Simulation of spring flows from a karst aquifer with an artificial neural network

Hu, Caihong; Hao, Yonghong; Yeh, Tian Chyi Jim; Pang, Bo; Wu, Zening

doi:10.1002/hyp.6625

Cited by 94 publications

(58 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The studies about the karst water transfer and storage use tools generally based on chemical analysis, borehole measurements and spring hydrograph often associated with modeling approach (Pinault et al, 2001;Hu et al, 2008;Zhang et al, 2011). Spring chemistry or flow approaches provide useful information at basin scale however bringing limited clues about the spatial distribution of hydrogeological properties.…”

Section: ) Introductionmentioning

confidence: 99%

Estimating epikarst water storage by time-lapse surface to depth gravity measurements

Champollion¹,

Devile²,

Chéry³

et al. 2017

Preprint

View full text Add to dashboard Cite

Abstract:In this study we attempt to evaluate the magnitude of epikarstic water storage variation in various karst settings using a relative spring gravimeter. Gravity measurements are performed two times a year at the surface and inside caves at different depths on three karst hydrosystems in southern France: two limestone karst systems and one dolomite karst system. We find that water storage variations occur mainly in the first ten meters of karst unsaturated zone. Afterward, surface to depth gravity measurements are compared between the sites with respect of net water inflow. A difference of seasonal water storage is evidenced probably associated with the lithology. The transmissive function of the epikarst has been partially deduced from the water storage change estimation. Long (> 6 months) and short (< 6 months) transfer time are revealed in the dolomite and in the limestone respectively.

show abstract

Section: ) Introductionmentioning

confidence: 99%

Estimating epikarst water storage by time-lapse surface to depth gravity measurements

Champollion¹,

Devile²,

Chéry³

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Then, the output layer had two neurons, one for each flow rate. We divided the field data in two sets, one for training and one for testing, since their number is rather restricted (Hu et al, 2008; ) were achieved with 10 neurons in the hidden layer and all of the input data (namely when the mean precipitation of the 6 th month prior to the date of measurement was added, too). Again, best results for May Vryssi have been achieved with substantially fewer neurons in the hidden layer, compared to Pera Vryssi.…”

Section: Trials and Resultsmentioning

confidence: 99%

“…Regarding prediction of karstic spring discharge, encouraging results have been obtained, at least when there are abundant field data (e.g. Kurtulus and Razack, 2007;Hu et al, 2008).…”

Section: Artificial Neural Network and Their Usefulnessmentioning

confidence: 98%

See 1 more Smart Citation

Measurement and prediction of karstic spring flow rates

Darivianakis

Katsifarakis²,

Vafeiadis³

2015

Issue 2

View full text Add to dashboard Cite

This paper deals with prediction of the response of karstic springs by means of artificial neural networks (ANNs). A feed-forward back propagation ANN with three layers has been developed, to predict flow rates of two karstic springs, located at Rouvas area, Crete, Greece, using rainfall data as input. While the number of neurons of the input and output layers was determined by choice of data and desired output respectively, the number of neurons of the hidden layer was decided by means of numerous tests. Data used in ANN training and testing include daily and monthly precipitation depths (from September, 2006 to December, 2010) and measured flow rates of the two springs (from April, 2007 to December, 2010. Results show that the trained artificial neural network performed well, although flow rate measurements were not very regular. Moreover, the possibility of estimating the flow rate of one spring, based on measurements of the other has been investigated. Again the ANN gave satisfactory results. All spring flow rate and rainfall measurements are presented as an appendix, to facilitate further scientific research in the area of ANN application to water resources management.

show abstract

“…Various methods such as the grey model (Yu et al, 2001;Trivedi and Singh, 2005), functional-coefficient time series model (Shao et al, 2009), wavelet analysis (Labat et al, 2000a, b;Lane, 2007;Sang, 2012), genetic algorithm (Seibert, 2000), and artificial neural network (Hsu et al, 1995;Hu et al, 2008;Tokar and Johnson, 1999;Modarres, 2009) have been widely used for hydrologic analysis and streamflow simulation. Hybrid models have been paid special attention (Nourani et al, 2009;Zhao et al, 2009;Sahay and Srivastava, 2014;Xu et al, 2014;Yarar, 2014).…”

Section: Introductionmentioning

confidence: 99%

A hybrid model to simulate the annual runoff of the Kaidu River in northwest China

Chen

Bai

et al. 2016

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Fluctuant and complicated hydrological processes can result in the uncertainty of runoff forecasting. Thus, it is necessary to apply the multi-method integrated modeling approaches to simulate runoff. Integrating the ensemble empirical mode decomposition (EEMD), the back-propagation artificial neural network (BPANN) and the nonlinear regression equation, we put forward a hybrid model to simulate the annual runoff (AR) of the Kaidu River in northwest China. We also validate the simulated effects by using the coefficient of determination (R 2 ) and the Akaike information criterion (AIC) based on the observed data from 1960 to 2012 at the Dashankou hydrological station. The average absolute and relative errors show the high simulation accuracy of the hybrid model. R 2 and AIC both illustrate that the hybrid model has a much better performance than the single BPANN. The hybrid model and integrated approach elicited by this study can be applied to simulate the annual runoff of similar rivers in northwest China.

show abstract

Simulation of spring flows from a karst aquifer with an artificial neural network

Cited by 94 publications

References 51 publications

Estimating epikarst water storage by time-lapse surface to depth gravity measurements

Estimating epikarst water storage by time-lapse surface to depth gravity measurements

Measurement and prediction of karstic spring flow rates

A hybrid model to simulate the annual runoff of the Kaidu River in northwest China

Contact Info

Product

Resources

About