Predicting longitudinal dispersion coefficient in natural streams by artificial intelligence methods

Toprak, Z. Fuat; Ciğizoğlu, H. Kerem

doi:10.1002/hyp.7012

Cited by 88 publications

(51 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks constitute a useful tool to predict and forecast various hydrological variables and are used extensively in water resources research (Tayfur, 2002;Cigizoglu, 2003aCigizoglu, ,b, 2004Sudheer, 2005;Cigizoglu & Kisi, 2006;Toprak & Cigizoglu, 2008). The ANN models are frequently employed for rainfall forecasting (Hsu et al, 1997;Kulligowski & Barros., 1998;Hall, 1999;Silverman & Dracup, 2000;Applequist et al, 2002;Ramirez et al, 2005;Freiwan & Cigizoglu, 2005).…”

Section: Introductionmentioning

confidence: 99%

Prediction of daily precipitation using wavelet—neural networks

Partal

Ciğizoğlu

2009

Hydrological Sciences Journal

View full text Add to dashboard Cite

This study aims to predict the daily precipitation from meteorological data from Turkey using the wavelet-neural network method, which combines two methods: discrete wavelet transform (DWT) and artificial neural networks (ANN). The wavelet-ANN model provides a good fit with the observed data, in particular for zero precipitation in the summer months, and for the peaks in the testing period. The results indicate that wavelet-ANN model estimations are significantly superior to those obtained by either a conventional ANN model or a multi linear regression model. In particular, the improvement provided by the new approach in estimating the peak values had a noticeably high positive effect on the performance evaluation criteria. Inclusion of the summed sub-series in the ANN input layer brings a new perspective to the discussions related to the physics involved in the ANN structure.Key words wavelet transforms; artificial neural networks; precipitation; Turkey; estimation Prévision de précipitation journalière à l'aide de réseaux neuronaux-ondelettes Résumé Cette étude cherche à prévoir les précipitations journalières à partir de données météorologiques Turques, à l'aide de la méthode de réseau neuronal-ondelettes qui combine deux méthodes: la transformée en ondelettes discrète (TOD) et les réseaux de neurones artificiels (RNA). Le modèle RNA-ondelettes produit un bon accord avec les données observées, en particulier pour l'absence de précipitation pendant les mois d'été, et pour les pics durant la période de test. Les résultats indiquent que les estimations du modèle RNA-ondelettes sont significativement supérieures à celles que l'on obtient avec un modèle RNA conventionnel ou avec un modèle de régression multilinéaire. En particulier, l'amélioration permise par la nouvelle approche pour l'estimation des valeurs de pic a un effet positif notable sur les critères de performance. L'inclusion des sous-séries sommées dans la couche d'entrées du RNA ouvre de nouvelles perspectives en termes de prise en compte de la physique dans la structure d'un RNA.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of daily precipitation using wavelet—neural networks

Partal

Ciğizoğlu

2009

Hydrological Sciences Journal

View full text Add to dashboard Cite

show abstract

“…The presented work is an extension and generalization of previous studies (Kashefipour et al, 2002;Toprak & Cigizoglu, 2008) including some works of the authors (Wallis & Manson, 2004;Rowinski et al, 2005) in which predictions of dispersion coefficients were made based on previous tracer experiments performed in similar river reaches. In Piotrowski et al (2007) neural network predictions of the whole breakthrough curves on a single river under various river conditions were studied.…”

Section: Introductionmentioning

confidence: 71%

“…Wallis & Manson, 2004), or neural network-based models (Kashefipour et al, 2002;Rowinski et al, 2005;Tayfur, 2006;Toprak & Cigizoglu, 2008) for estimating dispersion coefficients, but they all require relatively detailed knowledge about the characteristics of the considered river reaches. In this study, an attempt is made to determine the reach average longitudinal dispersion coefficient, K L , and the velocity, U, when the results of tracer tests and/or detailed hydraulic studies are not available; hence, the methods suggested in the papers cited above cannot be applied.…”

Section: Development Of Parameter Estimation Modelsmentioning

confidence: 99%

Evaluation of temporal concentration profiles for ungauged rivers following pollution incidents

