Lithology and mineralogy recognition from geochemical logging tool data using multivariate statistical analysis

Konaté, Ahmed Amara; Ma, Huolin; Pan, Heping; Qin, Zhihong; Ahmed, Hafizullah Abba; Dembélé, N'dji dit Jacques

doi:10.1016/j.apradiso.2017.06.041

Cited by 12 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1997) or Konaté et al. (2017) was not possible. Consequently, we chose a rather simple approach and formed trend curves (TCs) from logs with similar deviation for rock classification.…”

Section: Discussionmentioning

confidence: 96%

“…The results of core-log correlation at the pilot hole allowed to define a detailed lithological column for the nearly un-cored main hole and to estimate the physical properties. A similar approach was used in the Continental Scientific Drilling Program in the Sulu-Dabie ultra-high pressure terrane, where Konaté et al (2017) applied cross plot and principal component analysis to various dry weight percent oxide concentration logs to characterize the lithology and derive the mineralogy. Their method allowed them to determine the different characteristics of eclogite, orthogneiss, amphibolite, and paragneiss.…”

Section: Log-core Correlation and Its Relevance For Lithological Clasmentioning

confidence: 99%

“…The dark blue areas in the first columns indicate groups of high amplitude reflections, the light blue ones highlight groups of minor amplitude reflections. done by Pechnig et al (1997) or Konaté et al (2017) was not possible. Consequently, we chose a rather simple approach and formed trend curves (TCs) from logs with similar deviation for rock classification.…”

Section: Log-core Correlation and Its Relevance For Lithological Clasmentioning

confidence: 99%

See 2 more Smart Citations

Core‐Log‐Seismic Integration in Metamorphic Rocks and Its Implication for the Regional Geology: A Case Study for the ICDP Drilling Project COSC‐1, Sweden

Elger

Berndt

Kästner

et al. 2021

Geochem Geophys Geosyst

View full text Add to dashboard Cite

Beyond a general scientific curiosity about the nature of the continental crust and its formation, detailed information on its lower and middle parts is a prerequisite for mineral and geothermal exploration and the assessment of earthquake hazards. For example, some of the most damaging earthquakes such as in Nepal (2015; Mw 7.8) and Sichuan (2008; Mw 7.9) occur in continental collision zones (Hubbard et al., 2016; Lin et al., 2009). Continental crust is up to 70 km thick. Thus, the lower crustal processes in active continental collision zones (e.g., formation of mafic or ultramafic cumulate rocks and emplacement of magma from the mantle) occur at too great depth to be studied directly (Arndt & Goldstein, 1989; Hacker et al., 2015), far beyond the reach of boreholes, for example, the deepest borehole on Kola peninsula was 12 km deep

show abstract

“…(1997) or Konaté et al. (2017) was not possible. Consequently, we chose a rather simple approach and formed trend curves (TCs) from logs with similar deviation for rock classification.…”

Section: Discussionmentioning

confidence: 96%

Section: Log-core Correlation and Its Relevance For Lithological Clasmentioning

confidence: 99%

Section: Log-core Correlation and Its Relevance For Lithological Clasmentioning

confidence: 99%

See 1 more Smart Citation

Core‐Log‐Seismic Integration in Metamorphic Rocks and Its Implication for the Regional Geology: A Case Study for the ICDP Drilling Project COSC‐1, Sweden

Elger

Berndt

Kästner

et al. 2021

Geochem Geophys Geosyst

View full text Add to dashboard Cite

show abstract

“…This procedure includes two processes: raising dimensions to get nonlinear information and reducing dimensions to get classification features. Cross plots and Principal Component Analysis were used to lithology characterization and mineralogy description from geochem-ical logging tool data [10]. In [6], five machine learning methods were employed to classify the formation lithology identification using well log data samples.…”

Section: Introductionmentioning

confidence: 99%

Extreme Learning Machine combined with a Differential Evolution algorithm for lithology identification

Saporetti

Duarte

Fonseca

et al. 2018

RITA

View full text Add to dashboard Cite

Lithology identification, obtained through the analysis of several geophysical properties, has an important role in the process of characterization of oil reservoirs. The identification can be accomplished by direct and indirect methods, but these methods are not always feasible because of the cost or imprecision of the results generated. Consequently, there is a need to automate the procedure of reservoir characterization and, in this context, computational intelligence techniques appear as an alternative to lithology identification. However, to acquire proper performance, usually some parameters should be adjusted and this can become a hard task depending on the complexity of the underlying problem. This paper aims to apply an Extreme Learning Machine (ELM) adjusted with a Differential Evolution (DE) to classify data from the South Provence Basin, using a previously published paper as a baseline reference. The paper contributions include the use of an evolutionary algorithm as a tool for search on the hyperparameters of the ELM. In addition, an activation function recently proposed in the literature is implemented and tested. The computational approach developed here has the potential to assist in petrographic data classification and helps to improve the process of reservoir characterization and the production development planning.

show abstract

A Review on Intelligent Recognition with Logging Data: Tasks, Current Status and Challenges

Zhu,

Zhang,

Ren

et al. 2024

Surv Geophys

View full text Add to dashboard Cite

Lithology and mineralogy recognition from geochemical logging tool data using multivariate statistical analysis

Cited by 12 publications

References 24 publications

Core‐Log‐Seismic Integration in Metamorphic Rocks and Its Implication for the Regional Geology: A Case Study for the ICDP Drilling Project COSC‐1, Sweden

Core‐Log‐Seismic Integration in Metamorphic Rocks and Its Implication for the Regional Geology: A Case Study for the ICDP Drilling Project COSC‐1, Sweden

Extreme Learning Machine combined with a Differential Evolution algorithm for lithology identification

A Review on Intelligent Recognition with Logging Data: Tasks, Current Status and Challenges

Contact Info

Product

Resources

About