Identification of lithofacies and prediction of mineral composition in shales – A case study of the Shahejie Formation in the Bozhong Sag

Cui, Qinyu; Yang, Haifeng; Li, Xin-Qi; Lu, Yongchao

doi:10.1016/j.uncres.2022.09.002

Cited by 6 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[5][6][7][8] Overall, beach bar sand bodies have favorable conditions to become a target for hydrocarbon exploration activities due to their proximity to the oil source, good reservoir properties and wellconfiguration of source, reservoir and cap rock, which is conducive to large-scale oil and gas enrichment. [9][10][11][12][13][14] In recent years, there has been an increasing focus on beach-bar sedimentary systems for exploring stratigraphic traps in various basins in eastern China. [15][16][17][18] Herein, beach bar sandstones are particular shallowwater deposits, with low mud content and good petrophysical properties.…”

Section: Introductionmentioning

confidence: 99%

“…Beach sand bodies are widely distributed and are relatively small in thickness, while beach bar sand bodies are usually less distributed and relatively large in thickness 5‐8 . Overall, beach bar sand bodies have favorable conditions to become a target for hydrocarbon exploration activities due to their proximity to the oil source, good reservoir properties and well‐configuration of source, reservoir and cap rock, which is conducive to large‐scale oil and gas enrichment 9‐14 . In recent years, there has been an increasing focus on beach‐bar sedimentary systems for exploring stratigraphic traps in various basins in eastern China 15‐18 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin

Liao,

Xiao,

Long

et al. 2024

Energy Science & Engineering

View full text Add to dashboard Cite

Beach bar sand bodies are a relatively new type of reservoir in oil exploration where they can be found in the proximity of the source rock. In this study, the genetic type of sand bodies in the Upper Triassic Yanchang Formation in the southwest Ordos Basin is systematically studied through the observation of outcrops, core description, microscopic inspection of thin sections, along with petrophysical properties, mineralogy, and geochemical analysis of trace elements. The results showed that a new sedimentary type of beach bar sand bodies are developed in the Chang 82 submember of the Yanchang Formation, that are generally characterized with a flat bottom and convex top, where the contact interface between the bottom of the single sand body and mudstone is flat, and the bottom lacks erosion and filling structure. Moreover, a variety of wave‐induced sedimentary structures are developed, showing a reverse sedimentary sequence from fine to coarse grains. The structural and compositional maturity of the beach bar sand bodies are higher than that of the river channel sand body. Moreover, reservoir pore type is mainly comprised of intergranular pores, and the porosity and permeability of the samples retrieved from the sand body are much higher than that of the river channel sand body. Finally, the main controlling factors of the formation and preservation of beach bar sands are found to be the lake basin bottom topography, the base level cycle, and the stable paleo‐lake shoreline. During the Chang 82 submember depositional period, a large area where the beach bar sand bodies were deposited parallel to the lake shoreline in the southwest of the basin was created. Such depositional environments had suitable conditions to host large‐scale oil‐bearing reservoirs, as major exploration and development targets in the Ordos Basin in the future.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin

Liao,

Xiao,

Long

et al. 2024

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…Commonly used methods include nonlinear regression analysis (BPANN), nearest neighbor (KNN), decision tree (DT), and vector machine (SVM). Naive Bayes (NB) is less frequently used due to difficulties in handling interfering data sets [18][19][20][21]. Naive Bayes (NB) is seldom used because it is difficult to deal with data sets that interfere with each other [22,23].…”

Section: Introductionmentioning

confidence: 99%

Application and Comparison of Machine Learning Methods for Mud Shale Petrographic Identification

et al. 2023

View full text Add to dashboard Cite

Machine learning is the main technical means for lithofacies logging identification. As the main target of shale oil spatial distribution prediction, mud shale petrography is subjected to the constraints of stratigraphic inhomogeneity and logging information redundancy. Therefore, choosing the most applicable machine learning method for different geological characteristics and data situations is one of the key aspects of high-precision lithofacies identification. However, only a few studies have been conducted on the applicability of machine learning methods for mud shale petrography. This paper aims to identify lithofacies using commonly used machine learning methods. The study employs five supervised learning algorithms, namely Random Forest Algorithm (RF), BP Neural Network Algorithm (BPANN), Gradient Boosting Decision Tree Method (GBDT), Nearest Neighbor Method (KNN), and Vector Machine Method (SVM), as well as four unsupervised learning algorithms, namely K-means, DBSCAN, SOM, and MRGC. The results are evaluated using the confusion matrix, which provides the accuracy of each algorithm. The GBDT algorithm has better accuracy in supervised learning, while the K-means and DBSCAN algorithms have higher accuracy in unsupervised learning. Based on the comparison of different algorithms, it can be concluded that shale lithofacies identification poses challenges due to limited sample data and high overlapping degree of type distribution areas. Therefore, selecting the appropriate algorithm is crucial. Although supervised machine learning algorithms are generally accurate, they are limited by the data volume of lithofacies samples. Future research should focus on how to make the most of limited samples for supervised learning and combine unsupervised learning algorithms to explore lithofacies types of non-coring wells.

show abstract

Tectonic fracture prediction for lacustrine carbonate oil reservoirs in Paleogene formations of the western Yingxiongling area, Qaidam Basin, NW China based on numerical simulation

Zhuo,

Zhang,

Zhang

et al. 2024

Carbonates Evaporites

View full text Add to dashboard Cite

Identification of lithofacies and prediction of mineral composition in shales – A case study of the Shahejie Formation in the Bozhong Sag

Cited by 6 publications

References 27 publications

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin

Application and Comparison of Machine Learning Methods for Mud Shale Petrographic Identification

Tectonic fracture prediction for lacustrine carbonate oil reservoirs in Paleogene formations of the western Yingxiongling area, Qaidam Basin, NW China based on numerical simulation

Contact Info

Product

Resources

About

Identification of lithofacies and prediction of mineral composition in shales – A case study of the Shahejie Formation in the Bozhong Sag

Cited by 6 publications

References 27 publications

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 82 submember, southwest Ordos Basin

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 82 submember, southwest Ordos Basin

Application and Comparison of Machine Learning Methods for Mud Shale Petrographic Identification

Tectonic fracture prediction for lacustrine carbonate oil reservoirs in Paleogene formations of the western Yingxiongling area, Qaidam Basin, NW China based on numerical simulation

Contact Info

Product

Resources

About

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin

Sedimentary characteristics, formation conditions, and distribution mechanisms of beach bar sand bodies of Chang 8₂ submember, southwest Ordos Basin