Introduction to Machine Learning and its Applications to Petrophysics

Westside Houston


Seminar Date: May 26 2021

Registration Opens: May 01 2021 - May 26 2021

Time: 11:00 AM - 12:00 PM (US CDT)

Admission/Registration Link:

Donation Link: None

Meeting/Webinar Link:

Contact: QinShan “Shan” Yang (VP Westside, SPWLA Houston Chapter)


Fees: FREE


Machine learning is becoming a popular tool within the petrophysics domain. It can be used for a variety of tasks such as prediction of missing data, prediction of continuous curves from discretely sampled data such as core, division of the subsurface into different facies etc. As machine learning technologies become more commonplace and more reliance is placed on them, it is essential that the data used to train the models is fit for purpose, of good quality and appropriately selected. Within this talk, the focus will be on an introduction to machine learning, the machine learning workflow, differences between supervised and unsupervised learning, and the importance of ensuring the data is of good quality prior to adopting these algorithms will also be covered. Examples of petrophysical applications will also be discussed.


Andy McDonald is a Petrophysicist at Lloyd’s Register in Aberdeen, UK, and he has over 15 years of industry experience. His primary focus is providing domain expertise to software development projects and applications of machine learning/artificial intelligence to petrophysics. He is also a keen Python developer. Prior to working with Lloyd's Register, he worked as a geoscientist for Baker Hughes where he specialized in log quality control, petrophysics, and acoustic waveform processing and interpretation. Andy holds an MSc in Earth Science from the Open University, and a BSc (Hons) in Geology & Petroleum Geology from the University of Aberdeen. He has co-authored several technical papers for SPWLA and SPE conferences covering machine learning, heavy oil, and low salinity waterflooding.

After Payment/Registration, you will receive a confirmation email containing information about joining the seminar.

500 / 500