A non-linear rainfall–runoff model using an artificial neural network

Sajikumar, N.; Thandaveswara, B. S.

doi:10.1016/s0022-1694(98)00273-x

Cited by 276 publications

(141 citation statements)

References 27 publications

Supporting

Mentioning

136

Contrasting

Unclassified

Order By: Relevance

“…In order to accommodate these nonlinearities and possibly provide more accurate headwater and tributary temperature estimates, our second approach was to follow the recent examples of Zealand et al (1999) and Sajikumar and Thandaveswara (1999) and employ a neural network model. Trials using ThinksPro software (ThinksPro, 1996) showed that the best results were obtained with a simple 3-layer network that employed normal back propagation.…”

Section: Analyses Of Fraser Watershed Flows Andmentioning

confidence: 99%

Simulations and retrospective analyses of fraser watershed flows and temperatures

et al. 2001

View full text Add to dashboard Cite

show abstract

Section: Analyses Of Fraser Watershed Flows Andmentioning

confidence: 99%

Simulations and retrospective analyses of fraser watershed flows and temperatures

et al. 2001

View full text Add to dashboard Cite

show abstract

“…Many studies have used similar models and compared them with the classical rainfall-runoff model (Hsu et al, 1995;Zealand et al, 1997;Sajikumar and Thandaveswara, 1999;Govindaraju, 2000). The most frequently cited advantage of neural networks in hydrology is their ability to model the complexity of the rainfall-runoff relation thanks to their property of universal approximation (Hornik et al, 1989).…”

Section: State-of-the-art Assessmentmentioning

confidence: 99%

Complexity selection of a neural network model for karst flood forecasting: The case of the Lez Basin (southern France)

Siou

Johannet

Estupina

et al. 2011

Journal of Hydrology

View full text Add to dashboard Cite

A neural network model is applied to simulate the rainfall-runoff relation of a karst spring. The input selection for such a model becomes a major issue when deriving a parsimonious and efficient model. The present study is focused on these input selection methods; it begins by proposing two such methods and combines them in a subsequent step. The methods introduced are assessed for both simulation and forecasting purposes. Since rainfall is very difficult to forecast, especially in the study area, we have chosen a forecasting mode that does not require any rainfall forecast assumptions. This application has been implemented on the Lez karst aquifer, a highly complex basin due to its structure and operating conditions. Our models yield very good results, and the forecasted discharge values at the Lez spring are acceptable up to a 1-day forecasting horizon. The combined input selection method ultimately proves to be promising, by reducing input selection time while taking into account: i) the model's ability to accommodate nonlinearity, and ii) the forecasting horizon.

show abstract

“…SVR showed the best performance as reported in [3], [4]. Rainfall lag time values are also used to consider for building a model to predict runoff [5], [6]. Runoff lag time values are also proposed to predict runoff [7].…”

Section: Introductionmentioning

confidence: 99%