Mineral inversion for element capture spectroscopy logging based on optimization theory

Zhao, Jianpeng; Chen, Hui; Yin, Lu; Li, Ning

doi:10.1088/1742-2140/aa7bfa

Cited by 18 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the GLT continuously records down a borehole and provides an in‐situ method for estimating mineralogical composition (e.g., Hertzog & Plasek, 1979; Hertzog, 1980; Herron, 1986; Hertzog et al., 1989; Pratson et al., 1992). Various approaches have been attempted to improve the accuracy of converting elemental measurements into quantitative estimates of mineralogy (e.g., Freedman et al., 2015; Harvey et al., 1990, 1992; Herron & Herron, 1996; Lofts et al., 1995; Zhao et al., 2017). To date, some modern GLTs newly developed provide accurate in‐situ mineralogical characterization for conventional and unconventional reservoirs (e.g., Pemper et al., 2018).…”

Section: Introductionmentioning

confidence: 99%

Mineralogical Characterization From Geophysical Well Logs Using a Machine Learning Approach: Case Study for the Horn River Basin, Canada

Hu,

Liu,

Chen

et al. 2023

Earth and Space Science

View full text Add to dashboard Cite

Accurate estimation of mineral composition is essential for refined reservoir characterization, thermal conductivity and mechanical determinations of sedimentary rocks, but is extremely challenging in shale units due to the mineralogical complexity, low porosity and ultra‐low permeability. Direct mineral measurements derived from laboratory X‐ray diffraction (XRD) analysis on core samples and borehole geochemical logging tool (GLT), and conventional geophysical logs from vertical wells penetrating sediments are widely available in some basins, which enables detailed mineralogical characterization of a well. A hybrid machine learning (ML) architecture that improves model training and validation by combining convolutional neural network (CNN) with XGBoost allows accurate description of the mineralogical compositions across a basin. We applied this ML approach to predict the mineral compositions using conventional well logs from the Horn River Basin, northeast British Columbia, Canada, where extensive drilling for shale‐gas and conventional hydrocarbon resources, complemented by high temperature geothermal energy potential is ideal for case testing. The predicted mineral compositions from the ML approach are consistent with the mineralogical readings from the GLT and are confirmed by the XRD mineral measurements. This allows basin‐wide mineral compositions mapping that reveals spatial trends of major mineral compositions and their relationship with the previously recognized geomechanical and geological features, which have important implications for thermal conductivity modeling, reservoir evaluation and extensive geological studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Mineralogical Characterization From Geophysical Well Logs Using a Machine Learning Approach: Case Study for the Horn River Basin, Canada

Hu,

Liu,

Chen

et al. 2023

Earth and Space Science

View full text Add to dashboard Cite

show abstract

“…A traditional approach, called by some authors a probabilistic model, consists of defining a system of equations in which the input values corresponding to each well log are approximated by combining the individual responses of the different components – minerals and fluids – constituents of formation considered in the model, as a function of their respective volume fractions (Collett et al., 2011; El‐Bagoury, 2020; Mitchell & Nelson, 1988; Stadtmuller et al., 2018). Another widely used approach, here called the direct model, consists of calculating the mineral fractions exclusively from the concentrations of chemical elements in the rock matrix acquired by the geochemical tool (Anderson et al., 1988; Flaum & Pirie, 1981; Herron et al., 2014; Zhao et al., 2017). A third class, called the machine learning model, was recently introduced where mineral models are created through trained artificial intelligence algorithms using experimental chemical and mineral composition analysis in rock samples and applied to geochemical logs (de Oliveira et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

Hybrid mineral model integrating probabilistic and machine learning approaches for the Brazilian pre‐salt carbonate reservoirs

Oliveira

Freitas

Pesce

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

Well mineralogy can be estimated from probabilistic, direct and machine learning models; however, all these models have limitations. The maximum number of components in probabilistic models is restricted to the number of logs plus one. Direct models require the precise composition of minerals. Machine learning models demand unbiased databases, a challenge as the samples are collected in reservoir intervals. These limitations impact the evaluation for the Santos Basin pre‐salt rocks due to the complexity of facies and magnesian clays. This work proposes creating a hybrid model through the combination of probabilistic and machine learning models. First, mineral fractions of calcite, dolomite, quartz, k‐feldspar, detrital clay, plagioclase and pyroxene are estimated by the algorithm XGBoost trained using rock samples. Then, a probabilistic model reconstructs the well logs and machine learning estimations through the seven minerals mentioned plus magnesian clays, pyrite, barite and fluids. The difference between the real and reconstructed responses is minimized, weighted by the curves’ uncertainties. The hybrid model is used to estimate the mineralogy of three wells drilled in the Santos Basin, honouring the mineralogy of the rock samples collected in these wells and improving the quantification of dolomite, pyroxene and magnesian clay. Among the advances introduced, the following stand out: The use of machine learning estimates and well logs improved the quantification of magnesian clay; the machine learning estimates regularized the probabilistic model, generating more coherent results; the uncertainties of the machine learning algorithms dealt with database bias. The hybrid model mitigated limitations related to database bias without the costs associated with collecting more samples.

show abstract

“…The relative elemental yields of the formation are calculated using the Elemental Capture Spectroscopy (ECS) tool. Calcium (Ca), silicon (Si), magnesium (Mg), iron (Fe), sulfur (S), titanium (Ti), and gadolinium (Gd) are among the elemental yields determined from ECS spectra, with hydrogen providing a measure of the pore space and borehole fluids but otherwise being ignored in the mineralogy determination [4].…”

Section: -Introductionmentioning

confidence: 99%

Accurate Petrophysical Interpretation of Carbonate using the Elemental Capture Spectroscopy (ECS)

Alameedy

2023

IJCPE

View full text Add to dashboard Cite

Elemental capture spectroscopy (ECS) is an important tool in the petroleum industry for determining the composition and properties of rock formations in a reservoir. Knowledge of the types and abundance of different minerals in the reservoir is crucial for accurate petrophysical interpretation, reservoir engineering practices, and stratigraphic correlation. ECS measures the elemental content of the rock, which directly impacts several physical properties that are essential for reservoir characterization, such as porosity, fluid saturation, permeability, and matrix density. The ability to accurately determine these properties leads to better reservoir mapping, improved production, and more effective resource management. Accurately determining the mineralogy and porosity of carbonate rocks and other materials is the aim of this paper. Calcite, dolomite, quartz, clay (illite), anhydrite, and pyrite, in addition to water as a fluid, are taken into account in the computation. The formation's lithology and porosity can be ascertained from this data. When compared to the core descriptions in the geological report, the results demonstrated a distinct zone of unique lithology with good prediction accuracy.

show abstract

Mineral inversion for element capture spectroscopy logging based on optimization theory

Cited by 18 publications

References 23 publications

Mineralogical Characterization From Geophysical Well Logs Using a Machine Learning Approach: Case Study for the Horn River Basin, Canada

Mineralogical Characterization From Geophysical Well Logs Using a Machine Learning Approach: Case Study for the Horn River Basin, Canada

Hybrid mineral model integrating probabilistic and machine learning approaches for the Brazilian pre‐salt carbonate reservoirs

Accurate Petrophysical Interpretation of Carbonate using the Elemental Capture Spectroscopy (ECS)

Contact Info

Product

Resources

About