I’m still talking about a #mineralfindertechnology (MFT) that has the potential to accelerate the speed of the exploration phase of mining, reduce costs, and increase the success rates. This technology been a game-changer for mining exploration for a decade, but is still not widely known.
MFT employs unique software and algorithms. These process the ore body data that comes from the ore samples and three different electromagnetic sources.
MFT mixes supervised and unsupervised deep learning algorithms, based on multilayered neural networks.
These are are effective for pattern recognition, anomaly detection and feature extraction.
The #MFT algorithm and modelling contrasts with the traditional methods. Conventional methods for resource models often require a great deal of subjective manual interpretation, and estimation, using whichever method generates the least error.
The accuracy has always been dependent on the skills, efficiency, and subjectivity of the operator. And the process is very slow - usually months long.
The MFT neural network deep learning approach can rapidly generate classified and domained orebody models.
These include the estimation of multiple numeric variables, and uncertainties, directly from the ore sample data, and spatially referenced pre-coded survey data.
This is the future of orebody modelling.
In my next posts we’ll have a look at a case study.