Machine learning yields positive results for Gran Colombia
After several months of work, Gran Colombia Gold (TSX: GCM) confirmed the exploration targets identified by the machine learning system installed at its Segovia operation by GoldSpot Discoveries (TSXV: SPOT).
Teams from GoldSpot and Gran Colombia collaborated to leverage machine learning capabilities for data processing and prospectivity analysis to aid in establishing future drilling targets, both near the existing mine areas as well as regional exploration away from the main mines.
“We successfully tested some of our recent drill results against the preliminary findings in GoldSpot’s analysis. The favourable overlap of our actual drill results with the preliminary machine-learning models bodes well as we get ready to carry out about 70,000 metres of drilling at Segovia over the next approximately 18 months,” Serafino Iacono, executive chairman of Gran Colombia, said in a media statement.
Goldspot used its geoscience and machine science expertise to clean, unify and analyse Segovia exploration data and produce 2D and 3D targets for the exploration program.
The raw data also allowed the tech company to deliver newly constructed lithological and mineralization models, new geophysical products, and new structural interpretations and models.
Segovia is located in the Segovia-Remedios mining district of Antioquia, northwestern Colombia. It has produced over 5 million ounces of gold in the past 150 years.
Gran Colombia, the largest underground gold and silver producer in the South American country, acquired the operation in 2010.
Current mineral reserves sit at 1.9 million tonnes grading 11 grams per tonne of gold for 688,000 ounces, at cut-off grades ranging from 3.25 to 4.31g/t depending on the mining area and method.
Measured and indicated resources at Segovia, which consist of the producing El Silencio, Providencia and Sandra K mines, are 3.5Mt grading 11.8g/t for 1.3Moz using a 3g/t cut-off grade.