Developed a new method for evaluating drill cores
CORESMART workflow enables quantitative determination of valuable metals in drill core – results published in the Australian Journal of Earth Sciences
With the current publication in the international Australian Journal of Earth Sciences , GEOS and Dimap Spectral GmbH report on the latest results of the AI-based prediction of the content of gold, copper and iron in cores based on hyperspectral core scans. The article “Performance measurements of machine learning and different neural network designs for prediction of geochemical properties based on hyperspectral core scans” demonstrates the performance of the newly developed method, which is now also commercially available as the CORESMART workflow.
It was impressively demonstrated that the AI-based CORESMART workflow developed by GEOS and Dimap can be used to quantitatively determine valuable metals in drill cores. An accuracy of the predictions of more than 80% is achieved. This goes well beyond the results of previous AI-based approaches. The very good performance is achieved on the one hand by the network structure used and on the other hand by the extremely extensive training data from more than 700 kilometers of drill cores with more than 110,000 chemical analyses.
Thus, this method can be used to minimize the cost of chemical analysis in exploration and re-evaluation of existing drill cores. In the investigations, the CORESMART workflow was tested for the elements gold, copper, iron, tin, tungsten, silver, nickel and uranium with prediction accuracies of more than 80%.
copy right by G.E.O.S.