The results from the artificial intelligence challenge issued last
year by Norway’s FORCE industry body are now in. The challenge involved
predicting lithology from a labelled set of North Sea logs from
Norway’s Diskos repository. Labeling was performed by Stavanger-based Explocrowd and I2G.cloud.
The open data set now comprises ‘the first truly open lithology
interpretation dataset in the world’. Some 400 teams took part in the
contest. The winner was Olwale Ibrahim, an applied geophysics student from the Federal University of Technology Akure, Nigeria. Runners-up were the GIR research team from Brazil’s Universidade Estadual do Norte Fluminense and the Lab ICA Team at the Pontifical Catholic University of Rio de Janeiro.
Commenting the results, the challenge organizer, Equinor’s John Borman observed, ‘Comparing the machine predictions to inhouse data and vendor purchased data I came to conclude that the machine predictions offer an extremely valid second opinion and often highlight the shortcoming in these large databases that have been curated, somewhat inconsistently, over the past 50 years’. All data, submitted machine learning codes and final scores are here and you can read the full report of the challenge here.
© Oil IT Journal - all rights reserved.