Dennis, S. R.Steyl, Gideon2015-11-242015-11-242009-03http://hdl.handle.net/11660/1770English: Groundwater has been identified as a viable alternative for future freshwater production in South Africa. The management thereof is steadily gaining more recognition from governmental institutions. A significant obstacle in the development of this resource is the conceptual understanding of surface water and groundwater interaction. The availability of reliable data for rainfall, flow volumes in rivers and water levels in boreholes have prompted an investigation into patching incomplete data sets. This study also focused on predicting the influence of rainfall and flow volumes in a river on the surrounding groundwater levels. Neural networks have been used to investigate both data patching and forward prediction of water levels in selected data sets.Afrikaans: Die gebruik van grondwater as ʼn alternatiewe bron van varswater in Suid Afrika is geïdentifiseer as ʼn heel bruikbare opsie. Die bestuur van die hulpbron is stadig maar seker besig om weier impak en erkenning te kry by regeringsinstansies. ʼn Werklike probleem in die ontwikkeling van hierdie hulpbron is die konsepsiuele interaksie tussen oppervlakswater en grondwater. Die beskikbaarheid van ʼn volledige stel data van reënval, vloeivolumes en watervlakke in boorgate het tot gevolg gehad dat opvulling van verlore data benodig word deur die gebruik van neurale netwerke. In hierdie ondersoek is gefokus op die voorspelling van die invloed wat reënval en vloeivolumes in riviere op die omliggende boorgat watervlakke het, dus word neurale netwerke ingespan om beide onvolledige data stelle te voltooi en om voorwaartse skattings te maak van watervlakke in boorgate.enSurface water and groundwater interactionPatchingForecastingGeohydrologyNeural network ((Computer science)HydrogeologyGroundwater -- South Africa -- Computer simulationDissertation (M.Sc. (Institute for Groundwater Studies))--University of the Free State, 2009DissertationUniversity of the Free State