Determining the main drivers in hydrocarbon production from shale using advanced data-driven analytics

Today, I read the paper ‘Determining the main drivers in hydrocarbon production from shale using advanced data-driven analytics-A case study in Marcellus shale’.

Summary

Results of this study show that completion practices that results in good production in low quality shale are not necessarily just as good for higher quality shale. When it comes to completion practices in shale, ‘one-size-fit-all’ is a poor prescription.

Pattern recognition technology is important for designing parameters in shale wells productivity and distinguishing the impact of parameters that control rock quality and completion practices.

One plot of Net Pay Thickness versus Gas saturation is shown as follows:

The figure of 2 and 3 categories are shown below:

The general completion design is more significant in wells completed in High Quality Shale (HQS) than it is in wells completed in Low Quality Shale (LQS). HQS is a more prolific reservoir than LQS.

In both low and high quality shale, it is better to have more number of stages.

(MCF: million cubic feet)

The granularity is increased from 3 to 6 categories.

Regardless of the rock quality, it is better to start the fracturing jobs with a higher amount of pad volume.

Formations with higher values of Net Pay Thickness, Porosity, Hydrocarbon Saturation, TOC (Total Organic Carbon) should have more hydrocarbon reserves than formations with lower values of Net Pay Thickness, Porosity, Hydrocarbon Saturation, TOC (Total Organic Carbon).

Supervised Fuzzy Cluster Analysis (SFCA)

Fuzzy Cluster Analysis is a better tool when we try to discover order in the seemingly chaotic behavior observed in the complex, multi-dimensional data sets, of which, data from shale is a good representative.

In this study acceptable trends and patterns are those that hold at least one level increase in granularity.

The paper postulates the acceptable minimum number of wells (population) in a cluster or category to be 8 wells.

Completion analysis of LQS is shown below:

Completion analysis of LHQS is shown below:

In the LQS, completion does not do much more than allowing the rock to behave in a matter that is expected of it. However, for the HQS completion and well construction practices must influence the production such that they overshadow the influence of reservoir characteristics.

The objective of this paper is to introduce a novel, advanced data driven analytics technology that makes sense of complexities of production from shale wells.

Advanced Data-Driven Analytics is capable of using facts (field measurements) to help optimize production form shale.

Tomorrow, I will read more papers on ANN.