Neural network simulation of spring flow in karst environments

Paleologos, Evan K.; Skitzi, I.; Katsifarakis, Konstantinos; Darivianakis, Nektarios

doi:10.1007/s00477-013-0717-y

Cited by 22 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ANNs were found more than convenient, easy-to-use tool, which outperforms traditional statistical and physical models, as discussed in [5][6][7][8] and [9]. Some applications of ANNs to inflow modelling and prediction on karst landscape can be found in [9][10][11][12] and [13].…”

Section: Introductionmentioning

confidence: 99%

Complex Hydrological System Inflow Prediction using Artificial Neural Network

2022

Teh. vjesn.

View full text Add to dashboard Cite

Artificial neural networks have been successfully used to model and predict water flows for a few decades. Different network types have proven to work better in different cases and additional tools and algorithms have been implemented to improve those neural models. However, some problems still occur in certain cases. This paper deals with the limitation of complex hydrological system inflow prediction using artificial neural network and inflow time series. This limitation is called the prediction lag and it disables the model from giving accurate predictions. To eliminate the prediction lag and to extend prediction horizon an alternative input variable named forecasted precipitation frequency is proposed in addition to antecedent inflow time-series. Simulation results prove the efficiency of the proposed solution that enables time series neural network model for 7th-day inflow prediction. This represents important information in operational planning of the hydrological system, used for short-term optimization of the system, e.g. optimization of the hydroelectric power plant operation.

show abstract

Section: Introductionmentioning

confidence: 99%

Complex Hydrological System Inflow Prediction using Artificial Neural Network

2022

Teh. vjesn.

View full text Add to dashboard Cite

show abstract

“…A number of other springs appear in the same area, some of them in rough terrain. (Paleologos et al, 2013) …”

Section: The Study Areamentioning

confidence: 99%

“…Using the larger part of the aforementioned rainfall and spring flow data Paleologos et al, (2013) have come up with different ANN structures.…”

Section: Selection Of Basic Ann Featuresmentioning

confidence: 99%

Measurement and prediction of karstic spring flow rates

Darivianakis

Katsifarakis²,

Vafeiadis³

2015

Global NEST Journal

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

“…Većina radova koja obrađuju tematiku krša koristi tzv. klasične neuronske mreže za predviđanje otjecanja (Lallahem i Mania, 2003;Kurtulus i Razack, 2006;Sepúlveda, 2009;Paleologos et al 2013). Najnovija istraživanja se posvećuju implementaciji ANN kao poboljšanje postojećih modela i to bilance voda u kršu (Kraller et al 2012) kao i sistemskom pristupu kontrole dizajna modela (Kong-A-Siou et al 2011), stoga je nužna analiza primjene ovakvih modela na lokalnim krškim slivovima.…”

Section: Postojeća Saznanja U Istraživačkom Područjuunclassified

Identifikacija hidroloških režima otjecanja u kršu konceptualnim i parametarskim modelima

Željković¹

View full text Add to dashboard Cite

Water balance characteristic of karst aquifer consist of different water regime flows influenced not only with amount of precipitation but especially with heterogenic and hydrogeological processes which can’t be directly measured. Aside from measurement problems, identification of hydrological regime becomes more difficult if the available data is scarce and discontinuous. Although constant uncertainty is always present in predicting natural phenomena, it is possible to model estimators which can be used to analyse current state of the system and give indication trends of their main features. Relations between rainfall and runoff, the RR model, are becoming more prominent because of their capabilities to implement noisy data. RR model represents an assembly of different mathematical principles trying to describe functioning of river catchment. RR models use certain assumptions about shapes of recession curve, catchment area, base flow-quick flow ratio, soilmoisture content and so on, to determine key parameters of the water circulation process. If the parameters are successfully calibrated and tested, they can be used as new insight to the properties of regional karst. Then, calibrated model represents hydrological behaviour under conditions determined in available database. Simulation of complex karst aquifer requires conceptual and computational learning approach. Current state of computer technology is becoming ever more useful in analysing processes of limited knowledge especially for the fact that computational time is becoming shorter and available software is more flexible and understandable to end user. Aim of proposed models is defining key factors for successful representation of observed runoff. Conceptual model combines transfer function and imbeds these key factors. Parametric model uses transformation which is not transparent but gives better approximation of cost function. Systematic approach to architectural design of parametric model overcomes these problems. Implementation of new findings from both models gives better hydrological understanding of investigated case study in karst.

show abstract

Neural network simulation of spring flow in karst environments

Cited by 22 publications

References 31 publications

Complex Hydrological System Inflow Prediction using Artificial Neural Network

Complex Hydrological System Inflow Prediction using Artificial Neural Network

Measurement and prediction of karstic spring flow rates

Identifikacija hidroloških režima otjecanja u kršu konceptualnim i parametarskim modelima

Contact Info

Product

Resources

About