Extraction of depth to bedrock from airborne electromagnetic data using artificial neural networks

ABSTRACT: Infrastructure cost overruns and delays are persistent challenges for engineers and project owners. Reported average cost overruns from 20 to 50% for linear infrastructure are typical. Assessing geological risk is a significant part of planning; however, this risk is hard to control given the high cost of detailed ground investigation programs using traditional approaches (i.e. geotechnical drillings). Airborne geo-scanning is a technology that is increasingly being used to mitigate geological uncertainty. We have translated complicated geophysical models to parameters valuable for engineers using artificial neural networks. In this study we illustrate the applicability of airborne geo-scanning surveys to derive bedrock topography (i.e. depth of cover). Tight integration of accurate geophysical models and sparse geotechnical data is a key element leading to final bedrock topography uncertainty of a few meters or 20 % – 30 % of the sediment thickness.