Blog

A data science blog for Petroleum Engineering.

Topics covered

Subject ▸ data science

Transforming Petroleum Engineers in Data Science Wizards. Update 2019

29 July 2019

Note. This is an update of the original article I published in 2017. Many, many things have changed, or have progressed, so fast that the article needs some rewriting. Very often I receive questions from colleagues asking for tips on Data Science and Machine Learning applied to Petroleum Engineering. These answers address some of those questions I have collected over time. In this case, you may call this, some advice to becoming a Petroleum Engineer and Data Science wizard:

R and Python commingled: preparing your machine for RPyStats. Season 1, Episode 3

15 July 2019

data science

Adding R and Python superpowers to your data science toolbox involves installing a handful of applications in your machine. This model applies to Windows, Linux and Unix Mac. I have tested RPyStats in all these operating systems and it runs great. The applications to install are: R 3.6+ Rtools 3.5+ RStudio 1.2+ Anaconda 3 Python 3.6+ Git for Windows (which also provide a Unix terminal Git Bash) Completely optional is installing a Git client such a GitKraken.

R and Python commingled: a Hello World of RPyStats. Season 1, Episode 2

14 July 2019

data science

In the previous episode I described what we can achieve with RPyStats. In this episode, we will run an example -ready to run-, that I have prepared for you to experiment working at deployment level, meaning at one level above R and RStudio, including calls to Python libraries. A master project One thing that is different from the way we have been doing R or Python projects is that we add an extra layer of control above any other type of project, an R project, a Python project, an R package or a Python package.

R and Python commingled: how to get the best of both worlds. Season 1, Episode 1

12 July 2019

R, python, data science

I confess. I have been in a long term relationship with … Python. Sometimes feels like 10+ years- other times like 15+ years, if I count my sporadic adventures with the language. Few years ago, I finally dared to explore other universes, and took the #rstats R route. I don’t regret it at all. It has been years of full productivity, challenges in learning the language, discovering its strong publishing tools (blogdown, bookdown, pkgdown, and the king of all: Rmarkdown), its science-oriented ecosystem, and, of course, making discoveries from data.

Podcast - Petroleum Engineering Data Science

7 May 2019

data science

The Energy Innovators podcast just released this evening, May 6, 2019, an interview I gave to Francis Norman, with NERA, during my recent trip to Perth, Australia. Link: https://energyinnovatorspodcast.com/alfonso-reyes-petroleum-data-science/ I hope you enjoy it. Where I talk about: How I started my career My first contact with data and digital stuff How digital helped model our field fracs Data was not really a love at first sight; digital controllers were What was my Eureka moment in Data Science How looking at datasets of many wells instead of one-well-at-a-time (standalone well) turns to increase oil in all the fields that data science touched How computer science and data science intersect Why analyzing datasets of wells brings you discoveries More Eureka moments with statistical analysis Why now is the moment of experimenting with new approaches in petroleum engineering This is not stopping: as more fields are converted to digital oilfields more data will be flowing Of course you cannot detect outliers with one well = one row No matter how good is your well modeling software is, it becomes irrelevant when you input bad well data Going from standalone wells to networks of wells Applying statistical tools to create multiple scenarios in network models Automating the selection the best oil production scenarios at the lower cost The joy of sending network model programs to production operators How I learned data science with real data, a real challenge: increasing oil rates through production optimization How to listen your wells through data.

On Data Science

17 March 2019

data science

At request of colleagues, what I have to say on this is: I believe that data science doesn’t have the word “science” to make it look sexy. It really means it. Data Science as a discipline is not new. It has been living among us for 50 years. It was invented by scientists with deeply ingrained love for statistics. Statisticians have been the inventors and guardians of data science. They still are.

The whole point of data science

10 March 2019

data science

Article Predict Core Properties with Machine Learning by Amrita Sen. _“The OAG platform allows subject matter experts to then quickly build and assess machine learning models without having to learn Python or R.” _ <- ARR. But that is the whole point of the data science revolution: getting rid of black boxes and bring more open science to increase the discoveries and untap hidden oil. Petroleum engineers should strive to make reproducible examples.

Not travelling but half way through the multiwell stats tutorial

23 January 2019

data science, production technology

No, I am not travelling or anything like that. I am actually half done writing the tutorial for the multiwell-stats application in Python. I will be writing it using the magnificent tools of data science, so we have a fully reproducible document. My pick for writing tutorials, booklets and books is #bookdown. It is an #rstats package that lets you combine math, code and text in the same document. Remember, data science is about reproducibility, as in reproducible research.

How do you sell a data science project to your boss

8 January 2019

data science, business case

This post was inspired on my response a few months ago in the SPE forums. The question was -if I remember correctly-, on how you sell predictive analytics to a conservative manager. I have made some changes to my original answer to make it more current, and independent off the original post. So, the question is: How do sell a petroleum engineering data science project to your skeptic manager?

Why I decided to publish data science in a blog

7 January 2019

data science

Introduction As I announced last week, my blog is now online at http://blog.oilgainsanalytics.com. LinkedIn may obfuscate the link so I am also providing it as an image below. Clicking on the image will bring you to the blog: blog.oilgainsanalytics.com or oilgainsanalytics.com/blog Motivation I believe in the sharing philosophy of data science as I learned it from my biostatistician instructors at Johns Hopkins University (Peng, Leek, Caffo, et al).

All Blog posts by date