A Stratigraphic Prediction Method Based on Machine Learning
Source abstract
Abstract
Simulation of a geostratigraphic unit is of vital importance for the study of geoinformatics, as well as geoengineering planning and design. A traditional method depends on the guidance of expert experience, which is subjective and limited, thereby making the effective evaluation of a stratum simulation quite impossible. To solve this problem, this study proposes a machine learning method for a geostratigraphic series simulation. On the basis of a recurrent neural network, a sequence model of the stratum type and a sequence model of the stratum thickness is successively established. The performance of the model is improved in combination with expert-driven learning. Finally, a machine learning model is established for a geostratigraphic series simulation, and a three-dimensional (3D) geological modeling evaluation method is proposed which considers the stratum type and thickness. The results show that we can use machine learning in the simulation of a series. The series model based on machine learning can describe the real situation at wells, and it is a complimentary tool to the traditional 3D geological model. The prediction ability of the model is improved to a certain extent by including expert-driven learning. This study provides a novel approach for the simulation and prediction of a series by 3D geological modeling.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geological Modeling and Analysis · Reservoir Engineering and Simulation Methods · Geochemistry and Geologic Mapping
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Civil Engineering, Sun Yat-sen University, Guangzhou 510275, China
Guangdong Engineering Research Centre for Major Infrastructure Safety, Guangzhou 510275, China
Funding
Provincial Science and Technology Project of Guangdong Province · Science and Technology Youth Top-Notch Talent Project of Guangdong Special Support Program · Guangzhou Science and Technology Project
References (39)
Show source-provided references
1. Conditioning surface-based geological models to well and thickness data10.1007/s11004-013-9455-4 ↗
2. Building 3D solid models of sedimentary stratum systems from borehole data: An automatic method and case studies10.1016/j.enggeo.2011.12.001 ↗
3. Hydrogeologic unit flow characterization using transition probability geostatistics10.1111/j.1745-6584.2005.0007.x ↗
4. Qiao, J., Pan, M., Li, Z., and Jin, Y. (2011, January 24–26). 3D Geological modeling from DEM, boreholes, cross-sections and geological maps. Proceedings of the 2011 19th International Conference on Geoinformatics, Shanghai, China.10.1109/GeoInformatics.2011.5980941 ↗
5. Uncertainty assessment in the stratigraphic well correlation of a carbonate ramp: Method and application to the Beausset Basin, SE France10.1016/j.crte.2015.10.002 ↗
6. Uncertainty management in stratigraphic well correlation and stratigraphic architectures: A training-based method
7. The “Glass Earth”—Geochemical frontiers in exploration through cover
8. A topology for 3D vector maps
9. A survey of construction and manipulation of octrees10.1016/0734-189X(88)90092-8 ↗
10. Houlding, S.W. (1994). 3D Geoscience Modeling—Computer Techniques for Geological Characterization, Springer.10.1007/978-3-642-79012-6 ↗
11. Caumon, G., and Mallet, J.L. (2006, January 3–8). 3D Stratigraphic models: Representation and stochastic modelling. Proceedings of the IAMG 2006, Liège, Belgium.
