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

摘要

Airborne electromagnetic (AEM) methods supply data over large areas in acost-effective way. We used Artificial Neural Networks (ANN) to classify thegeophysical signal into a meaningful geological parameter. By using examplesof known relations between ground-based geophysical data (in this caseelectrical conductivity, EC, from electrical cone penetration tests) andgeological parameters (presence of glacial till), we extracted learningrules that could be applied to map the presence of a glacial till using theEC profiles from the airborne EM data. The saline groundwater in the areawas obscuring the EC signal from the till but by using ANN we were able toextract subtle and often non-linear, relations in EC that wererepresentative of the presence of the till. The ANN results were interpretedas the probability of having till and showed a good agreement with drillingdata. The glacial till is acting as a layer that inhibits groundwater flow,due to its high clay-content, and is therefore an important layer inhydrogeological modelling and for predicting the effects of climate changeon groundwater quantity and quality.