMDH permeability model and ANN methods of the back propagation neural network (BPNN) and radial basis function neural network (RBFNN) were further explored. The results of the study showed that the proposed GMDH model outperformed BPNN and RBFNN as it achieved R/root mean square error (RMSE) value of 0.989/0.0241 for training and 0.868/0.204 for predicting, respectively. Sensitivity analysis carried out revealed that shale volume, standard resolution formation density, and thermal neutron porosity were the most influential well log parameters when developing the GMDH permeability model.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The Soil and Water Assessment Tool (SWAT) can simulate water, sediment, and nutrient yield in a watershed by using input data from GIS and applying different agricultural practices, climate change, and land use (Bosch et al 2011;Makarewicz et al 2014;Schiefer et al 2013). Nowadays, the use of artificial intelligence methods as an approach to solving complex nonlinear prob-lems and lake level forecasting has increased (Myronidis et al 2012;Shafaei and Kisi 2016;Shaghaghi et al 2017;Shiri et al 2016;Wang et al 2009;Zaji et al 2018;Zeynoddin et al 2018). Another method of lake level fluctuation analysis and prediction is using data from long-term studies of ice phenology (Apsite et al 2014;Jensen et al 2007;Kostecki 2013;Nõges and Nõges 2014).…”

Section: Introductionmentioning

confidence: 99%

Spectral–time analysis of cycle fluctuations in lake water levels in Belarus and Poland

Volchak

Kirvel

Choiński

et al. 2020

Limnological Review

View full text Add to dashboard Cite

On the basis of the mean volume of annual water levels of 25 lakes (9 Belarusian and 16 Polish) over a period of 55 years (1956-2010) spectral time analysis of water fluctuations has been executed. The choice of the lakes was based on two factors, i.e. the continuous period of observation and insignificant anthropogenic influence. The complex analysis of water level fluctuation cycles has shown that for Belarus the cycles observed most often were 3, 5 and 10-year cycles. Polish lakes also have three cycles, but in the majority of them they amount to 5 and 10-years. It can be assumed that this is impacted by the continental climate growing to the east. Most probably it is one of the key factors defining the diversity of water fluctuations in all the analyzed lakes.

show abstract

“…Therefore, identification of the type of shape profile created on the banks like as specified channel geometric dimensions of stable channels is important. Concerning to the determination of slope, depth and water surface width in stable state or regime of channels, extensive research has been done (Lee and Julien 2006;Afzalimehr et al 2010;Métivier et al 2016;Gholami et al 2017a;Shaghaghi et al 2017;Joshi et al 2018). But there is little research to determine the type of bank profiles.…”

Section: Introductionmentioning

confidence: 99%

“…To increase the speed and performance of ANFIS models, using optimization algorithms (Hosseini et al 2016;Gholami et al 2017b;Bonakdari and Zaji 2018;Karaboga and Kaya 2018) and evolutionary models (multi-objective optimization) (Dariane and Azimi 2016; Ahmadianfar et al 2017;Saba et al 2017;Karkevandi-Talkhooncheh et al 2017;Nouiri 2017) has been very common. Regarding the use of AI methods in prediction of the stable channel geometry dimensions (width, depth and slope), it can be noted to Madvar et al (2011), Taher-Shamsi et al (2013, Bonakdari and Gholami (2016), Gholami et al (2017a), Shaghaghi et al (2017Shaghaghi et al ( , 2018a. All of them referred to high ability of AI models in prediction of stable channels geometry.…”

Section: Introductionmentioning

confidence: 99%

Analyzing bank profile shape of alluvial stable channels using robust optimization and evolutionary ANFIS methods

et al. 2019

Self Cite

View full text Add to dashboard Cite

In natural rivers and artificial channels in addition to the channel dimensions (widening, reduction in slope and depth in the channel banks), formed shape profile in the case that the sediment on the banks with no movement (thresholds state) is of considerable importance for engineers. To determine the bank shape profiles, various theoretical, empirical and statistical relations have been provided based on physical and numerical models by different researchers. In this study, a simple model of adaptive neuro-fuzzy inference systems (ANFIS) is combined with two algorithms of differential evolution (DE) and singular value decomposition value (SVD) and the performance of these models to predict the stable shape profiles of the channels is evaluated and compared. In this paper, the main goal is to assess extensively the effect of hybrid models based on optimized algorithms (ANFIS-DE) and multi-objective evolutionary algorithm (ANFIS-DE/SVD) in improvement of performance of ANFIS and ANFIS-DE models, respectively. Accordingly, the results assessment show that all three ANFIS, ANFIS-DE and ANFIS-DE/SVD models are perfectly able to predict shape profiles in accordance with the observed profiles for the threshold channels. Using optimized and evolutionary algorithms has a positive impact on the performance of simple model of ANFIS. As compared to the simple ANFIS model, ANFIS-DE approximately 10.1% and ANFIS-DE/SVD model 7.2% is improved compared to the ANFIS-DE model. The accuracy of ANFIS-DE/SVD model showed better performance as well about 18.6% compared to the simple ANFIS model. Therefore, it can be said that not only DE optimization algorithms have a significant impact on increasing the performance of a simple ANFIS model but also using evolutionary algorithms (ANFIS-DE/SVD) reduce the ANFIS-DE model error accordingly. Polynomial equations of bank profiles proposed by hybrid ANFIS models in the present study can be used in design and implementation of cross section of stable channels.

show abstract

Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design

Cited by 60 publications

References 52 publications

Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

Spectral–time analysis of cycle fluctuations in lake water levels in Belarus and Poland

Analyzing bank profile shape of alluvial stable channels using robust optimization and evolutionary ANFIS methods

Contact Info

Product

Resources

About