Reservoir Lithology Classification by the Hidden Markov Model

Runhai Feng; Stefan Luthi; Dries Gisolf

doi:10.3997/2214-4609.201700221

Reservoir Lithology Classification by the Hidden Markov Model

Runhai Feng, Stefan Luthi, Dries Gisolf

Applied Geology

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific

2 Citations (Scopus)

Abstract

Hidden Markov Model has been applied to predict the reservoir lithologies by using seismic inversion results as inputs. This method can take the conditional probability between different states or lithologies into account which is the vertical correlation in geology. In order to consider the misfit between the inversion results and the true well-logging data, the model needs to be trained. The application on a field example is quite successful in which most of lithologies have been predicted correctly even for some thin layers. However, this method is only 1D which means that the lateral continuity has not been considered yet.

Original language	English
Title of host publication	4th EAGE Exploration Workshop 2017
Subtitle of host publication	2-4 May 2017, Muscat, Oman
Number of pages	5
DOIs	https://doi.org/10.3997/2214-4609.201700221
Publication status	Published - 2017
Event	4th EAGE Exploration Workshop 2017 - Muscat, Oman Duration: 2 May 2017 → 4 May 2017 Conference number: 4 https://events.eage.org/en/2017/fourth-eage-exploration-workshop

Workshop

Workshop	4th EAGE Exploration Workshop 2017
Country/Territory	Oman
City	Muscat
Period	2/05/17 → 4/05/17
Internet address	https://events.eage.org/en/2017/fourth-eage-exploration-workshop

Access to Document

10.3997/2214-4609.201700221

Cite this

@inproceedings{07006656598345268ddb44b9b329bf81,

title = "Reservoir Lithology Classification by the Hidden Markov Model",

abstract = "Hidden Markov Model has been applied to predict the reservoir lithologies by using seismic inversion results as inputs. This method can take the conditional probability between different states or lithologies into account which is the vertical correlation in geology. In order to consider the misfit between the inversion results and the true well-logging data, the model needs to be trained. The application on a field example is quite successful in which most of lithologies have been predicted correctly even for some thin layers. However, this method is only 1D which means that the lateral continuity has not been considered yet. ",

author = "Runhai Feng and Stefan Luthi and Dries Gisolf",

year = "2017",

doi = "10.3997/2214-4609.201700221",

language = "English",

booktitle = "4th EAGE Exploration Workshop 2017",

note = "4th EAGE Exploration Workshop 2017 ; Conference date: 02-05-2017 Through 04-05-2017",

url = "https://events.eage.org/en/2017/fourth-eage-exploration-workshop",

}

TY - GEN

T1 - Reservoir Lithology Classification by the Hidden Markov Model

AU - Feng, Runhai

AU - Luthi, Stefan

AU - Gisolf, Dries

N1 - Conference code: 4

PY - 2017

Y1 - 2017

N2 - Hidden Markov Model has been applied to predict the reservoir lithologies by using seismic inversion results as inputs. This method can take the conditional probability between different states or lithologies into account which is the vertical correlation in geology. In order to consider the misfit between the inversion results and the true well-logging data, the model needs to be trained. The application on a field example is quite successful in which most of lithologies have been predicted correctly even for some thin layers. However, this method is only 1D which means that the lateral continuity has not been considered yet.

AB - Hidden Markov Model has been applied to predict the reservoir lithologies by using seismic inversion results as inputs. This method can take the conditional probability between different states or lithologies into account which is the vertical correlation in geology. In order to consider the misfit between the inversion results and the true well-logging data, the model needs to be trained. The application on a field example is quite successful in which most of lithologies have been predicted correctly even for some thin layers. However, this method is only 1D which means that the lateral continuity has not been considered yet.

U2 - 10.3997/2214-4609.201700221

DO - 10.3997/2214-4609.201700221

M3 - Conference contribution

BT - 4th EAGE Exploration Workshop 2017

T2 - 4th EAGE Exploration Workshop 2017

Y2 - 2 May 2017 through 4 May 2017

ER -

Reservoir Lithology Classification by the Hidden Markov Model

Abstract

Workshop

Access to Document

Fingerprint

Cite this