Application of Several Data-Driven Techniques for Predicting Groundwater Level

Shirmohammadi, Bagher; Vafakhah, Mehdi; Moosavi, Vahid; Moghaddamnia, A.

doi:10.1007/s11269-012-0194-y

Cited by 131 publications

(58 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The partial autocorrelation function (PACF), as one of the statistical methods, was frequently used to select suitable models [10]. The PACF of well site M1255 from lag-0 to lag-18 is shown in Figure 8.…”

Section: Study Site and Data Preprocessingmentioning

confidence: 99%

“…Recently, data-driven models such as artificial neural networks (ANN), support vector machines (SVM), adaptive neuro-fuzzy inference systems (ANFIS) and genetic programming (GP), and time series methods such as autoregressive moving average (ARMA) and autoregressive integrated moving average (ARIMA) have been proved efficient in forecasting hydrologic time series (e.g., groundwater level, water demand and inflow) [5][6][7][8][9][10][11][12][13][14][15][16][17][18]. Yoon et al [5] developed ANN and SVM models to forecast groundwater level fluctuations in a coastal aquifer.…”

Section: Introductionmentioning

confidence: 99%

“…The performance of the SVM was similar to or even better than that of the ANN model, according to the results from the validation. Shirmohammadi et al [10] applied time series, system identification and ANFIS models to predict groundwater levels. The obtained results showed that ANFIS is superior to time series and system identification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Groundwater Level Forecasting Using Data-Driven Models Based on Ensemble Empirical Mode Decomposition

Gong

Wang

et al. 2018

Water

View full text Add to dashboard Cite

Abstract:The reliable and accurate prediction of groundwater levels is important to improve water-use efficiency in the development and management of water resources. Three nonlinear time-series intelligence hybrid models were proposed to predict groundwater level fluctuations through a combination of ensemble empirical mode decomposition (EEMD) and data-driven models (i.e., artificial neural networks (ANN), support vector machines (SVM) and adaptive neuro fuzzy inference systems (ANFIS)), respectively. The prediction capability of EEMD-ANN, EEMD-SVM, and EEMD-ANFIS hybrid models was investigated using a monthly groundwater level time series collected from two observation wells near Lake Okeechobee in Florida. The statistical parameters correlation coefficient (R), normalized mean square error (NMSE), root mean square error (RMSE), Nash-Sutcliffe efficiency coefficient (NS), and Akaike information criteria (AIC) were used to assess the performance of the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models. The results achieved from the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models were compared with those from the ANN, SVM and ANFIS models. The three hybrid models (i.e., EEMD-ANN, EEMD-SVM, and EEMD-ANFIS) proved to be applicable to forecast the groundwater level fluctuations. The values of the statistical parameters indicated that the EEMD-ANFIS and EEMD-SVM models achieved better prediction results than the EEMD-ANN model. Meanwhile, the three models coupled with EEMD were found have better prediction results than the models that were not. The findings from this study indicate that the proposed nonlinear time-series intelligence hybrid models could improve the prediction capability in forecasting groundwater level fluctuations, and serve as useful and helpful guidelines for the management of sustainable water resources.

show abstract

Section: Study Site and Data Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Groundwater Level Forecasting Using Data-Driven Models Based on Ensemble Empirical Mode Decomposition

Gong

Wang

et al. 2018

Water

View full text Add to dashboard Cite

show abstract

“…Various methods have been proposed to determine the optimum number of neurons in the hidden layer such as 2n + 1, 2n and n, where n is the number of nodes in the input layer (Moosavi et al, 2014); however, trial-and-error approach is an appropriate way as indicated by Mishra and Desai (2006), and Shirmohammadi et al (2013). Therefore, 4-22 nodes with increment of 3 are tested for the hidden layer.…”

Section: Experimental Designmentioning

confidence: 99%

Fractional Snow Cover Mapping By Artificial Neural Networks and Support Vector Machines

Çiftçi

Kuter

Akyürek

et al. 2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Snow is an important land cover whose distribution over space and time plays a significant role in various environmental processes. Hence, snow cover mapping with high accuracy is necessary to have a real understanding for present and future climate, water cycle, and ecological changes. This study aims to investigate and compare the design and use of artificial neural networks (ANNs) and support vector machines (SVMs) algorithms for fractional snow cover (FSC) mapping from satellite data. ANN and SVM models with different model building settings are trained by using Moderate Resolution Imaging Spectroradiometer surface reflectance values of bands 1-7, normalized difference snow index and normalized difference vegetation index as predictor variables. Reference FSC maps are generated from higher spatial resolution Landsat ETM+ binary snow cover maps. Results on the independent test data set indicate that the developed ANN model with hyperbolic tangent transfer function in the output layer and the SVM model with radial basis function kernel produce high FSC mapping accuracies with the corresponding values of R = 0.93 and R = 0.92, respectively.

show abstract

“…This is because their amplitudes are generally less then 10 cm and only slightly increase the scatter of water level time series (Cengiz 2011). In fact, in mean water level computation, most of these local processes approach zero at the scale of selected time series of the lake, assuming homogeneous sampling of surface patterns (Hofmann et al 2008;Shirmohammadi et al 2013). Thus, to better understand the long-term complex nature of water level fluctuations, the wavelet transform method is a powerful tool for analyzing nonstationary time series, as well as an exploration of interest changes with inner/over the last few years in water resources.…”

Section: Introductionmentioning

confidence: 99%

Long-term periodic structure and seasonal-trend decomposition of water level in Lake Baiyangdian, Northern China

Wang

Zhao

et al. 2013

Int. J. Environ. Sci. Technol.

View full text Add to dashboard Cite

Water level, as an intuitive factor of hydrologic conditions, is of great importance for lake management. In this study, periodic structures of water level and its fluctuations in Lake Baiyangdian are analyzed based on wavelet analysis and seasonal-trend decomposition using local error sum of squares (STL). Data of monthly time series are divided into three types with emphasis on anthropogenic influence from water allocation. It is found that intra-annual characteristics of water level fluctuations are the common periodic structures. Water allocation alters the periodic structures by decreasing and weakening the oscillations of water level, compared with the slight effects of natural hydrologic water supplies and short-term climate changes. An irregular water level decline and short-term oscillation with irregular periodicity are deduced from seasonal-trend decomposition analysis using STL. With seasonality depicted monthly, the influence of water allocation implies irregular oscillations with high-frequency components, especially for monthly changes. The water level fluctuations are influenced by seasonal changes, as demonstrated by three types of time series. The impacts of water allocation on seasonality show the differences with continuous single-peak oscillations representing no influences and continuous double-peak oscillations representing frequent influences. Furthermore, the accumulation of water allocation shows a slight rising trend in average monthly level fluctuations over the last several years. The study helps understand periodic structures and long-term trend changes of water level fluctuations, which will facilitate lake management of Lake Baiyangdian.

show abstract

Application of Several Data-Driven Techniques for Predicting Groundwater Level

Cited by 131 publications

References 42 publications

A Comparative Study of Groundwater Level Forecasting Using Data-Driven Models Based on Ensemble Empirical Mode Decomposition

A Comparative Study of Groundwater Level Forecasting Using Data-Driven Models Based on Ensemble Empirical Mode Decomposition

Fractional Snow Cover Mapping By Artificial Neural Networks and Support Vector Machines

Long-term periodic structure and seasonal-trend decomposition of water level in Lake Baiyangdian, Northern China

Contact Info

Product

Resources

About