Artificial intelligence-

Shan, C., Abbaszadeh Shahri, A., Larsson, S., Zäll, E., (2021) Artificial intelligence-based models to predict the spatial bedrock levels for geoengineering application. 3rd Conference of the Arabian Journal of Geosciences. CAJG-2020-P856.

Abstract: Delineating and mapping the bedrock and overlaid deposits due to complex spatial patterns, associated uncertainties and sparse data is a vital difficult task in geo-engineering applications. Modern computing techniques such as artificial intelligence-based models (AIM) are appropriate alternative to overcome the deficiencies of previous methods. The objective of this study is to investigate the feasibility of AIM in prediction of 3D spatial distribution of subsurface bedrock in a large area in Stockholm, Sweden. The predictive artificial intelligence models were developed using 1968 processed soil-rock soundings comprising the geographical coordinates and ground surface elevation. The optimum topology was captured through the examining of wide variety of internal characteristics. It was observed that in sparse dataset, the developed AIMs efficiently can provide much more accurate prediction than traditionally applied techniques such as geostatistical approaches. This implies that the developed AIM due to significant capacities and acceptable predictability level can decrease the residuals between the predicted and measured data.