Machine learning, a modern incarnation of artificial intelligence, has shown great promise in solving problems that once defied formalism. What distinguishes machine learning is not merely its capacity for computation, but its capacity for adaptation—for constructing predictive models from data, often without explicit programming. The rise of machine learning has been driven by a confluence of forces: an explosion of data, advances in mathematical theory, and extraordinary improvements in computational capability. While once confined to finance, communication, and transport, machine learning has now entered the geosciences—a domain long marked by uncertainty, sparse data, and complex, multi-scale phenomena.

 In the context of Earth exploration, particularly for oil/gas and minerals, machine learning offers a new approach: not to replace the physics of the Earth, but to augment it. From seismic records to well logs, gravity fields to magnetics, the challenge is to extract structure from noise, signal from ambiguity—and to do so not merely by statistical means, but by combining human insight with algorithmic pattern recognition. This inaugural workshop in Perth brings together voices from academia, industry, and technology to explore how machine learning is shaping our understanding of the Earth. Through presentations, case studies, and discussion, we aim to chart the challenges ahead and the opportunities yet unrealized.