Rock type (facies) identification plays a key role in the exploration and development of oil and gas reservoirs. Petroleum geologists are generally interested in categorizing rocks according to their ability to store and transmit fluids (porosity and permeability).

Conventionally, facies are manually identified by geologists based on the observation of core samples of rocks extracted from wells. Typical features considered for facies prediction are mineral composition (especially volume of sand and clay), porosity, fluid saturations, and texture characteristics. These features are mostly extracted from laboratory procedures. Nevertheless, core samples cannot always be obtained due to associated costs.

Traditional core-based facies identification is costly, time consuming, and subjective (e.g., different geologists may describe the same core with different results). To address some of these challenges, we have evaluated different techniques for automated facies classification using machine learning algorithms.
Watch Facies Detection with Supervised Machine Learning to learn more.



Federico Gamba
Senior Product Application Specialist
Thermo Fisher Scientific

Federico joined Thermo Fisher in 2003. His focus is on Digital Rock Analysis and 3D Visualization for E&P. He obtained an MSc with Honors in Computer Science at the University of Genoa (Italy) in 1993. His main mission is to support customers by helping them reduce their learning curve regarding a wide variety of Thermo Scientific application software solutions in order to increase productivity and gain time.

Registration form

Style Sheet for Global Design System
Style Sheet for Komodo Tabs