Subject ▸ Petroleum Engineering

Transforming Petroleum Engineers in Data Science Wizards

Once in a while I get messages from colleagues asking for tips on Data Science applied to Petroleum Engineering. This is stuff I have collected over time (responses), advice to follow to become a Petroleum Engineer and Data Science wizard: Complete any of the Python or R online courses on Data Science. My favorites are the ones from Johns Hopkins in Coursera, complementing with DataCamp short workshops. Just two that come quick to my mind.

Read More…

Data Science for Petroleum Engineering - Part 5.2: Finding and filling missing data

NOTE. You can find the PDF version of the R markdown notebook in GitHub at this link. The reproducible R markdown notebook (.Rmd) itself is here. Both are full versions of this LinkedIn article. For the time being, LinkedIn publishing does not support markdown which would make sharing scientific and engineering documents much easier. Mistyped data One of the challenges in cleaning up well data is having uniform and standard well names.

Read More…

Data Science for Petroleum Engineering - Part 5: "Transforming Excel well raw data into datasets.​"

One of the big challenges of this new era of data science. machine learning and artificial intelligence is getting unhooked from the habit of working with spreadsheets. They have been around for 30+ years and were awesome. But spreadsheets - or worksheets - do not scale well with massive amounts of data; or continuous streams of data; or other characteristics that are key for taking good and sound decisions such as reproducibility.

Read More…

Data Science for Petroleum Engineering - Part 5.1: Data Introspection with R

NOTE. You can find the PDF version of the R markdown notebook in GitHub at this link. The reproducible R markdown notebook (.Rmd) itself is here. Both are full versions of this LinkedIn article. For the time being, LinkedIn publishing does not support markdown which would make sharing scientific and engineering documents much easier. Transforming Excel well raw data into datasets This section is about getting familiar with our data.

Read More…

Growing your petroleum engineering library: calling FORTRAN from R

If you have already installed R and RStudio in your Windows PC or your Linux laptop or your Mac Book, then you need to think about including FORTRAN subroutines in your R toolbox. There are plenty of excellent math libraries built with old friend FORTRAN that greatly deserve to be part of our engineering library, either, to improve performance, or just avoid retyping (convert) of the whole routine in R.

Read More…

Building your own petroleum engineering library with "R": humble beginnings with the compressibility factor 'z'

Few weeks ago I was working on the marching algorithm to create vertical lift performance (VLP) curves and datasets for statistical analysis using the classical Hagedorn-Brown and Fancher-Brown correlations. Then I noticed some weird variations in the column for the compressibility factor or z. I started to investigate and found discontinuities in parts of the isotherms that are used for building the gas compressibility correlations. Digging a little bit more finally found that the problem was that the values of the fluid properties of my well had accidentally hit a critical point in the equations.

Read More…

"R" and the search of the ideal language for petroleum engineering

I have to confess my sin. I am coming from writing thousands of lines of Python code for a well modeling and optimization project. I did Exploratory Data Analysis (EDA) for the resulting well models and applied statistics using Python, pandas, matplotlib, SciPy and NumPy. I went full throttle and didn’t look behind. Got the results, the production engineering team increased the oil production we were looking for. All went fine, with the exception of being at fault for not exploring the other alternative: doing the work with “R”.

Read More…

OTC 2016: second day

For the first time since I started attending OTC in 2001, I could park in the first row of the parking lot. I wonder why! Couple of things grabbed my attention immediately during the session “Coping with low prices”: a more collaborative attitude between Deepwater companies to share R&D costs; “co-creation”, and despite of the low oil prices and financial straits, keeping safety first as a non-negotiable. I was happy to hear that maintaining the culture of safety is as important, or more, than fitting the financial targets.

Read More…

Data Science for Petroleum Production Engineering. Part 2: Acquiring the data

In the past session we got an introduction to the multiwell statistics package showing a few of the things that we can do with the Petronas PTech Engineering Library. Now, we will explore some more functionality. It is incredible the huge amount of information when we get from all the wells in one scan pass. The data starts to have sense. A well in isolation or standalone doesn’t tell used much about the field or differences between well parameters from well to well.

Read More…

Data Science for Petroleum Production Engineering

In the last century, the production engineer built the well models one by one and analyzed the results also one by one. With the ubiquity of the personal computer, desktops and laptops, an unimaginable computational power has been put in our hands. But we need the right tools! The spreadsheet was invented in the 80’s and was a great invention. The beauty of it is that you can produce results right away.

Read More…