Piotrowski

Napiorkowski

Rowiński

et al. 2011

Hydrological Sciences Journal

View full text Add to dashboard Cite

In order to predict the impact of pollution incidents on rivers, it is necessary to predict the dispersion coefficient and the flow velocity corresponding to the discharge in the river of interest. This paper explores methods for doing this, particularly with a view to applications on ungauged rivers, i.e. those for which little hydraulic or morphometric data are available. An approach based on neural networks, trained on a wide-ranging database of optimized parameter values from tracer experiments and corresponding physical variables assembled for American and European rivers, is proposed. Tests using independent cases showed that the neural networks generally gave more reliable parameter estimates than a second-order polynomial regression approach. The quality of predictions of temporal concentration profiles was heavily influenced by the accuracy of the velocity prediction.Key words longitudinal dispersion; pollutant transport; ungauged river; neural networks; data-based modelling Evaluation des profils temporels de concentration de cours d'eau non jaugés à la suite d'incidents de pollution Résumé Afin de prévoir l'impact des incidents de pollution dans les rivières, il est nécessaire de prévoir le coefficient de dispersion et la vitesse d'écoulement correspondant au débit dans la rivière considérée. Cet article explore les méthodes pour ce faire, en particulier en vue d'applications à des rivières non jaugées, c'est-à-dire pour lesquelles peu de données hydrauliques ou morphométriques sont disponibles. Une approche basée sur des réseaux neuronaux, entraînés avec une importante base de données de valeurs de paramètres optimisés à partir d'expériences de traçage et de variables physiques correspondantes, assemblée pour des rivières américaines et européennes, est proposée. Des tests utilisant des cas indépendants ont montré que les réseaux de neurones ont généralement donné des estimations de paramètres plus fiables qu'une approche de régression polynomiale du second ordre. La qualité des prévisions des profils temporels de concentration a été fortement influencée par la précision de la prévision de la vitesse.

show abstract

“…Other common applications of machine learning methods include: forecasting of non-stationary hydrological time series using dynamically driven recurrent neural networks, [20] prediction of longitudinal dispersion coefficients in natural streams using different types of neural networks, [21] the use of quantile regression forests to determine sediment transport, [22] downscaling of stream-flow using relevance vector machines, [23] using support vector regression to predict seasonal winter extreme precipitation, [24] and downscaling of maximum and minimum temperatures, [25] wind speeds, [26] and daily precipitation [27] using Bayesian neural networks.…”

Section: Related Workmentioning

confidence: 99%

Can we obtain viable alternatives to Manning’s equation using genetic programming?

Gaitán

Balaji

Moore

2016

AIR

View full text Add to dashboard Cite

Applied water research, like the one derived from open-channel hydraulics, traditionally links empirical formulas to observational data; for example Manning's formula for open channel flow driven by gravity relates the discharge (Q), cross-sectional average velocity (V ), the hydraulic radius (R), and the slope of the water surface (S) with a friction coefficient n, characteristic of the channel's surface needed in the location of interest. Here we use Genetic Programming (GP), a machine learning technique inspired by nature's evolutionary rules, to derive empirical relationships based on synthetic datasets of the aforementioned parameters. Specifically, we evaluated if Manning's formula could be retrieved from datasets with: a) 300 pentads of A, n, R, S, and Q (from Manning's equation), b) from datasets containing an uncorrelated variable and the parameters from (a), and c) from a dataset containing the parameters from (b) but using values of Q containing noise. The cross-validated results show success retrieving the functional form from the synthetic data in the first two experiments, and a more complex solution of Q for the third experiment. The results encourage the application of GP on problems where traditional empirical relationships show high biases or are non-parsimonious. The results also show alternative flow equations that might be used in the absence of one or more predictors; however, these equations should be used with caution outside of the training intervals.

show abstract

Predicting longitudinal dispersion coefficient in natural streams by artificial intelligence methods

Cited by 88 publications

References 80 publications

Prediction of daily precipitation using wavelet—neural networks

Prediction of daily precipitation using wavelet—neural networks

Evaluation of temporal concentration profiles for ungauged rivers following pollution incidents

Can we obtain viable alternatives to Manning’s equation using genetic programming?

Contact Info

Product

Resources

About