Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska
Neural networks (NNs) are widely used to investigate the relationship among variables in complex multivariate problems. In cases of limited data, the network behavior strongly depends on factors such as the choice of network activation function and network initial weights. In this study, I investiga...
Main Author: | |
---|---|
Other Authors: | , , , , |
Format: | Book |
Language: | English |
Published: |
Texas A&M University
2005
|
Subjects: | |
Online Access: | https://hdl.handle.net/1969.1/2593 |
id |
fttexasamuniv:oai:oaktrust.library.tamu.edu:1969.1/2593 |
---|---|
record_format |
openpolar |
spelling |
fttexasamuniv:oai:oaktrust.library.tamu.edu:1969.1/2593 2023-07-16T03:57:50+02:00 Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska Bui, Thang Dinh Jensen, Jerry L. Hanks, Catherine L. Schechter, David S. Chester, Judith S. Ayers, Walter B. 2005-11-01 2598415 bytes electronic application/pdf born digital https://hdl.handle.net/1969.1/2593 en_US eng Texas A&M University https://hdl.handle.net/1969.1/2593 Neural network naturally fractured reservoir discrete fracture network Book Thesis Electronic Dissertation text 2005 fttexasamuniv 2023-06-27T22:08:56Z Neural networks (NNs) are widely used to investigate the relationship among variables in complex multivariate problems. In cases of limited data, the network behavior strongly depends on factors such as the choice of network activation function and network initial weights. In this study, I investigated the use of neural networks for multivariate analysis in the case of limited data. The analysis shows that special attention should be paid when building and using NNs in cases of limited data. The linear activation function at the output nodes outperforms the sigmoidal and Gaussian functions. I found that combining network predictions gives less biased predictions and allows for the assessment of the prediction variability. The NN results, along with conventional statistical analysis, were used to examine the effects of folding, bed thickness, structural position, and lithology on the fracture properties distributions in the Lisburne Formation, folded and exposed in the northeastern Brooks Range of Alaska. Fracture data from five folds, representing different degrees of folding, were analyzed. In addition, I modeled the fracture system using the discrete fracture network approach and investigated the effects of fracture properties on the flow conductance of the system. For the Lisburne data, two major fracture sets striking north/south and east/west were studied. Results of the NNs analysis suggest that fracture spacing in both sets is similar and weakly affected by folding and that stratigraphic position and lithology have a strong effect on fracture spacing. Folding, however, has a significant effect on fracture length. In open folds, fracture lengths in both sets have similar averages and variances. As the folds tighten, both the east/west and north/south fracture lengths increase by a factor of 2 or 3 and become more variable. In tight folds, fracture length in the north/south direction is significantly larger than in the east/west direction. The difference in length between the two fracture sets creates a ... Book Brooks Range Alaska Texas A&M University Digital Repository |
institution |
Open Polar |
collection |
Texas A&M University Digital Repository |
op_collection_id |
fttexasamuniv |
language |
English |
topic |
Neural network naturally fractured reservoir discrete fracture network |
spellingShingle |
Neural network naturally fractured reservoir discrete fracture network Bui, Thang Dinh Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
topic_facet |
Neural network naturally fractured reservoir discrete fracture network |
description |
Neural networks (NNs) are widely used to investigate the relationship among variables in complex multivariate problems. In cases of limited data, the network behavior strongly depends on factors such as the choice of network activation function and network initial weights. In this study, I investigated the use of neural networks for multivariate analysis in the case of limited data. The analysis shows that special attention should be paid when building and using NNs in cases of limited data. The linear activation function at the output nodes outperforms the sigmoidal and Gaussian functions. I found that combining network predictions gives less biased predictions and allows for the assessment of the prediction variability. The NN results, along with conventional statistical analysis, were used to examine the effects of folding, bed thickness, structural position, and lithology on the fracture properties distributions in the Lisburne Formation, folded and exposed in the northeastern Brooks Range of Alaska. Fracture data from five folds, representing different degrees of folding, were analyzed. In addition, I modeled the fracture system using the discrete fracture network approach and investigated the effects of fracture properties on the flow conductance of the system. For the Lisburne data, two major fracture sets striking north/south and east/west were studied. Results of the NNs analysis suggest that fracture spacing in both sets is similar and weakly affected by folding and that stratigraphic position and lithology have a strong effect on fracture spacing. Folding, however, has a significant effect on fracture length. In open folds, fracture lengths in both sets have similar averages and variances. As the folds tighten, both the east/west and north/south fracture lengths increase by a factor of 2 or 3 and become more variable. In tight folds, fracture length in the north/south direction is significantly larger than in the east/west direction. The difference in length between the two fracture sets creates a ... |
author2 |
Jensen, Jerry L. Hanks, Catherine L. Schechter, David S. Chester, Judith S. Ayers, Walter B. |
format |
Book |
author |
Bui, Thang Dinh |
author_facet |
Bui, Thang Dinh |
author_sort |
Bui, Thang Dinh |
title |
Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
title_short |
Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
title_full |
Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
title_fullStr |
Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
title_full_unstemmed |
Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska |
title_sort |
neural network analysis of sparse datasets ?? an application to the fracture system in folds of the lisburne formation, northeastern alaska |
publisher |
Texas A&M University |
publishDate |
2005 |
url |
https://hdl.handle.net/1969.1/2593 |
genre |
Brooks Range Alaska |
genre_facet |
Brooks Range Alaska |
op_relation |
https://hdl.handle.net/1969.1/2593 |
_version_ |
1771544652346818560 |