skip to main content
Tipo de recurso Mostra resultados com: Mostra resultados com: Índice

Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX).(Report)

Wunsch, Andreas ; Liesch, Tanja ; Broda, Stefan

Journal of Hydrology, 2018, Vol.567, p.743 [Periódico revisado por pares]

Texto completo disponível

Citações Citado por
  • Título:
    Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX).(Report)
  • Autor: Wunsch, Andreas ; Liesch, Tanja ; Broda, Stefan
  • Assuntos: Hydrogeology – Analysis ; Artificial Neural Networks – Usage ; Artificial Neural Networks – Analysis ; Aquifers – Analysis ; Groundwater – Analysis ; Precipitation (Meteorology) – Analysis
  • É parte de: Journal of Hydrology, 2018, Vol.567, p.743
  • Descrição: Byline: Andreas Wunsch [andreas.wunsch@kit.edu] (a,*), Tanja Liesch (a), Stefan Broda (b) Keywords Groundwater levels; Forecasting; Neural networks; NARX; Germany Highlights * NARX were applied to obtain groundwater level forecasts with lead times up to half a year. * Porous, fractured and karst aquifers with and without external influences on groundwater levels. * The developed approach is easily transferable on other wells. * Input- and feedback delays were determined by applying STL time series decomposition. * The results indicate an outstanding suitability of NARX for groundwater level predictions. Abstract While the application of neural networks for groundwater level forecasting in general has been investigated by many authors, the use of nonlinear autoregressive networks with exogenous inputs (NARX) is relatively new. For this work NARX were applied to obtain groundwater level forecasts for several wells in southwest Germany. Wells in porous, fractured and karst aquifers were investigated and forecasts of lead times up to half a year were conducted for both influenced (e.g. nearby pumping) and uninfluenced wells. Precipitation and temperature were chosen as predictors, which makes the selected approach easily transferable, since both parameters are widely available and simple to measure. Input and feedback delays were determined by applying STL time series decomposition on the data and using auto- and cross-correlation functions on the remainders to determine significant time lags. Coefficient of determination, (relative) root mean squared error and Nash-Sutcliffe efficiency were used to evaluate forecasts, the model selection was based on an out-of-sample validation on rolling basis. The results are promising and indicate an outstanding suitability of NARX for groundwater level predictions with such a small set of inputs in all three aquifer types. Author Affiliation: (a) Karlsruhe Institute of Technology, Institute of Applied Geosciences, Division of Hydrogeology, Kaiserstr. 12, 76131 Karlsruhe, Germany (b) Federal Institute for Geosciences and Natural Resources, Wilhelmstr. 25-30, 13593 Berlin, Germany * Corresponding author. Article History: Received 24 May 2017; Revised 17 November 2017; Accepted 21 January 2018 (miscellaneous) This manuscript was handled by A. Bardossy, Editor-in-Chief, with the assistance of Niels Schuetze, Associate Editor
  • Idioma: Inglês

Buscando em bases de dados remotas. Favor aguardar.