The continuous growth in global demand for mineral resources and the increasing difficulty of mineral exploration have created bottlenecks for traditional mineral prediction methods in handling complex geological information and large amounts of data. This review aims to explore the latest research progress in machine learning technology in the field of large-scale mineral prediction from 2016 to 2025. By systematically searching the Web of Science core database, we have screened and analyzed 255 high-quality scientific studies. These studies cover key areas such as mineral information extraction, target area selection, mineral regularity modeling, and resource potential evaluation. The applied machine learning technologies include Random Forests, Support Vector Machines, Convolutional Neural Networks, Recurrent Neural Networks, etc., and have been widely used in the exploration and prediction of various mineral deposits such as porphyry copper, sandstone uranium, and tin. The findings indicate a substantial shift within the discipline towards the utilization of deep learning methodologies and the integration of multi-source geological data. There is a notable rise in the deployment of cutting-edge techniques, including automatic feature extraction, transfer learning, and few-shot learning. This review endeavors to synthesize the prevailing state and prospective developmental trajectory of machine learning within the domain of large-scale mineral prediction. It seeks to delineate the field’s progression, spotlight pivotal research dilemmas, and pinpoint innovative breakthroughs.

The metamorphism and geological significance of amphibolites in the Diebusige and Bayanwulashan Complexes of the eastern Alxa Block, North China Craton, were poorly understood until now. This study presents the results of petrology, laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) zircon U–Pb analysis, phase equilibrium modeling and geothermobarometry for these rocks. The peak mineral assemblage of clinopyroxene + hornblende + plagioclase + K-feldspar + ilmenite + quartz + melt is inferred for amphibolite sample ALS2164 in the Diebusige Complex. Correspondingly, the peak mineral assemblage of clinopyroxene + hornblende + plagioclase ± K-feldspar + ilmenite + quartz + melt is identified for amphibolite sample ALS2191 in the Bayanwulshan Complex. Phase equilibrium modelling constrained the peak metamorphic condition of amphibolite sample ALS2164 in the Diebusige Complex to be 825–910 °C/7.2–10.8 kbar, which is similar to that (800–870 °C/7.0–10.7 kbar) of amphibolite sample ALS2191 in the Bayanwulashan Complex. Hbl–pl–qz thermobarometry yielded the metamorphic PT conditions of 732–810 °C/3.0–6.7 kbar for these amphibolites, which are consistent with the average temperatures of 763 °C, 768 °C and 780 °C calculated by Ti-zircon thermometry. As a result, phase equilibrium modelling yielded wide PT condition ranges of 800–910 °C/7.0–10.8 kbar, the lower limit of which is consistent with the upper limit of estimates by the hbl–pl–qz thermobarometer. In addition, LA-ICP-MS U–Pb analysis on metamorphic zircons yielded weighted mean ²⁰⁷Pb/²⁰⁶Pb ages of 1901 ± 22–1817 ± 21 Ma, which represent the timing of amphibolite-facies metamorphism. As a whole, the PT estimates display a high geothermal gradient, which is consistent with coeval ultrahigh-temperature metamorphism and associated mantle-derived mafic-ultramafic rocks in the Diebusige Complex. Combing this information with the previously published data from the Diebusige Complex, an extensional setting after continental collision is inferred for the eastern Alxa Block during the late Paleoproterozoic. The HREE enrichment patterns of metamorphic zircons from the amphibolites in this study are in agreement with that these amphibolites formed at relatively shallower crust than the garnet-bearing mafic granulites in the Diebusige Complex.