Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning. / Lorentzen, Mads; Bredesen, Kenneth; Mosegaard, Klaus; Nielsen, Lars.

In: Geophysical Prospecting, Vol. 70, No. 8, 2022, p. 1410-1431.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Lorentzen, M, Bredesen, K, Mosegaard, K & Nielsen, L 2022, 'Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning', Geophysical Prospecting, vol. 70, no. 8, pp. 1410-1431. https://doi.org/10.1111/1365-2478.13252

APA

Lorentzen, M., Bredesen, K., Mosegaard, K., & Nielsen, L. (2022). Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning. Geophysical Prospecting, 70(8), 1410-1431. https://doi.org/10.1111/1365-2478.13252

Vancouver

Lorentzen M, Bredesen K, Mosegaard K, Nielsen L. Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning. Geophysical Prospecting. 2022;70(8):1410-1431. https://doi.org/10.1111/1365-2478.13252

Author

Lorentzen, Mads ; Bredesen, Kenneth ; Mosegaard, Klaus ; Nielsen, Lars. / Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning. In: Geophysical Prospecting. 2022 ; Vol. 70, No. 8. pp. 1410-1431.

Bibtex

@article{40ec43cb858c4a4cb071676d477c5023,
title = "Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning",
abstract = "Shear wave velocity information is valuable in many aspects of seismic exploration and characterization of reservoirs. However, shear wave logs are not always available in the interval of interest due to cost and time-saving purposes. In this study, we present a tailored supervised learning approach to estimate shear wave velocity from well-log measurements in the Lower Cretaceous succession of the Valdemar and Boje fields in the Danish North Sea. Our objective is to investigate the performance of four supervised learning regression models (linear, random forest, support vector and multi-layer perceptron). A limited well-log data set from six wells is used for training and testing the supervised learning models. A set of well data containing normalized gamma ray, compressional wave velocity, neutron porosity and medium resistivity logs gave reasonable shear wave velocity estimates in the test wells with root-mean-square error scores within the range of other published studies. Based on limited input data and complex geology, the multi-layer perceptron was the most successful model in predicting the reservoir sections of the test wells. However, all models lacked stability in the overburden zones. Lastly, re-training the multi-layer perceptron on the six wells to predict missing shear wave velocity in a nearby well showed promising results for further reservoir characterization. The obtained results can yield useful input into, for example, seismic pre-stack inversion, amplitude versus offset analysis and rock physics analysis.",
keywords = "borehole geophysics, data processing, interpretation, modelling, rock physics, WAVE VELOCITY, CHALK, PREDICTION, FIELD, DIAGENESIS, RESERVOIR, EXAMPLE",
author = "Mads Lorentzen and Kenneth Bredesen and Klaus Mosegaard and Lars Nielsen",
year = "2022",
doi = "10.1111/1365-2478.13252",
language = "English",
volume = "70",
pages = "1410--1431",
journal = "Geophysical Prospecting",
issn = "0016-8025",
publisher = "Wiley-Blackwell",
number = "8",

}

RIS

TY - JOUR

T1 - Estimation of shear sonic logs in the heterogeneous and fractured Lower Cretaceous of the Danish North Sea using supervised learning

AU - Lorentzen, Mads

AU - Bredesen, Kenneth

AU - Mosegaard, Klaus

AU - Nielsen, Lars

PY - 2022

Y1 - 2022

N2 - Shear wave velocity information is valuable in many aspects of seismic exploration and characterization of reservoirs. However, shear wave logs are not always available in the interval of interest due to cost and time-saving purposes. In this study, we present a tailored supervised learning approach to estimate shear wave velocity from well-log measurements in the Lower Cretaceous succession of the Valdemar and Boje fields in the Danish North Sea. Our objective is to investigate the performance of four supervised learning regression models (linear, random forest, support vector and multi-layer perceptron). A limited well-log data set from six wells is used for training and testing the supervised learning models. A set of well data containing normalized gamma ray, compressional wave velocity, neutron porosity and medium resistivity logs gave reasonable shear wave velocity estimates in the test wells with root-mean-square error scores within the range of other published studies. Based on limited input data and complex geology, the multi-layer perceptron was the most successful model in predicting the reservoir sections of the test wells. However, all models lacked stability in the overburden zones. Lastly, re-training the multi-layer perceptron on the six wells to predict missing shear wave velocity in a nearby well showed promising results for further reservoir characterization. The obtained results can yield useful input into, for example, seismic pre-stack inversion, amplitude versus offset analysis and rock physics analysis.

AB - Shear wave velocity information is valuable in many aspects of seismic exploration and characterization of reservoirs. However, shear wave logs are not always available in the interval of interest due to cost and time-saving purposes. In this study, we present a tailored supervised learning approach to estimate shear wave velocity from well-log measurements in the Lower Cretaceous succession of the Valdemar and Boje fields in the Danish North Sea. Our objective is to investigate the performance of four supervised learning regression models (linear, random forest, support vector and multi-layer perceptron). A limited well-log data set from six wells is used for training and testing the supervised learning models. A set of well data containing normalized gamma ray, compressional wave velocity, neutron porosity and medium resistivity logs gave reasonable shear wave velocity estimates in the test wells with root-mean-square error scores within the range of other published studies. Based on limited input data and complex geology, the multi-layer perceptron was the most successful model in predicting the reservoir sections of the test wells. However, all models lacked stability in the overburden zones. Lastly, re-training the multi-layer perceptron on the six wells to predict missing shear wave velocity in a nearby well showed promising results for further reservoir characterization. The obtained results can yield useful input into, for example, seismic pre-stack inversion, amplitude versus offset analysis and rock physics analysis.

KW - borehole geophysics

KW - data processing

KW - interpretation

KW - modelling

KW - rock physics

KW - WAVE VELOCITY

KW - CHALK

KW - PREDICTION

KW - FIELD

KW - DIAGENESIS

KW - RESERVOIR

KW - EXAMPLE

U2 - 10.1111/1365-2478.13252

DO - 10.1111/1365-2478.13252

M3 - Journal article

VL - 70

SP - 1410

EP - 1431

JO - Geophysical Prospecting

JF - Geophysical Prospecting

SN - 0016-8025

IS - 8

ER -

ID: 318696566