Schmidt institute of physics of the Earth of the RAS
Moscow, Russian Federation
Russian Federation
Moscow, Russian Federation
Despite the impressive list of examples of the integration of pattern recognition theory into various activities in the development of oil and gas fields, the authors propose a fundamentally new approach to the use of artificial intelligence. The paper considers in detail the algorithm for searching for extremity zones, based on discrete mathematical analysis (DMA), as applied to the problem of identifying geological hazards. The application of the method is shown on models of the physical properties of rocks reconstructed from seismic data. Potentially, it can also be applied directly to the wave seismic field to identify objects.
Discrete mathematical analysis, density, geological section, permafrost, gas content
1. Averkin A. N., Batyrshin I. Z., Blishun A. F., Silov V. B., Tarasov V. B. Fuzzy sets in control and artificial intelligence models. - Science, Moscow, 1986. - (In Russian).
2. Kolyubakin A. A., Roslyakov A. G., Mironyuk S. G., Pirogova A. S., Tokarev M. Y., Ksenofontova M. A. Study of priority geological hazards in preparation for exploration work on the Laptev Sea shelf // Engineering surveys. - 2017. - № 10. - P. 36-52. - DOI:https://doi.org/10.25296/1997-8650-2017-10-36-52. - (In Russian).
3. Mironyuk S. G., Roslyakov A. G. Frozen soils of the Arctic Sea shelf: approaches to detection and study // Foundations. - 2021. - № 1. - P. 17-21. - (In Russian).
4. Pirogova A. S., Tikhotsky S. A., Tokarev M. Y., Suchkova A. V. Forecast of elastic-strength properties of bottom soils based on inversion of ultra-high and ultra-high resolution seismic data // Geophysical processes and Biosphere. - 2019. - Vol. 18, № 4. - P. 191-202. - DOI:https://doi.org/10.21455/gpb2019.4-16. - (In Russian).
5. Agayan S., Bogoutdinov S., Kamaev D., Kaftan V., Osipov M., Tatarinov V. Theoretical Framework for Determination of Linear Structures in Multidimensional Geodynamic Data Arrays // Applied Sciences. - 2021. - Vol. 11, no. 24. - P. 11606. - DOI:https://doi.org/10.3390/app112411606.
6. Agayan S., Bogoutdinov S., Krasnoperov R. Short introduction into DMA // Russian Journal of Earth Sciences. - 2018. - Vol. 18, no. 2. - P. 1-10. - DOI:https://doi.org/10.2205/2018ES000618.
7. Jaglan H., Kocsis G., Lakhlifi A., Groot P. de. Experiences with Machine Learning and Deep Learning Algorithms for Seismic, Wells and Seismic-to-Well Applications // 82nd EAGE Annual Conference & Exhibition. - European Association of Geoscientists & Engineers, 2021. - DOI:https://doi.org/10.3997/2214-4609.202010990.
8. Marsset B., Thomas Y., Sultan N., Gaillot A., Stephan Y. A multi-disciplinary approach to ma- rine shallow geohazard assessment // Near Surface Geophysics. - 2012. - Vol. 10, no. 4. - P. 279-288. - DOI:https://doi.org/10.3997/1873-0604.2012012.
9. Sacrey D., Roden R. Solving exploration problems with machine learning // First Break. - 2018. - Vol. 36, no. 6. - P. 67-72. - DOI:https://doi.org/10.3997/1365-2397.n0100.
