This paper is the result of mineral exploration engineering.

Objectives Artificial intelligence (AI) and machine learning (ML) technologies present opportunities for a paradigm shift in the field of mineral exploration. This paper aims to systematically analyze the development trajectory and application status of AI/ML in mineral exploration, providing theoretical support for the deep integration of intelligent technology and geological exploration.

Methods Through literature tracking, the domestic and abroad development history in the field of mineral exploration research was reviewed. The three research stages of machine learning in mineral exploration and the application progress over the past decade were systematically summarized.

Results AI/ML has become a hotspot in mineral exploration, playing an active role in areas such as integration and mining of deep mineral exploration information, automatic core recognition, image interpretation, missing value prediction, geophysical data processing and inversion, 3D geological modeling, and mineral prospectivity mapping.

Conclusions (1)AI/ML technologies significantly enhance exploration accuracy and efficiency through multi-source data integration and intelligent algorithms. (2) Current intelligent exploration still faces challenges such as sample scarcity, poor model interpretability, data heterogeneity, and limited cross-regional generalization capability, which hinder its large-scale application. (3) Future efforts should focus on integrating technologies such as transfer learning, physics-informed neural networks, and human-machine collaborative modeling to promote the development of intelligent exploration toward transparency, lightweight, and real-time capabilities, while strengthening interdisciplinary collaboration between geology and data science to drive technological innovation and paradigm transformation.