Comparison of ANNs and Empirical Approaches for Predicting Watershed Runoff

Anmala, Jagadeesh; Zhang, Bin; Govindaraju, Rao S.

doi:10.1061/(asce)0733-9496(2000)126:3(156)

Cited by 91 publications

(28 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Outra característica importante é a extensão das séries de dados, que está relacionada com a quantidade de dados utilizados para o treinamento e validação das RNAs. Anmala et al (2000) acreditam que, quanto maior for o tamanho da amostra de dados melhor será a generalização do problema. Em um problema chuva-vazão mensal, Lima & Ferreira Filho (2003) utilizaram 456 dados para sua solução, enquanto Elshorbagy et al (2000) empregaram apenas 50 para treinamento e validação para uma previsão de vazão anual.…”

Section: Rna Propostaunclassified

Rede neural artificial aplicada à previsão de vazão da Bacia Hidrográfica do Rio Piancó

Sousa¹,

Sousa²

2010

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

RESUMOA previsão de vazão em um sistema hídrico não é apenas uma das técnicas utilizadas para minimizar o impacto das incertezas do clima sobre o gerenciamento dos recursos hídricos mas, também, um dos principais desafios relacionados ao conhecimento integrado da climatologia e da hidrologia de uma bacia hidrográfica. O objetivo deste trabalho foi modelar a relação não-linear entre chuva e vazão na bacia hidrográfica do rio Piancó, no semiárido paraibano, através da técnica de Redes Neurais Artificiais (RNA). Aqui se avaliou a capacidade da RNA modelar o processo chuva-vazão em base mensal e se considerou, durante o seu treinamento, a influência da arquitetura da rede e da inicialização dos pesos. No final do treinamento foi escolhida a melhor arquitetura para modelar vazões médias mensais na bacia estudada, com base no desempenho do modelo. A arquitetura de RNA que produziu melhor resultado foi a RC315L, com valores para o coeficiente de determinação, de eficiência e erro padrão da estimativa de 92,0, 77,0% e 8,29, respectivamente. Palavras-chave: hidrometeorologia, processo estocástico, processo chuva-vazãoArtificial neural network applied to the forecast of streamflow in the Piancó River Basin ABSTRACT Streamflow forecasting in a water system is one of the techniques used to reduce the impact of the uncertainties of the climate on administration of the water resources. That technique can be considered as one of the principal challenges related to the integrated knowledge of the climatology and of the hydrology of the river basin. The aim of this work was to model the non-linear relationship between rainfall and streamflow in the Piancó River Basin, in the Paraíba semiarid, using the technique of Artificial Neural Networks (ANN). Here the ability of ANN was evaluated to model the rainfallrunoff process on a monthly basis. During training of the ANN, the network architecture and weights initialization influence were considered. At the end of the training the best architecture was chosen, to model the streamflow monthly mean in the studied basin, based upon the performance of the model. The ANN architecture that produced the better result was RC315L with values for the determination coefficient, efficiency coefficient and standard estimate error (SEE) equal to 92.0, 77.0% and 8.29 respectively.

show abstract

Section: Rna Propostaunclassified

Rede neural artificial aplicada à previsão de vazão da Bacia Hidrográfica do Rio Piancó

Sousa¹,

Sousa²

2010

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

show abstract

“…Catchment's responses to any hydrological event are convoluted by various hydro-geomorphologic and climatic factors. These factors are distributed within a system in a heterogeneous manner both spatially and temporally (Anmala et al, 2000). To understand the underlying physical processes, detailed information of the various hydro-geomorphologic and climatic factors along with catchment characteristics are required.…”

Section: Introductionmentioning

confidence: 99%

Water level prediction by artificial neural network in a flashy transboundary river of Bangladesh

2014

Global NEST Journal

View full text Add to dashboard Cite

This paper presents the sensitivity analysis results of feed forward multilayer perceptron based Artificial Neural Network model for water level prediction in a data constraint transnational Surma River of Bangladesh. Catchment characteristics, hydro-geomorphological, meteorological and headwater information of the upper catchment area are not available to the authors. As such past daily total rainfall and water levels data available within the country are utilized in this study. Logistic sigmoid activation function with unit steepness parameter is exercised for non-linear transformations in both hidden and output layers. Synaptic weights are adjusted using modified delta rule through error back propagation algorithm. Batch mode of training is adopted for global error minimization. Finally, statistical indicators are used to evaluate the prediction performance of the neural network. The model is then applied to predict water levels with twenty four and forty eight hours lead time.It is found that a single hidden layer with two hidden neurons are adequate to train the network. A higher number of hidden neurons is speeding up the training procedure, but with an unacceptable generalization for the application. The authors have successfully created a model that recognizes the intricate pattern of water levels, without having the spatially distributed geomorphic characteristics of the watershed and the time-series of the climatic factors.

show abstract

“…[6] Statistical approaches have been utilized to model the complex relationships between streamflows and the large-scale atmospheric circulation phenomena [Anmala et al, 2000;Maity and Nagesh Kumar, 2008b]. The predictors used in majority of these data-driven approaches were hydroclimatic variables such as mean temperature, mean sea-level pressure, soil moisture, precipitation, runoff, and wind speed.…”

Section: Introductionmentioning

confidence: 99%

Identification of hydrologic drought triggers from hydroclimatic predictor variables

Maity

Ramadas

Govindaraju

2013

Water Resources Research

Self Cite

View full text Add to dashboard Cite

[1] Drought triggers are patterns in hydroclimatic variables that herald upcoming droughts and form the basis for mitigation plans. This study develops a new method for identification of triggers for hydrologic droughts by examining the association between the various hydroclimatic variables and streamflows. Since numerous variables influence streamflows to varying degrees, principal component analysis (PCA) is utilized for dimensionality reduction in predictor hydroclimatic variables. The joint dependence between the first two principal components, that explain over 98% of the variability in the predictor set, and streamflows is computed by a scale-free measure of association using asymmetric Archimedean copulas over two study watersheds in Indiana, USA, with unregulated streamflows. The M6 copula model is found to be suitable for the data and is utilized to find expected values and ranges of predictor hydroclimatic variables for different streamflow quantiles. This information is utilized to develop drought triggers for 1 month lead time over the study areas. For the two study watersheds, soil moisture, precipitation, and runoff are found to provide the fidelity to resolve amongst different drought classes. Combining the strengths of PCA for dimensionality reduction and copulas for building joint dependence allows the development of hydrologic drought triggers in an efficient manner.Citation: Maity, R., M. Ramadas, and R. S. Govindaraju (2013), Identification of hydrologic drought triggers from hydroclimatic predictor variables, Water Resour. Res., 49,[4476][4477][4478][4479][4480][4481][4482][4483][4484][4485][4486][4487][4488][4489][4490][4491][4492]

show abstract

Comparison of ANNs and Empirical Approaches for Predicting Watershed Runoff

Cited by 91 publications

References 23 publications

Rede neural artificial aplicada à previsão de vazão da Bacia Hidrográfica do Rio Piancó

Rede neural artificial aplicada à previsão de vazão da Bacia Hidrográfica do Rio Piancó

Water level prediction by artificial neural network in a flashy transboundary river of Bangladesh

Identification of hydrologic drought triggers from hydroclimatic predictor variables

Contact Info

Product

Resources

About