1887

Abstract

Summary

Accurate forecasting of geological structures ahead of the drill bit is critical for safe and efficient geosteering. Such forecasting remains a significant challenge due to uncertainty in plausible layer configurations, which, even in simple formations, may include faults, dips, and folding.

To address this, the open international Geology Forecast Challenge introduced a data-driven benchmark focused on probabilistic prediction of stratigraphic geometry.

Participants were tasked with generating several layer-boundary-depth realizations that capture geological ambiguity while maintaining predictive accuracy.

The dataset consisted of thousands of interpreted one-dimensional lateral stratigraphies from worldwide geosteering operations.

Submitted models were evaluated on a hidden test dataset using the Negative Log-Likelihood metric, which emphasizes uncertainty calibration.

The top-performing approaches employed advanced training and a combination of modern deep-learning architectures.

Results show that probabilistic, sequence-aware machine-learning models can effectively learn geological variability. They provide a foundation for improving uncertainty-aware geosteering decision support in the future.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202639057
2026-03-09
2026-02-15

  • From This Site

    /content/papers/10.3997/2214-4609.202639057
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Ressi BMuhammad, YasamanCheraghi, SergeyAlyaev, ApoorvSrivastava, and Reidar BBratvold. Geosteering robot powered by multiple probabilistic interpretation and artificial intelligence: Benchmarking against human experts. SPE Journal, pages 1–15, 2025.
     [Google Scholar]
  2. Hibat ErrahmenDjecta, SergeyAlyaev, KristianFossum, Reidar B.Bratvold, Ressi BontiMuhammad, and ApoorvSrivastava. Uncertainty-aware well placement: Simulator-verified dual-network reinforcement learning approach meets particle filters. In International Conference on Computational Science, pages 188–202. Springer, 2025.
     [Google Scholar]
  3. SergeyAlyaev, NelloBlaser, AntonFedorov, and IgorKuvaev. Geology forecast challenge. https://kaggle.com/competitions/geology-forecast-challenge-open, 2025. Kaggle.
     [Google Scholar]
  4. AlexBoyd. On the efficient marginalization of probabilistic sequence models, 2024.
     [Google Scholar]
  5. DonglaiZhu, HengshuaiYao, BeiJiang, and PengYu. Negative log likelihood ratio loss for deep neural network classification, 2018.
     [Google Scholar]
  6. SergeyAlyaev. Top solutions of the geology forecast challenge. GitHub repository: https://github.com/geosteering-no/Geology_Forecast_Top, 2025. Accessed: 2025-10-31.
     [Google Scholar]
  7. KaimingHe, XiangyuZhang, ShaoqingRen, and JianSun. Deep residual learning for image recognition, 2015.
     [Google Scholar]
  8. SeppHochreiter and JürgenSchmidhuber. Long short-term memory. Neural Comput., 9(8): 1735–1780, November 1997.
     [Google Scholar]
  9. Diederik RKingma and JimmyBa. Adam: A method for stochastic optimization, 2017.
     [Google Scholar]
  10. XinJin, HongyuZhu, SiyuanLi, ZedongWang, ZichengLiu, JuanxiTian, ChangYu, HuafengQin, and Stan Z.Li. A survey on mixup augmentations and beyond, 2025.
     [Google Scholar]
  11. Ressi BontiMuhammad, ApoorvSrivastava, SergeyAlyaev, Reidar BBratvold, and Daniel MTartakovsky. High-precision geosteering via reinforcement learning and particle filters. Computational Geosciences, 29(2): 14, 2025.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202639057
Loading
Sequence Machine Learning for Geological Forecasting: Insights from the Open Geology Forecast Challenge
Conference Proceedings 2026, 1 (2026); https://doi.org/10.3997/2214-4609.202639057
/content/papers/10.3997/2214-4609.202639057
/content/papers/10.3997/2214-4609.202639057
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

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