Usage of Machine Learning Algorithms for Structural Boundaries Reconstruction Using The Non-Seismic Methods Data with Feature Selection

Zaycev, S.V.; Ahmetsafin, R.D.; Budennyj, S.A.; Zhuravlev, S.D.; Kiselev, Kirill; Orlov, R.V.; Smelov, Artem S.; Grigorev, G.S.; Gulin, V.D.; Ananev, Vladislav Valerievich

doi:10.3997/2214-4609.202156005

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction of the faults scheme is essential in geoscience, as it helps in understanding the structural and tectonic evolution of the area and also in resource exploration and exploitation. The accuracy of the interpretation can be increased by using a larger dataset for training, and by using additional methods to switch to the usual linear type of faults [17,18]. The estimated permissible data error for the interpretation is about 10%.…”

Section: Case Study Prediction Of Faultsmentioning

confidence: 99%

Combining non-seismic and seismic information for geological understanding - a case study

2023

View full text Add to dashboard Cite

Non-seismic methods such as gravity and magnetic prospecting can provide valuable complementary information in oil and gas exploration in complex with seismic data. The integration of seismic and non-seismic research has become increasingly important in recent years due to advancements in technology and the use of artificial intelligence. The integration of these methods allows for a more comprehensive understanding of the subsurface and can improve the accuracy of predictions. Three examples highlight the potential benefits of integrating potential field data into the seismic interpretation process, including improved accuracy in predicting structural surfaces, the ability to predict discontinuous disturbances, and the ability to restore the depth-velocity model are given. The potential benefits of integrating, particularly in the context of sites located in Siberia, are pointed.

show abstract

Section: Case Study Prediction Of Faultsmentioning

confidence: 99%