1887

Abstract

Summary

We compared variations of the two most relevant and widespread approaches for reservoir analogs: search by manual filtering and search by similarity measures with properties weights. The filtering approach tends to be a conventional way of search which can be easily performed manually by geologists, but its results seems to underestimate and limit the width of possibilities. The similarity approach has a more sophisticate implementation and, therefore, offers a range of additional useful analytics. Sensitivity analysis was performed using SHAP values which opens the way to evaluate the effect of different properties to the resulting list of analogs and revealing causal links between these properties themselves.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202053163
2020-11-16
2024-03-29
Loading full text...

Full text loading...

References

  1. O.Popova
    . Analogy in the World of Geological Uncertainties or How Reservoir Analogs May Refine Your Probabilistic Geomodel. Annual Caspian Technical Conference and Exhibition Proceedings. 2018.
    [Google Scholar]
  2. M.Perez-Valiente, M.Rodriguez, C.Santos, M.Vieira, S.Embid
    . Identification of Reservoir Analogues in the Presence of Uncertainty. SPE Intelligent Energy Conference & Exhibition Proceedings. 2014.
    [Google Scholar]
  3. M.Rodriguez, E.Escobar, S.Embid, N. RodriguezMorillas, M.Hegazi, L.Lake
    . New approach to identify analogous reservoirs. SPE Annual Technical Conference and Exhibition Proceedings. 2014.
    [Google Scholar]
  4. R.Silva, L.Gualda, L.Lima, E. VitalBrazil, R.Cerqueiro, R.Paula, U.Mello
    . Sensitivity analysis in a machine learning methodology for reservoir analogues. Rio Oil & Gas Expo and Conference Proceedings. 2018.
    [Google Scholar]
  5. S.Lundberg, S.Lee
    . A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems30. 2017
    [Google Scholar]
  6. A.Perez-Suay, G.Camps-Valls
    . Causal Inference in Geoscience and Remote Sensing from Observational Data. IEEE Transactions on Geoscience and Remote Sensing. 2018.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202053163
Loading
/content/papers/10.3997/2214-4609.202053163
Loading

Data & Media loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error