1887

Abstract

We predicted the porosity volumes using multivariate and neural-network analyses for the the upper Cretaceous Carapebus sands and Albian Quissama carbonates in Campos Basin BM-C-37/38 exploration blocks, offshore Brazil. There are three wells on the blocks for the purpose of statistical analysis and neural network training. The predicted Albian porosity matches well with the well information and the results were used to improve the understanding of reservoir presence and connectivity and for horizontal well planning. On the other hand, we deemed the predicted Carapebus porosity unreliable due to a low validation value and geological reasoning. We concluded that neural-network predictions can be useful in BM-C-37/38 blocks with only three wells; but proper quality control and integration with geological interpretation are essential.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.20148587
2012-06-04
2024-03-29
Loading full text...

Full text loading...

http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.20148587
Loading
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error