Brittleness index prediction in shale gas reservoirs based on efficient network models

Shi, Xian; Lei, Gang; Cheng, Yuanfang; Liu, Yang; Jiang, Hailong; Chen, Lei; Jiang, Shu; Wang, Jian

doi:10.1016/j.jngse.2016.09.009

Cited by 36 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various machine learning (ML) methods offer more generalizable approaches to well-log based BI predictions (Kaunda and Asbury, 2016;Wood, 2021). ML methods tend to exploit multiple combinations of the basic suite of recorded well logs (Shi et al, 2016;Verma et al, 2016), typically, gamma ray (GR), bulk density (PB), deep resistivity (RS), neutron porosity (NP), and compressional sonic (DT). However, a substantial constraint to applying such ML methods in practice is that many of the wells drilled in shale provinces do not acquire a complete basic suite of well logs.…”

Section: Bi =mentioning

confidence: 99%

Predicting brittleness indices of prospective shale formations from sparse well-log suites assisted by derivative and volatility attributes

Wood

2022

Adv. Geo-Energy Res.

View full text Add to dashboard Cite

show abstract

Section: Bi =mentioning

confidence: 99%

Predicting brittleness indices of prospective shale formations from sparse well-log suites assisted by derivative and volatility attributes

Wood

2022

Adv. Geo-Energy Res.

View full text Add to dashboard Cite

show abstract

“…The brittleness index is a function of the mineral composition, diagenesis and organic content [38]. Brittleness index is one of the critical geomechanical properties for shale reservoir rocks to screen effective hydraulic fracturing candidates [42]. According to Lou et al [43], it can be influenced by mineral composition and particle size distribution.…”

Section: Brittleness Indexmentioning

confidence: 99%

Pore Structure Characteristics and Gas Storage Potential of the Cretaceous La Luna Formation, Middle Magdalena Valley Basin, Colombia

Casadiego-Quintero

Ríos‒Reyes

2020

ing.cienc

View full text Add to dashboard Cite

The rocks of interest in the present study (mudstones) show inherently a heterogeneous pore-size distribution in the matrix. They can present organic and inorganic pores and the transport mechanism through pores is different, and, therefore, it is necessary to describe their organic and inorganic porosity. This work uses different microscopy techniques to characterize mudstones from the Galembo Member of the Cretaceous La Luna Formation, Middle Magdalena Valley Basin, Colombia. These rocks present several pore types, including interparticle pores due to flocculation of clay minerals, organoporosity due to burial and thermal maturity, intraparticle pores from organisms, intraparticle pores within mineral grains, and microchannels and microfractures. The existence of interconnected pores in such complex fracture-pore system provides effective pathways for primary gas migration and it also provides a storage space for the residual hydrocarbon in mudstones, which is important for the primary migration and storage in gas reservoir rocks. The pore connectivity is high and increases towards the top of the sedimentary sequence.

show abstract

“…Several scholars used MFFNN and MLR methods to predict the brittleness index using nondestructive tests and physical characteristics [11][12][13]. Altindag and Guney [14] presented some relationships to estimate brittleness based on UCS, Schmidt hardness number, and Ts.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Rock's Brittleness and Dynamic Properties Utilizing Effective Artificial Intelligence Approaches

Xie,

Wang,

et al. 2024

Period. Polytech. Civil Eng.

View full text Add to dashboard Cite

This research aims to determine the brittleness index (BI) and engineering properties of limestone specimens. In addition, this study evaluates the effect of moisture on the developed models to predict the BI and shear wave velocity (Vs), based on the point load index (Is50), dry and saturated tensile strength (Ts-d and Ts-s), and porosity. Gaussian process regression (GPR), multilayer feed-forward neural network (MFFNN), and multiple linear regression (MLR) predictive models were utilized. Microscopic examination of the limestone specimens revealed that calcite is the predominant mineral. It was observed that samples with higher calcite content exhibited greater brittleness and strength properties while having lower porosity. The results obtained from the MLR analysis demonstrated that it is possible to accurately forecast the brittleness index (BI), as well as the dry and saturated shear wave velocities (Vs-d and Vs-s) at the specific sites under investigation. The moisture effect on developed models showed that Vs prediction in dry conditions (Vs-d) was less accurate compared to the saturated conditions (Vs-s). Conversely, the relationships developed for estimating the BI in dry conditions exhibited higher accuracy. The analysis of all model assumptions using MLR indicated that the models could be reliably utilized. However, the MFFNN and GPR methods were found to be more conservative in estimating these properties. Moreover, the study identified the best transfer function and training algorithm for predicting Vs and BI. The evaluation metrics, such as R2 and RMSE revealed that GPR demonstrated higher precision compared to MFFNN and MLR.

show abstract

Brittleness index prediction in shale gas reservoirs based on efficient network models

Cited by 36 publications

References 28 publications

Predicting brittleness indices of prospective shale formations from sparse well-log suites assisted by derivative and volatility attributes

Predicting brittleness indices of prospective shale formations from sparse well-log suites assisted by derivative and volatility attributes

Pore Structure Characteristics and Gas Storage Potential of the Cretaceous La Luna Formation, Middle Magdalena Valley Basin, Colombia

Prediction of Rock's Brittleness and Dynamic Properties Utilizing Effective Artificial Intelligence Approaches

Contact Info

Product

Resources

About