12. Discrete Smooth Interpolation10.1145/62054.62057 ↗
13. Mallet, J.L. (2002). Geomodeling, Oxford University Press.
14. Mallet, J.L. (2014). Elements of Mathematical Sedimentary Geology: The GeoChron Model, EAGE.10.3997/9789462820081 ↗
15. Uncertainty in geological interpretations: Effectiveness of expert elicitations10.1130/GES01586.1 ↗
16. Machine Learning: A Maturing Field10.1007/BF00993251 ↗
17. Machine learning as an experimental science10.1007/BF00115008 ↗
18. Induction of Decision Trees10.1007/BF00116251 ↗
19. Statistical modeling: The two cultures (with comments and a rejoinder by the author)10.1214/ss/1009213726 ↗
20. Bachri, I., Hakdaoui, M., Raji, M., Teodoro, A.C., and Benbouziane, A. (2019). Machine Learning Algorithms for Automatic Lithological Mapping Using Remote Sensing Data: A Case Study from Souk Arbaa Sahel, Sidi Ifni Inlier, Western Anti-Atlas, Morocco. ISPRS Int. J. Geo-Inf., 8.10.3390/ijgi8060248 ↗
21. Chen, L., Ren, C., Li, L., Wang, Y., Zhang, B., Wang, Z., and Li, L. (2019). A Comparative Assessment of Geostatistical, Machine Learning, and Hybrid Approaches for Mapping Topsoil Organic Carbon Content. ISPRS Int. J. Geo-Inf., 8.10.3390/ijgi8040174 ↗
22. Mueller, E., Sandoval, J., Mudigonda, S., and Elliott, M. (2019). A Cluster-Based Machine Learning Ensemble Approach for Geospatial Data: Estimation of Health Insurance Status in Missouri. ISPRS Int. J. Geo-Inf., 8.10.3390/ijgi8010013 ↗
23. Learning to Recognize Volcanoes on Venus10.1023/A:1007400206189 ↗
24. A machine learning approach to the potential-field method for implicit modeling of geological structures10.1016/j.cageo.2017.03.015 ↗
25. Klump, J.F., Huber, R., Robertson, J., Cox, S.J., and Woodcock, R. (2004, January 15–19). Linking descriptive geology and quantitative machine learning through an ontology of lithological concepts. Proceedings of the AGU Fall Meeting Abstracts 2014, San Francisco, CA, USA.
26. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines10.1016/j.oregeorev.2015.01.001 ↗
27. Artificial Neural Networks for Mineral-Potential Mapping: A Case Study from Aravalli Province, Western India10.1023/A:1025171803637 ↗
28. Zhang, T. (2016). The Relationships between Rock Elements and the Igneous Rocks, the Lithologic Discrimination and Mineral Identification of Sedimentary Rocks: A Study Based on the Method of Artificial Neural Network. [Ph.D. Thesis, Northwest University].
29. Zhang, Y., Su, G., and Yan, L. (2011). Gaussian Process Machine Learning Model for Forecasting of Karstic Collapse. International Conference on Applied Informatics and Communication, Springer.10.1007/978-3-642-23214-5_48 ↗
30. Well-Log and Seismic Data Integration for Reservoir Characterization: A Signal Processing and Machine-Learning Perspective10.1109/MSP.2017.2776602 ↗
31. Gaurav, A. (2017). Horizontal shale well eur determination integrating geology, machine learning, pattern recognition and multivariate statistics focused on the permian basin. SPE Liquids-Rich Basins Conference-North America, Society of Petroleum Engineers.10.2118/187494-MS ↗
32. Recognition and Measurement of Pavement Disasters Based on Convolutional Neural Networks
33. Connor, J.T., Martin, R.D., and Atlas, L.E. (1994). Recurrent Neural Networks and Robust Time Series Prediction, IEEE Press.10.1109/72.279188 ↗
34. Graves, A. (2012). Supervised Sequence Labelling with Recurrent Neural Networks, Springer.10.1007/978-3-642-24797-2 ↗
35. Lamb, A.M., Goyal, A.G., Zhang, Y., Zhang, S., Courville, A.C., and Bengio, Y. (2016). Professor Forcing: A New Algorithm for Training Recurrent Networks. Advances in Neural Information Processing Systems, Proceedings of the 30th Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 5–10 December 2016, Curran Associates, Inc.
36. Minority oversampling in kernel adaptive subspaces for class imbalanced datasets10.1109/TKDE.2017.2779849 ↗
37. Maximal causes for non-linear component extraction
38. Application of BP neural network in insider rock identification of Taiguyu in Liaohe
39. Royer, J.J., Mejia, P., Caumon, G., and Collon, P. (2015). 3D and 4D Geomodelling Applied to Mineral Resources Exploration—An Introduction. 3D, 4D and Predictive Modelling of Major Mineral Belts in Europe, Springer.10.1007/978-3-319-17428-0_4 ↗