Borehole-to-surface electrical data interpretation at Takigami geothermal field in Kyushu, Japan using neural network

Ho Trong Long, Hideki Mizunaga, Keisuke Ushijima

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper deals with the application of neural network technique for the three-dimension interpretation of mise-à-la-masse data from the Takigami geothermal field in Kyushu, which is one of the most active geothermal area in Japan. To understand the structure of the geothermal field, a 4-layers neural network had been developed. The training algorithm for the network is back-propagation with five paradigms, e.g. on-line back-propagation, batch back-propagation, delta-bar-delta, resilient propagation (RPROP) and quick propagation, were applied to find out the most efficient one. The network was trained with 3-D mise-à-la-masse simulation data set, including 864 cases of a single anomalous resistivity block of 10 Ohm.m moving in the model mesh with background resistivity of 100 Ohm.m. To generate the training data set, a high accuracy algorithm for 3-D numerical simulation, based on finite difference method and the algorithm of the singularity removal, was used. The trained network was tested by a synthetic data and then applied for the real field data set of the study area. The obtained results are remarkably correlated with the other available data from the field such as previous geoelectrical data, formation temperatures, lost circulation zones, hence, promising zones for production or re-injection can be indicated quickly at site of Takigami geothermal field.

Original languageEnglish
Pages (from-to)1318-1322
Number of pages5
JournalSEG Technical Program Expanded Abstracts
Volume25
Issue number1
DOIs
Publication statusPublished - Jan 2006

Fingerprint

Geothermal fields
data interpretation
boreholes
Boreholes
Backpropagation
back propagation
Japan
borehole
Neural networks
electrical resistivity
Finite difference method
education
finite difference method
propagation
simulation
data simulation
Computer simulation
mesh
injection
Temperature

All Science Journal Classification (ASJC) codes

  • Geophysics
  • Geotechnical Engineering and Engineering Geology

Cite this

Borehole-to-surface electrical data interpretation at Takigami geothermal field in Kyushu, Japan using neural network. / Long, Ho Trong; Mizunaga, Hideki; Ushijima, Keisuke.

In: SEG Technical Program Expanded Abstracts, Vol. 25, No. 1, 01.2006, p. 1318-1322.

Research output: Contribution to journalArticle

@article{fd2901e919714637bf5bf1b796b7ca9a,
title = "Borehole-to-surface electrical data interpretation at Takigami geothermal field in Kyushu, Japan using neural network",
abstract = "This paper deals with the application of neural network technique for the three-dimension interpretation of mise-{\`a}-la-masse data from the Takigami geothermal field in Kyushu, which is one of the most active geothermal area in Japan. To understand the structure of the geothermal field, a 4-layers neural network had been developed. The training algorithm for the network is back-propagation with five paradigms, e.g. on-line back-propagation, batch back-propagation, delta-bar-delta, resilient propagation (RPROP) and quick propagation, were applied to find out the most efficient one. The network was trained with 3-D mise-{\`a}-la-masse simulation data set, including 864 cases of a single anomalous resistivity block of 10 Ohm.m moving in the model mesh with background resistivity of 100 Ohm.m. To generate the training data set, a high accuracy algorithm for 3-D numerical simulation, based on finite difference method and the algorithm of the singularity removal, was used. The trained network was tested by a synthetic data and then applied for the real field data set of the study area. The obtained results are remarkably correlated with the other available data from the field such as previous geoelectrical data, formation temperatures, lost circulation zones, hence, promising zones for production or re-injection can be indicated quickly at site of Takigami geothermal field.",
author = "Long, {Ho Trong} and Hideki Mizunaga and Keisuke Ushijima",
year = "2006",
month = "1",
doi = "10.1190/1.2369763",
language = "English",
volume = "25",
pages = "1318--1322",
journal = "SEG Technical Program Expanded Abstracts",
issn = "1052-3812",
publisher = "Society of Exploration Geophysicists",
number = "1",

}

TY - JOUR

T1 - Borehole-to-surface electrical data interpretation at Takigami geothermal field in Kyushu, Japan using neural network

AU - Long, Ho Trong

AU - Mizunaga, Hideki

AU - Ushijima, Keisuke

PY - 2006/1

Y1 - 2006/1

N2 - This paper deals with the application of neural network technique for the three-dimension interpretation of mise-à-la-masse data from the Takigami geothermal field in Kyushu, which is one of the most active geothermal area in Japan. To understand the structure of the geothermal field, a 4-layers neural network had been developed. The training algorithm for the network is back-propagation with five paradigms, e.g. on-line back-propagation, batch back-propagation, delta-bar-delta, resilient propagation (RPROP) and quick propagation, were applied to find out the most efficient one. The network was trained with 3-D mise-à-la-masse simulation data set, including 864 cases of a single anomalous resistivity block of 10 Ohm.m moving in the model mesh with background resistivity of 100 Ohm.m. To generate the training data set, a high accuracy algorithm for 3-D numerical simulation, based on finite difference method and the algorithm of the singularity removal, was used. The trained network was tested by a synthetic data and then applied for the real field data set of the study area. The obtained results are remarkably correlated with the other available data from the field such as previous geoelectrical data, formation temperatures, lost circulation zones, hence, promising zones for production or re-injection can be indicated quickly at site of Takigami geothermal field.

AB - This paper deals with the application of neural network technique for the three-dimension interpretation of mise-à-la-masse data from the Takigami geothermal field in Kyushu, which is one of the most active geothermal area in Japan. To understand the structure of the geothermal field, a 4-layers neural network had been developed. The training algorithm for the network is back-propagation with five paradigms, e.g. on-line back-propagation, batch back-propagation, delta-bar-delta, resilient propagation (RPROP) and quick propagation, were applied to find out the most efficient one. The network was trained with 3-D mise-à-la-masse simulation data set, including 864 cases of a single anomalous resistivity block of 10 Ohm.m moving in the model mesh with background resistivity of 100 Ohm.m. To generate the training data set, a high accuracy algorithm for 3-D numerical simulation, based on finite difference method and the algorithm of the singularity removal, was used. The trained network was tested by a synthetic data and then applied for the real field data set of the study area. The obtained results are remarkably correlated with the other available data from the field such as previous geoelectrical data, formation temperatures, lost circulation zones, hence, promising zones for production or re-injection can be indicated quickly at site of Takigami geothermal field.

UR - http://www.scopus.com/inward/record.url?scp=33845416008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845416008&partnerID=8YFLogxK

U2 - 10.1190/1.2369763

DO - 10.1190/1.2369763

M3 - Article

VL - 25

SP - 1318

EP - 1322

JO - SEG Technical Program Expanded Abstracts

JF - SEG Technical Program Expanded Abstracts

SN - 1052-3812

IS - 1

ER -