Data Science for Petroleum Engineering: How does someone become good at Deep Learning?

Alfonso R. Reyes
(23 September 2017)


I watched few days ago the interview from professor Andrew Ng to one of the luminaries of deep learning and artificial intelligence, Dr. Youshua Bengio. He has written books and dozens of papers on deep learning and neural networks. I liked the style. Pretty down to earth stuff. Just the way professor Andrew likes to do: bringing machine learning, deep learning to the masses.

So the question remains: do petroleum engineers need to learn data science, computer science, statistics, machine learning, neural networks, virtualization and GPU based engineering? I think it will be like the times where engineers had to learn about computers, spreadsheets, word processors, windows, serial ports, and the words software and hardware became part of our daily vocabulary.

New fascinating discoveries in science and engineering will be knocking at our door thanks to the application of super-efficient computer algorithms and more speed squeezed out of our computers from the graphics cards. The new revolution will not be brought by robots or super-AI terminators or “skynets” but by these deep learning techniques that find patterns in the data with more than 99% accuracy.

The massive amounts of data are just waiting for the right algorithm to start showing their secrets, making processes more economical, more accurate, repeatable, requiring less supervision and reducing risks.

Data science and deep learning are not as hard as they look. As Dr. Bengio says “you don’t really need a 5-year PhD”. We, petroleum engineers, just need a little bit of sharpening the saw of our computer science, math, probability, matrix algebra, optimization and calculus.

It will be like learning another kind of slide rule.