Conference Paper

Application of Artificial Neural Networks to Predicate Shale Content.

DOI: 10.1007/11427469_166 Conference: Advances in Neural Networks - ISNN 2005, Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part III
Source: DBLP

ABSTRACT This paper describes an Artificial Neural Network approach to the predication problem of shale content in the reservoir. An interval of seismic data representing the zone of interest is extracted from a three-dimensional data volume. Seismic data and well log data are used as input and target to Regularity Back-propagation (RBP) neural network. A series of ANNs is trained and results are presented.

Download full-text

Full-text

Available from: Ove Rustung Hjelmervik, Oct 01, 2014
1 Follower
 · 
68 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Advanced Language Processing and Web Information Technology, 2008. ALPIT '08. International Conference on; 08/2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Pervasive Computing and Applications, 2008. ICPCA 2008. Third International Conference on; 11/2008