Machine learning is becoming an appealing tool in various fields of earth sciences, especially in resources estimation. Six machine learning algorithms have been used to predict the presence of gold mineralization in drill core from geophysical logs acquired at the Lalor deposit, Manitoba, Canada. Results show that the integration of a set of rock physical properties — measured at closely spaced intervals along the drill core — with ensemble machine learning algorithms allows the detection of gold-bearing intervals with an adequate rate of success. Since the resulting prediction is continuous along the drill core, the use of this type of tool in the future will help geologists in selecting sound intervals for assay sampling and in modeling more continuous ore bodies during the entire life of a mine.

No abstract

No abstract

Deployment of carbon capture and storage on a large scale poses many challenges. One is the availability of reservoirs with suitable characteristics (high porosity and permeability, matched large emitters, etc.). Such a challenge might lead to the selection of reservoirs with relatively low porosity. In those environments, the rock matrix is often stiff and questions arise regarding the capabilities of seismic methods to monitor CO 2 injection. In this paper, a series of ultrasonic measurements were performed under various pressure and temperature conditions to test the seismic response of two low‐porosity reservoir samples of the St Lawrence Lowlands sedimentary basin to different CO 2 phases. Results show that the P‐wave velocity and amplitude can be used to detect the phase transition. Illustrative modeling of seismic reflectivities within a hypothetical geological formation with physical properties equal to that of the St Lawrence Lowlands sedimentary basin, suggests that a CO 2 liquid‐water contact is a potentially good seismic reflector. © 2017 Society of Chemical Industry and John Wiley & Sons, Ltd.

No abstract