Fitzroy Minerals Inc. has announced the results of an integrated seismic and machine-learning targeting study at its Buen Retiro Copper Project in Copiapo, Chile, conducted with Australian technology firm Fleet Space Technologies. The study generated a ranked portfolio of nine previously untested exploration targets, all located within 400 metres of surface, by combining 3D Ambient Noise Tomography (ANT) data with prior geophysical surveys, geological models, and approximately 24,400 copper assays from 140 drill holes.
The significance of the announcement lies in the project’s geological setting and the challenges it presents. Buen Retiro is interpreted to share characteristics with major iron oxide copper-gold (IOCG) deposits such as Candelaria and Mantoverde, yet the sulphide potential of the wider property has barely been tested. Extensive alluvial gravel cover across the area has historically made surface geological mapping and target generation difficult. Fleet’s ANT surveys, which use natural seismic noise to build a 3D picture of the rock beneath the surface, mapped the project’s deeper geology well beyond the depths of current drilling, providing a framework to trace known mineralized trends and identify blind targets under cover. The machine-learning model then learned the relationship between geophysical data and copper assays to predict zones where copper mineralization above a 0.5% Cu threshold might occur, together with an uncertainty value for each block.
According to Merlin Marr-Johnson, President and CEO of Fitzroy, the new tool allows the company to test the exploration optionality of a large IOCG system in one of Chile’s most prolific copper-producing regions. “If the ML targeting is successful it will be a cost-effective discovery tool, creating value for shareholders,” he said. The nine targets were refined by excluding previously mined ground, mapped gravel cover, and areas within 200 metres of existing drill holes, focusing on ground with genuine exploration value. A summary of the four datasets and copper assay results used in the new ML targeting is available via Click Here to see Table 1 - Summary of the 4 datasets and copper assay results used in the new ML targeting.
Fitzroy has already commenced a 5,000-metre drilling program using diamond and reverse circulation rigs to test the new targets. As drill logs and assay results come in, the company and Fleet will update the ML model, so that each new hole serves three purposes: testing a specific target, improving or validating the model, and informing the next drilling decision. The news was disseminated through NEWMEDIAWIRE.
The targets are conceptual and have not yet been tested by drilling; they do not confirm the presence, grade, size or continuity of mineralization. The reliability of the model depends on data quality and coverage and tends to decrease with distance from existing drill holes and with depth. Nonetheless, the integration of advanced subsurface imaging with machine learning represents a notable shift in exploration methodology, offering a potentially cost-effective way to prioritize drilling in covered terrains and to unlock value from under-explored IOCG systems.
