Hybrid of SOM-Clustering Method and Wavelet-ANFIS Approach to Model and Infill Missing Groundwater Level Data

Nourani, Vahid; Alami, Mohammad Taghi; Vousoughi, Farnaz Daneshvar

doi:10.1061/(asce)he.1943-5584.0001398

Cited by 29 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the spring discharge cycle is expected to be improved by the use of WA. In that, WA can provide quantitative evaluation and identify the major factors regulating spring discharge fluctuations in the time-frequency domain (Nourani et al 2016;Suryanarayana et al 2014). Wavelet transform can provide the timescale localization of a signal with a function form and identify the correlations between the wavelet functions and a signal as Mallat (1999):…”

Section: Wavelet Analysis (Wa)mentioning

confidence: 99%

See 1 more Smart Citation

Identifying and quantifying the latent factors controlling spring discharge in an industrialized karst watershed

Jamshidi

Qian

et al. 2021

Preprint

View full text Add to dashboard Cite

Karst springs have largely been impacted by human activity and climate change, which increases the uncertainties to supply and management of water resources. It’s essential to understand the footprint of the controlling factors on their hydrological behavior. Taking the example of Niangziguan springs in China, this study explores the time series of spring discharge over a 50-year time-window (1959–2007). Local Hurst exponent is employed to analyze its temporal correlation behavior. The prime latent factors of spring discharge are extracted and identified using dynamic factor analysis and wavelet analysis, respectively. Moreover, we quantified the contributions of latent factors to spring discharge. The results exhibit that the spring discharge is controlled by the positive feedback mechanism before the exploitation of karst groundwater, however, human activities lead to the feature of noise for spring discharge fluctuations. With the development of industry and agriculture, the effect of the combination of controlling factors on spring discharge tends to be stable. Before groundwater exploited, the local recharge cycle of groundwater shows the largest contribution (43%) on spring discharge focusing on the scales of 4–16 months, and the construction of the industrial region weakens the impact of local groundwater recharge (41%). The contribution of human activities, regional groundwater recharge, and rainfall/runoff to spring discharge (27%-30%) is almost equal. Therefore, human activities have become one of the most important factors controlling the spring discharge. The WNPM (West North Pacific Monsoon) and ISM (Indian Summer Monsoon) show the smallest effect (3%) on spring discharge.

show abstract

Section: Wavelet Analysis (Wa)mentioning

confidence: 99%

“…11. We selected the Daubechies-3 (db3) as the mother wavelet (Daubechies 1992) due to its prior use in hydrologic research, especially for non-stationary series (Moosavi et al 2013;Nourani et al 2016).…”

Section: Wavelet Analysis (Wa)mentioning

confidence: 99%

Identifying and quantifying the latent factors controlling spring discharge in an industrialized karst watershed

Jamshidi

Qian

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Multicollinearity takes place when two or more independent conditioning factors are highly correlated, or, in other words, interdependent (Li et al, 2010). Several methods have been proposed to diagnose multicollinearity, and among them, the variance inflation factor (VIF) and tolerance (TOL) are widely used in environmental modeling (O'brien, 2007;Bui et al, 2016); therefore, they were selected for this research. Factors with VIFs greater than 5 and TOL less than 0.1 indicate that multicollinearity problems existed (O'brien, 2007;Bui et al, 2011).…”

Section: Selection Of the Groundwater Conditioning Factorsmentioning

confidence: 99%

“…Several methods have been proposed to diagnose multicollinearity, and among them, the variance inflation factor (VIF) and tolerance (TOL) are widely used in environmental modeling (O'brien, 2007;Bui et al, 2016); therefore, they were selected for this research. Factors with VIFs greater than 5 and TOL less than 0.1 indicate that multicollinearity problems existed (O'brien, 2007;Bui et al, 2011). Another method, namely the information gain ratio (IGR) technique, was applied to identify the relative importance of the conditioning factor and also to obtain factors with null effect.…”

Section: Selection Of the Groundwater Conditioning Factorsmentioning

confidence: 99%

“…However, the ANN model has a number of weaknesses such as poor prediction and error in the modeling process (Bui et al, 2016); therefore, hybrid models have been proposed. Among hybrid frameworks, an ensemble of fuzzy logic and neural networks, i.e., an adaptive neuro-fuzzy inference system (ANFIS), has proven it is efficient in terms of high accuracy (Lohani et al, 2012;Emamgholizadeh et al, 2014;Zare and Koch, 2018;Bui et al, 2018;Nourani et al, 2016;Tien Bui et al, 2017;Pham et al, 2018a). It should be noted that although an ANFIS model has a higher accuracy than other models, it is still difficult to find the best internal weight values of ANFIS due to the limited nature of the adaptive algorithm used (Bui et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial prediction of groundwater spring potential mapping based on an adaptive neuro-fuzzy inference system and metaheuristic optimization

Khosravi

Panahi

Bui

2018

Hydrol. Earth Syst. Sci.

148

View full text Add to dashboard Cite

Abstract. Groundwater is one of the most valuable natural resources in the world (Jha et al., 2007). However, it is not an unlimited resource; therefore understanding groundwater potential is crucial to ensure its sustainable use. The aim of the current study is to propose and verify new artificial intelligence methods for the spatial prediction of groundwater spring potential mapping at the Koohdasht–Nourabad plain, Lorestan province, Iran. These methods are new hybrids of an adaptive neuro-fuzzy inference system (ANFIS) and five metaheuristic algorithms, namely invasive weed optimization (IWO), differential evolution (DE), firefly algorithm (FA), particle swarm optimization (PSO), and the bees algorithm (BA). A total of 2463 spring locations were identified and collected, and then divided randomly into two subsets: 70 % (1725 locations) were used for training models and the remaining 30 % (738 spring locations) were utilized for evaluating the models. A total of 13 groundwater conditioning factors were prepared for modeling, namely the slope degree, slope aspect, altitude, plan curvature, stream power index (SPI), topographic wetness index (TWI), terrain roughness index (TRI), distance from fault, distance from river, land use/land cover, rainfall, soil order, and lithology. In the next step, the step-wise assessment ratio analysis (SWARA) method was applied to quantify the degree of relevance of these groundwater conditioning factors. The global performance of these derived models was assessed using the area under the curve (AUC). In addition, the Friedman and Wilcoxon signed-rank tests were carried out to check and confirm the best model to use in this study. The result showed that all models have a high prediction performance; however, the ANFIS–DE model has the highest prediction capability (AUC = 0.875), followed by the ANFIS–IWO model, the ANFIS–FA model (0.873), the ANFIS–PSO model (0.865), and the ANFIS–BA model (0.839). The results of this research can be useful for decision makers responsible for the sustainable management of groundwater resources.

show abstract

Hybrid Model of Self-Organized Map and Integrated Fuzzy Rules with Support Vector Machine: Application to Stock Price Analysis

Nguyen

2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Hybrid of SOM-Clustering Method and Wavelet-ANFIS Approach to Model and Infill Missing Groundwater Level Data

Cited by 29 publications

References 41 publications

Identifying and quantifying the latent factors controlling spring discharge in an industrialized karst watershed

Identifying and quantifying the latent factors controlling spring discharge in an industrialized karst watershed

Spatial prediction of groundwater spring potential mapping based on an adaptive neuro-fuzzy inference system and metaheuristic optimization

Hybrid Model of Self-Organized Map and Integrated Fuzzy Rules with Support Vector Machine: Application to Stock Price Analysis

Contact Info

Product

Resources

About