Anovel data assimilation methodology for predicting lithology based on sequence labeling algorithms

Jina Jeong, Eungyu Park, Weon Shik Han, Kue Young Kim

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A hidden Markov model (HMM) and a conditional random fields (CRFs) model for lithological predictions based on multiple geophysical well-logging data are derived for dealing with directional nonstationarity through bidirectional training and conditioning. The developed models were benchmarked against their conventional counterparts, and hypothetical boreholes with the corresponding synthetic geophysical data including artificial errors were employed. In the three test scenarios devised, the average fitness and unfitness values of the developed CRFs model and HMM are 0.84 and 0.071 and 0.81 and 0.084, respectively, while those of the conventional CRFs model and HMM are 0.78 and 0.091 and 0.77 and 0.099, respectively. Comparisons of their predictabilities show that the models designed for directional nonstationarity clearly perform better than the conventional models for all tested examples. Among them, the developed linear-chain CRFs model showed the best or close to the best performance with high predictability and a low training data requirement.

Original languageEnglish
Pages (from-to)7503-7520
Number of pages18
JournalJournal of Geophysical Research: Solid Earth
Volume119
Issue number10
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Lithology
lithology
assimilation
data assimilation
Labeling
marking
methodology
Hidden Markov models
Well logging
education
labelling
Boreholes
fitness
well logging
conditioning
boreholes
borehole
requirements

All Science Journal Classification (ASJC) codes

  • Geophysics
  • Geochemistry and Petrology
  • Earth and Planetary Sciences (miscellaneous)
  • Space and Planetary Science

Cite this

@article{52729d95a6f74ee29d5bae6c1a28a874,
title = "Anovel data assimilation methodology for predicting lithology based on sequence labeling algorithms",
abstract = "A hidden Markov model (HMM) and a conditional random fields (CRFs) model for lithological predictions based on multiple geophysical well-logging data are derived for dealing with directional nonstationarity through bidirectional training and conditioning. The developed models were benchmarked against their conventional counterparts, and hypothetical boreholes with the corresponding synthetic geophysical data including artificial errors were employed. In the three test scenarios devised, the average fitness and unfitness values of the developed CRFs model and HMM are 0.84 and 0.071 and 0.81 and 0.084, respectively, while those of the conventional CRFs model and HMM are 0.78 and 0.091 and 0.77 and 0.099, respectively. Comparisons of their predictabilities show that the models designed for directional nonstationarity clearly perform better than the conventional models for all tested examples. Among them, the developed linear-chain CRFs model showed the best or close to the best performance with high predictability and a low training data requirement.",
author = "Jina Jeong and Eungyu Park and Han, {Weon Shik} and Kim, {Kue Young}",
year = "2014",
month = "1",
day = "1",
doi = "10.1002/2014JB011279",
language = "English",
volume = "119",
pages = "7503--7520",
journal = "Journal of Geophysical Research",
issn = "0148-0227",
publisher = "American Geophysical Union",
number = "10",

}

Anovel data assimilation methodology for predicting lithology based on sequence labeling algorithms. / Jeong, Jina; Park, Eungyu; Han, Weon Shik; Kim, Kue Young.

In: Journal of Geophysical Research: Solid Earth, Vol. 119, No. 10, 01.01.2014, p. 7503-7520.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Anovel data assimilation methodology for predicting lithology based on sequence labeling algorithms

AU - Jeong, Jina

AU - Park, Eungyu

AU - Han, Weon Shik

AU - Kim, Kue Young

PY - 2014/1/1

Y1 - 2014/1/1

N2 - A hidden Markov model (HMM) and a conditional random fields (CRFs) model for lithological predictions based on multiple geophysical well-logging data are derived for dealing with directional nonstationarity through bidirectional training and conditioning. The developed models were benchmarked against their conventional counterparts, and hypothetical boreholes with the corresponding synthetic geophysical data including artificial errors were employed. In the three test scenarios devised, the average fitness and unfitness values of the developed CRFs model and HMM are 0.84 and 0.071 and 0.81 and 0.084, respectively, while those of the conventional CRFs model and HMM are 0.78 and 0.091 and 0.77 and 0.099, respectively. Comparisons of their predictabilities show that the models designed for directional nonstationarity clearly perform better than the conventional models for all tested examples. Among them, the developed linear-chain CRFs model showed the best or close to the best performance with high predictability and a low training data requirement.

AB - A hidden Markov model (HMM) and a conditional random fields (CRFs) model for lithological predictions based on multiple geophysical well-logging data are derived for dealing with directional nonstationarity through bidirectional training and conditioning. The developed models were benchmarked against their conventional counterparts, and hypothetical boreholes with the corresponding synthetic geophysical data including artificial errors were employed. In the three test scenarios devised, the average fitness and unfitness values of the developed CRFs model and HMM are 0.84 and 0.071 and 0.81 and 0.084, respectively, while those of the conventional CRFs model and HMM are 0.78 and 0.091 and 0.77 and 0.099, respectively. Comparisons of their predictabilities show that the models designed for directional nonstationarity clearly perform better than the conventional models for all tested examples. Among them, the developed linear-chain CRFs model showed the best or close to the best performance with high predictability and a low training data requirement.

UR - http://www.scopus.com/inward/record.url?scp=84915751112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84915751112&partnerID=8YFLogxK

U2 - 10.1002/2014JB011279

DO - 10.1002/2014JB011279

M3 - Article

AN - SCOPUS:84915751112

VL - 119

SP - 7503

EP - 7520

JO - Journal of Geophysical Research

JF - Journal of Geophysical Research

SN - 0148-0227

IS - 10

ER -