The influence of groundwater abstraction on interpreting climate controls and extreme recharge events from well hydrographs in semi-arid South Africa

There is a scarcity of long-term groundwater hydrographs from sub-Saharan Africa to investigate groundwater sustainability, processes and controls. This paper presents an analysis of 21 hydrographs from semi-arid South Africa. Hydrographs from 1980 to 2000 were converted to standardised groundwater level indices and rationalised into four types (C1-C4) using hierarchical cluster analysis. Mean hydrographs for each type were cross-correlated with standardised precipitation and streamflow indices. Relationships with the El Nino-Southern Oscillation (ENSO) were also investigated. The four hydrograph types show a transition of autocorrelation over increasing timescales and increasingly subdued responses to rainfall. Type C1 strongly relates to rainfall, responding in most years, whereas C4 notably responds to only a single extreme event in 2000 and has limited relationship with rainfall. Types C2, C3 and C4 have stronger statistical relationships with standardised streamflow than standardised rainfall. C3 and C4 changes are significantly (p < 0.05) correlated to the mean wet season ENSO anomaly, indicating a tendency for substantial or minimal recharge to occur during extreme negative and positive ENSO years, respectively. The range of different hydrograph types, sometimes within only a few kilometres of each other, appears to be a result of abstraction interference and cannot be confidently attributed to variations in climate or hydrogeological setting. It is possible that high groundwater abstraction near C3/C4 sites masks frequent small-scale recharge events observed at C1/C2 sites, resulting in extreme events associated with negative ENSO years being more visible in the time series.