Challenge 6, 2019

Using Machine Learning to Understand Uncertainty in Subsurface Exploration

Keith Gray, Max Grossman, Anar Yusifov
BP plc

In the energy industry, an understanding of subsurface characteristics and structure is crucial to identifying and localizing untapped resources. At a high level, the process of taking an entirely unexplored region of earth and generating an actionable understanding of its structure includes:

  1. Seismic data collection
  2. Seismic data preprocessing
  3. Seismic migration and velocity model construction
  4. Seismic interpretation

Data Provided

  • A set of synthetic (but realistic) velocity models, generated from a single, synthetic, ground truth. That is, each of these velocity models could realistically be expected to be true for a given region of Earth.
  • For each of those velocity models, a realization (i.e., seismic volume) derived by running the corresponding seismic traces through a seismic migration kernel using the corresponding velocity model as an estimate of subsurface velocity.
  • For each of those velocity models, the gathers for all offset pairs in the synthetic survey.

Data Challenge Goals

Construct an uncertainty map for a given seismic survey, labeling each pixel in a final 2D seismic image with a value between 0.0 and 1.0, indicating how volatile the estimate for that pixel is.

Challenge Questions

  • Given that geophysicists generally use horizontal lines in gathers as a good indicator of velocity model accuracy, build a model (analytical, mathematical, data-driven, or other format) to estimate the quality of each velocity model based on its associated gathers.
  • Train a model to label each pixel with an uncertainty value between 0.0 and 1.0, indicating how uncertain any given realization of that part of the subsurface is.
  • Generate a single uncertainty map given all of the velocity models, realizations, and gathers at hand.
  • Generate of visualizations of this uncertainty map of the subsurface.

Download the PDF-file to learn more about seismic surveys.