The challenges facing mineral exploration and mining continue to mount as much of the world has already been surveyed and fewer deposits are economically recoverable. In mineral exploration, there is only a 5% success rate in brownfield exploration, and just a 0.5% success rate in greenfield exploration. When you compare this to oil and gas exploration, which makes greater use of computer modeling, there is an 35% success rate, leaving lots of room for improvement in mineral exploration.
Advances in data collection and storage technologies have vastly increased the amount of data available to a geologist; however it has led to databases that are far too vast and complex for geologists to effectively or efficiently evaluate.
At Minerva, we believe that the use of AI can revolutionize how companies search for mineral deposits. That’s exactly why we created TERRA, our AI platform for mineral exploration. With TERRA, users can standardize their mining and exploration data to ensure interoperability, enabling them to find, share and use that data for more sophisticated analytics by either a human or through machine learning and reasoning.
TERRA can help solve the issues of unmanageable data volume, organization, and decision support. The platform is built on a foundation of carefully structured human knowledge which allows it to provide conclusions on a variety of problems that are not well suited to traditional machine learning techniques. While machine learning techniques have made strides in aspects of mining, they continue to struggle with exploration, as mineral deposits are rare and complex with many different attributes… making the outputs difficult to interpret and validate without expensive field work.
Minerva optimizes mineral deposit discovery and metallurgical research by combining AI technologies with geological modelling, exploratory data analysis, and other modern technologies such as augmented reality. This optimum combination of AI technologies allows our clients to find the best locations for exploration, to explain in detail why each location was identified, and to provide advice on what additional exploration information to look for.
Minerva’s technology has been used in a number of projects for government agencies focused on identifying public domain exploration targets to promote mining within their jurisdictions. Last year Minerva completed the Yukon Mineral Targets project, an interactive website that allows the user to evaluate targets and understand how they were generated. Minerva recently completed a project in Papua New Guinea, the results of which will be announced publicly in early 2020.
Minerva has created a range of products in our TERRA Mining AI Suite that help mining and exploration companies harmonize their data, streamline their document management, find hundreds of new deposit-specific targets, or increase their R.O.I. in drill-hole assay data.
Yukon Mineral Targets, Canada
Generating good new mineral exploration targets is a difficult task, requiring the consideration of many variables.
Minerva’s approach to creating prospectivity maps for mineral exploration was designed to mimic the traditional methodology of an exploration geologist. We present 2,374 exploration targets, many of them new, which have been derived from the extensive geochemical sampling programs conducted in the Yukon by the Geological Survey of Canada.
Target maps for 59 different deposit-types are published on this site, each showing from 10’s to 100’s of locations in which there is evidence for the existence of a mineral deposit.
Prospectors and geologists can view targets by deposit type name, primary commodity, source of the model.
“Orogen has successfully utilized LEO to organize and search large numbers of scanned exploration documents in its proprietary property-file collections. With LEO, we are able to quickly search through hundreds of documents using keyword searches and obtain a listing of relevant documents along with contextual reference and a listing of other key geological words in the document. The resulting information is particularly useful in identifying geological features to support early exploration target concepts in targeted terranes.”
“By using Minerva’s cognitive AI to identify the geochemical relationships between various structures, we can essentially get an unbiased second opinion to augment our own exploration effort and at a price that’s about the cost of a single RAB hole.”
“This is a fantastic automatized tool for generating exploration targets and workable areas.”