Harnessing the Power of Artificial Intelligence and Machine Learning in Mineral Exploration—Opportunities and Cautionary Notes

Editor’s note: The aim of the Geology and Mining series is to introduce early-career professionals and students to various aspects of mineral exploration, development, and mining in order to share the experiences and insight of each author on the myriad of topics involved with the mineral industry and the ways in which geoscientists contribute to each. Abstract Artificial intelligence (AI), and machine learning (ML) have emerged in the last few years from relative obscurity in the mineral exploration sector and they now attract significant attention from people in both industry and academia. However, due to the novelty of AI and ML applications, their practical use and potential remain enigmatic to many beyond a relatively few expert practitioners. We introduce this subject for the nonexpert and review some of the current applications and evolving uses. For the most traditionally minded geologist, we argue that ML can be an invaluable new tool, contributing to topics that range from exploratory data analysis to automated core logging and mineral prospectivity mapping, such that it will have a substantial impact on how exploration is conducted in the future. However, ML algorithms perform best with a large amount of homogeneously distributed clean data for a well-constrained objective. For this reason, the application to exploration strategy, especially for optimizing target selection, will be a challenge where data are heterogeneous, multiscale, amorphous, and discontinuous. For the more tech-savvy geologist and data scientist, we provide notes of caution regarding the limitations of ML applied to geoscience data, and reasons to temper expectations. Nonetheless, we project that such technologies, if used in an appropriate manner, will eventually be part of the full range of exploration tasks, allowing explorers to do more with their data in less time. However, whether this will tip the scales in favor of higher discovery rates remains to be demonstrated.

Error Estimation and Adaptivity for Differential Equations with Multiple Scales in Time

We consider systems of ordinary differential equations with multiple scales in time. In general, we are interested in the long time horizon of a slow variable that is coupled to solution components that act on a fast scale. Although the fast scale variables are essential for the dynamics of the coupled problem, they are often of no interest in themselves. Recently, we have proposed a temporal multiscale approach that fits into the framework of the heterogeneous multiscale method and that allows for efficient simulations with significant speedups. Fast and slow scales are decoupled by introducing local averages and by replacing fast scale contributions by localized periodic-in-time problems. Here, we generalize this multiscale approach to a larger class of problems, but in particular, we derive an a posteriori error estimator based on the dual weighted residual method that allows for a splitting of the error into averaging error, error on the slow scale and error on the fast scale. We demonstrate the accuracy of the error estimator and also its use for adaptive control of a numerical multiscale scheme.