Well log analysis is one of the costliest parts of petroleum fields. It has been realized that developing synthetic well logs can help analyze the reservoir properties in areas where some necessary logs are absent or incomplete, and then reduce costs of companies. During generating synthetic logs, logging time should be used sufficiently for predicting trends and filling some incomplete logs to obtain consistent and high quality throughout the field. This paper presents a new methodology to generate synthetic well logs and detecting logging trends with time using BP neural network including hash function. In the model for multiple wells analysis, not only several loggings from the same well but the formation similarity among wells can be used effectively. It will provide the possibility to study logs for wells that do not have enough logs needed for the analysis. This hash-based method was confirmed effective through experiments on both real-world and synthetic well log data.
[1]
Shahab D. Mohaghegh,et al.
Developing Synthetic Well Logs for the Upper Devonian Units in Southern Pennsylvania
,
2005
.
[2]
Andrei Popa,et al.
Reducing the Cost of Field-Scale Log Analysis Using Virtual Intelligence Techniques
,
1999
.
[3]
Shahab D. Mohaghegh,et al.
Virtual Magnetic Imaging Logs: Generation of Synthetic MRI Logs from Conventional Well Logs
,
1998
.
[4]
Richard A. Startzman,et al.
Predicting Natural Gas Production Using Artificial Neural Network
,
2001
.
[5]
Anangela Garcia,et al.
Forecasting US Natural Gas Production into year 2020: a comparative study.
,
2004
.
[6]
Yi Wang,et al.
Application of Artificial Neural Networks to Predicate Shale Content
,
2005,
ISNN.
[7]
M. Bhuiyan,et al.
Reservoir Characterization Through Synthetic Logs
,
2000
.