Classifying basin‐scale stratigraphic geometries from subsurface formation tops with machine learning. (12th December 2020)

• Record Type: Journal Article
• Authors: Pisel, Jesse R.; Pyrcz, Michael J.
• Is Part Of: Depositional record. Volume 7:Number 1(2021)
• Page Start: 64
• Page End: 76
• Publication Date: 2020-12-12
• Subjects: fluvial -- machine learning -- stratigraphic -- subsurface; Sediments (Geology) -- Periodicals; Sedimentology -- Periodicals; Sedimentation and deposition -- Periodicals; 552.5
• DOI: 10.1002/dep2.129
• Languages: English
• ISSNs: 2055-4877

Abstract

Abstract: Presented here is a transfer‐learning model for classifying basin‐scale stratigraphic geometries from subsurface formation tops. Support vector, decision trees, random forests, AdaBoost and K‐nearest neighbour classification models are evaluated to support this challenge. Each model is trained on labelled synthetic stratigraphic geometry data generated in Python using observable geological principles and concepts. Accuracy is measured using a weighted Jaccard similarity coefficient score, and certainty of each prediction is quantified using margin sampling. The random forest classifier has the highest initial accuracy, and the optimal hyperparameters for the model that yield 88.4% accuracy and 72.8% mean certainty via five‐fold cross‐validation and active learning are documented on a real‐world subsurface dataset. The random forest classifier with optimised hyperparameters is then used to make predictions on the real‐world subsurface formation tops dataset. The dataset consists of formation tops for the Upper Cretaceous and Palaeocene strata of the Eastern Greater Green River Basin in south‐central Wyoming. Results from model predictions include an area of truncation in the Lance Formation across the basin, and an area of onlap and truncation on the nose of the Rock Springs Uplift that previous studies in the region corroborate. It is believed that this model is most useful for guided interpretation, and identifying regions that warrant further inquiry by domain experts. Abstract : We train a machine learning model trained on synthetic data to make predictions on a subsurface dataset. The predictions are validated against 50+ years of outcrop and subsurface studies in the region.