Proceedings

Learning 3D Geological Structure from Drill-Rig Sensors for Automated Mining

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2500-2505.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-416

© 2011 International Joint Conferences on Artificial Intelligence

Abstract

This paper addresses one of the key components of the mining process: the geological prediction of natural resources from spatially distributed measurements. We present a novel approach combining undirected graphical models with ensemble classifiers to provide 3D geological models from multiple sensors installed in an autonomous drill rig. Drill sensor measurements used for drilling automation, known as measurement-while-drilling (MWD) data, have the potential to provide an estimate of the geological properties of the rocks being drilled. The proposed method maps MWD parameters to rock types while considering spatial relationships, i.e., associating measurements obtained from neighboring regions. We use a conditional random field with local information provided by boosted decision trees to jointly reason about the rock categories of neighboring measurements. To validate the approach, MWD data was collected from a drill rig operating at an iron ore mine. Graphical models of the 3D structure present in real data sets possess a high number of nodes, edges and cycles, making them intractable for exact inference. We provide a comparison of three approximate inference methods to calculate the most probable distribution of class labels. The empirical results demonstrate the benefits of spatial modeling through graphical models to improve classification performance.

  1. [Besag, 1975] J. Besag. Statistical analysis of non-lattice data. Statistician, 24(3):179-195, 1975.
  2. [Cho et al., 2010] T. S. Cho, S. Avidan, and W. T. Freeman. The patch transform. IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, 32(8):1489-1501, 2010.
  3. [Dietterich et al., 2004] T. G. Dietterich, A. Ashenfelter, and Y. Bulatov. Training conditional random fields via gradi- ent tree boosting. In International Conference on Machine Learning, 2004.
  4. [Friedman et al., 2000] J. Friedman, T. Hastie, and R. Tib- shirani. Additive logistic regression: A statistical view of boosting. Annals of Statistics, 28(2):337-407, 2000.
  5. [Globerson and Jaakkola, 2008] A. Globerson and T. Jaakkola. Fixing max-product: Convergent mes- sage passing algorithms for MAP LP-relaxations. In Advances in Neural Information Processing Systems, pages 553-560, 2008.
  6. [Gutmann and Kersting, 2006] B. Gutmann and K. Kerst- ing. TildeCRF: Conditional random fields for logical se- quences. In European Conference on Machine Learning, pages 174-185, 2006.
  7. [Hastie et al., 2009] T. Hastie, R. Tibshirani, and J. Fried- man. The Elements of Statistical Learning. Springer, New York, NY, USA, 2nd edition, 2009.
  8. [He and Zemel, 2008] X. He and R. Zemel. Learning hybrid models for image annotation with partially labeled data. In Neural Information Processing Systems, pages 625-632, 2008.
  9. [Itakura et al., 2004] K. Itakura, J. Doki, K. Sato, Y. Ichi- hara, and H. Matsumoto. Visualization of roof rock geostructure around tunnel by analysis of mechanical data from MWD. In Asian Rock Mechanics Symposium, vol- ume 1, pages 179-184, 2004.
  10. [Kadkhodaie-Ilkhchi et al., 2010] A. Kadkhodaie-Ilkhchi, S. T. Monteiro, F. Ramos, and P. Hatherly. Rock recog- nition from mwd data: A comparative study of boosting, neural networks, and fuzzy logic. IEEE Geoscience and Remote Sensing Letters, 7(4):680-684, 2010.
  11. [Koller and Friedman, 2009] D. Koller and N. Friedman. Probabilistic Graphical Models: Principles and Tech- niques. MIT Press, 2009.
  12. [Kolmogorov, 2006] V. Kolmogorov. Convergent tree- reweighted message passing for energy minimization. IEEE Transactions on Pattern Analysis and Machine In- telligence, 28(10):1568-1583, 2006.
  13. [Lafferty et al., 2001] J. Lafferty, A. McCallum, and F. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In International Conference on Machine Learning, pages 282-289, 2001.
  14. [Monteiro et al., 2009] S. T. Monteiro, F. Ramos, and P. Hatherly. Conditional random fields for rock character- ization using drill measurements. In International Confer- ence on Machine Learning and Applications, pages 366- 371, 2009.
  15. [Nocedal and Wright, 2000] J. Nocedal and S. J. Wright. Numerical Optimization. Springer Verlag, New York, NY, USA, 2nd edition, 2000.
  16. [Pearl, 1988] J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kauf- mann Publishers Inc., San Francisco, CA, USA, 1988.
  17. [Scoble et al., 1989] M. J. Scoble, J. Peck, and C. Hendricks. Correlation between rotary drill performance parameters and borehole geophysical logging. Mining Science and Technology, 8:301-312, 1989.
  18. [Sokolova and Lapalme, 2009] M. Sokolova and G. La- palme. A systematic analysis of performance measures for classification tasks. Information Processing and Man- agement, 45(4):427-437, 2009.
  19. [Sontag et al., 2008] D. Sontag, T. Meltzer, A. Globerson, T. Jaakkola, and Y. Weiss. Tightening LP relaxations for MAP using message passing. In Uncertainty in Artificial Intelligence, pages 503-510, 2008.
  20. [Sutton and McCallum, 2007] C. Sutton and A. McCallum. An introduction to conditional random fields for relational learning. In L. Getoor and B. Taskar, editors, Introduction to Statistical Relational Learning, chapter 4. MIT Press, 2007.
  21. [Szeliski et al., 2008] R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, and C. Rother. A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 30(6):1068-1080, 2008.
  22. [Teale, 1965] R. Teale. The concept of specific energy in rock drilling. International Journal of Rock Mechanics and Mining Sciences, 2:57-73, 1965.
  23. [Utt, 1999] W. K. Utt. Neural network technology for strata strength characterization. In International Joint Confer- ence on Neural Networks, volume 6, pages 3806-3809, 1999.
  24. [Wainwright and Jordan, 2008] M. J. Wainwright and M. I. Jordan. Foundations and Trends in Machine Learning, volume 1, chapter Graphical Models, Exponential Fami- lies, and Variational Inference, pages 1-305. 2008.
  25. [Wainwright et al., 2005] M. J. Wainwright, T. Jaakkola, and A. S. Willsky. Map estimation via agreement on trees: message-passing and linear programming. IEEE Transac- tions on Information Theory, 51(11):3697-3717, 2005.
  26. [Werner, 2010] T. Werner. Revisiting the linear program- ming relaxation approach to Gibbs energy minimiza- tion and weighted constraint satisfaction. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 32(8):1474-1488, 2010.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards