Rock Type Classification Using Machine Learning

Recorded On: 11/14/2017

Rock mechanical properties are essential for drilling programs, well placement and well-completion design. Facies classification helps to improve estimates of rock mechanical properties by identifying a rock type from geophysical data. A facies classification open challenge, organized by the Society of Exploration GeoPhysicsts (SEG), investigated the application of artificial intelligence and pattern recognition techniques to identify complex patterns in the geophysical data which were impossible for humans to explore. The advent of artificial intelligence (AI) and technological advancements in computing and big data infrastructure, enables us to apply the process knowledge in less time and with minimal experience. Machine learning algorithms can extract patterns from data and make predictions based on these patterns. This webinar illustrates the workflow of machine learning algorithms followed in the SEG machine learning contest and how it is determining the rock type classification.

Sridharan Chandrasekaran

Data Scientist, PetroAnalytix

Mr. Chandrasekaran a data scientist in Kochi Innovation Centre, PetroAnalytix, India. He has research experience in the oil and gas domain for the past 10 years, in the field of reliability engineering, drilling dynamics and data analytics. He was involved in task forces to study and improve drilling performance of bottom-hole assemblies and to develop a mathematical model for early detection of down-hole problems. Chandrasekaran holds a bachelor’s degree in mechanical engineering from Anna University, Chennai, and a master’s degree in Computational engineering from the Indian Institute of Technology (IIT), Madras. He is a certified reliability engineer from American standards for quality (ASQ) and a certified six sigma green belt professional.

Mukhammad Taufan Rusady

Data Analyst, PetroAnalytix

Mr. Rusady is an experienced data analyst with PetroAnalytix in Indonesia for 3 years, working on real time analytics. His oil and gas experience is in the drilling data analytics and visualization domain, scientific and high performance computing, artificial intelligence, production optimization, and reservoir engineering and simulation. He holds a bachelor's degree in engineering physics from Institut Teknologi Sepuluh Nopember and an masters degree in petroleum engineering from Institut Teknologi Bandung (ITB).

SPE Webinars are FREE to members courtesy of the

image

Key:

Complete
Failed
Available
Locked
Webinar
11/14/2017 at 9:30 AM (EST)   |  90 minutes
11/14/2017 at 9:30 AM (EST)   |  90 minutes
Certificate
0.15 CEU/1.5 PDH credits  |  Certificate available
0.15 CEU/1.5 PDH credits  |  Certificate available