Combining ground-based and airborne EM through Artificial Neural Networks for modelling glacial till under saline groundwater conditions

Abstract. Airborne electromagnetic (AEM) methods supply data over large areas in a cost-effective way. We used Artificial Neural Networks (ANN) to classify the geophysical signal into a meaningful geological parameter. By using examples of known relations between ground-based geophysical data (in this case electrical conductivity, EC, from electrical cone penetration tests) and geological parameters (presence of glacial till), we extracted learning rules that could be applied to map the presence of a glacial till using the EC profiles from the airborne EM data. The saline groundwater in the area was obscuring the EC signal from the till but by using ANN we were able to extract subtle and often non-linear, relations in EC that were representative of the presence of the till. The ANN results were interpreted as the probability of having till and showed a good agreement with drilling data. The glacial till is acting as a layer that inhibits groundwater flow, due to its high clay-content, and is therefore an important layer in hydrogeological modelling and for predicting the effects of climate change on groundwater quantity and quality.