The present manuscript reports on the state-of-the-art and future perspectives of Machine Learning (ML) in petrology. To achieve this goal, it first introduces the basics of ML, including definitions, core concepts, and applications. Then, it starts reviewing the state-of-the-art of ML in petrology. Established applications mainly concern the so-called data-driven discovery and involve specific tasks like clustering, dimensionality reduction, classification, and regression. Among them, clustering and dimensionality reduction have been demonstrated to be valuable for decoding the chemical record stored in igneous and metamorphic phases and to enhance data visualization, respectively. Classification and regression tasks find applications, for example, in petrotectonic discrimination and geo-thermobarometry, respectively. The main core of the manuscript consists of depicting emerging trends and the future directions of ML in petrological investigations. I propose a future scenario where ML methods will progressively integrate and support established petrological methods in automating time-consuming and repetitive tasks, improving current models, and boosting discovery. In this framework, promising applications include (a) the acquisition of new multimodal petrologic data, (b) the development of data fusion techniques, physics-informed ML models, and ML-supported numerical simulations, and (c) the continuous exploration of the ML potential in petrology. To boost the contribution of ML in petrology, our main challenges are: (a) to improve the ability of ML models to capture the complexity of petrologic processes, (b) progressively link machine learning algorithms with the physical and thermodynamic nature of the investigated problems, (c) to start a collaborative effort among researchers coming from different disciplines, both in research and teaching.