FORCE: Machine Predicted Lithology was a challenging facies classification contest using well logs from the North Sea’s Norwegian coast. As we built different machine learning workflows to predict the lithofacies best, we encountered a few interesting challenges. The first involved merging different lithofacies to one single class and balancing the predictions accordingly with the class frequencies. The second was related to the contest metric. It did not consider the imbalanced classes. In fact, the most sampled classes, like the shale, which corresponded to 62% of the observations, were more critical. Our initial workflow focused on balancing the classes, and our balanced accuracy metric score was 0.56, while the contest metric was −1.35. In the second approach, we threw off the imbalanced classes consideration, and by doing so, we could improve the contest metric to −0.58, but with a trade-off on the balance accuracy score, which decreased to 0.41.
Pitfalls and insights from a machine learning contest on log facies classification
- Share Icon Share
- Search Site
Guarido, Marcelo, Emery, David J., Macquet, Marie, Trad, Daniel O., and Kristopher A. Innanen. "Pitfalls and insights from a machine learning contest on log facies classification." Paper presented at the SEG/AAPG/SEPM First International Meeting for Applied Geoscience & Energy, Denver, Colorado, USA and online, September 2021. doi: https://doi.org/10.1190/segam2021-3580872.1
Download citation file: