Abstract:
Delineation of geologic features that are capable of hosting water in economic quantity in the
Basement Complex has been a major concern because they are usually localized due to restricted
fractured and weathered rock. An approach engaging Vertical Electrical Sounding (VES) and
remotely sensed data was carried out with a view to producing groundwater potential model of
Oke-Ilewo Community, Abeokuta, Nigeria. Sixty two (62) depth sounding data were acquired
using Schlumberger array with (AB/2) ranging from 1– 120 m. The VES were quantitatively
interpreted using autopartial curve match software and computer aided iteration to determine the
geo-electrical parameters. Twelve parameters of hydrogeological importance were used to develop
groundwater potential model for the study area. This was subjected to the Gradient Boosting Tree
(GBT) model using the Salford Predictive Modeler 8.0 software. Four (4) were from remotely
sensed data. The other eight (8) of these parameters were derived from the interpreted results of
geophysical data. The data were partitioned into Training and test dataset in ratio 90:10 using k
10 cross validation techniques. Their prediction importance was determined and the groundwater
potential index calculated. The groundwater potential map (GPM) of the area revealed three (3)
zonations, which are the low groundwater potential, the moderate groundwater and the high
groundwater potential with percentage frequency of 46%, 10%, and 44%. Water column of wells
in the area was used to validate the GPM developed. This was done by superimposing the values
in the GPM and observed the accuracy. The model gave an accuracy of 87%. In conclusion, the
model has proven that the drop in aquifer resistivity doesn't necessitate the presence of
groundwater but rather several parameter should be integrated together to better understand the
true nature of the aquifer.
