Vol.:(0123456789) GEM - International Journal on Geomathematics (2020) 11:8 https://doi.org/10.1007/s13137-020-0145-3 1 3 ORIGINAL PAPER Lithology prediction in the subsurface by artifcial neural networks on well and 3D seismic data in clastic sediments: a stochastic approach to a deterministic method Ana Kamenski 1  · Marko Cvetković 2  · Iva Kolenković Močilac 2  · Bruno Saftić 2 Received: 30 September 2019 / Accepted: 23 January 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020 Abstract A small area covered by a seismic volume was selected for the analysis of using arti- fcial neural networks for the purpose of lithology modelling in a stochastic approach to an otherwise deterministic method. Subsurface lithology was simplifed to three categories (sandstone, marl and coal) in accordance with the general geological com- position of the Pannonian age sediments in the eastern part of Drava Depression. Two approaches to artifcial neural networks were used—training and prediction with a large number of networks with diferent architecture, and with the same architecture but with the variability of dataset distribution of cases for error calculation in the learning process. Out of a 1000 total cases, 100 realizations of each approach were singled out upon which the data points with probability of 50%, 75% and 90% of occurrence of certain lithology category were upscaled in the model. Six models were generated by indicator kriging. Although in theory, the higher accuracy data should provide a more accurate result, the geologically most sound results were obtained by 50% accuracy data. In higher accuracy results, sandstone lithology was unrealistically over emphasized as a result of the upscaling process, variography and statistical anal- ysis. Presented research can be used in all geoenergy-related subsurface explorations, including hydrocarbon and geothermal explorations, and subsurface characterization for CO 2 storage potential and underground energy storage potential as well. Keywords Geological modelling · Artifcial neural networks · Stochastics · Lithology · Probability · Pannonian Basin Mathematics Subject Classifcation 86A32 · 86A60 Electronic supplementary material The online version of this article (https://doi.org/10.1007/s1313 7-020-0145-3) contains supplementary material, which is available to authorized users. * Marko Cvetković marko.cvetkovic@unizg.rgn.hr Extended author information available on the last page of the article