Engineering & Mining Journal

FEB 2019

Engineering and Mining Journal - Whether the market is copper, gold, nickel, iron ore, lead/zinc, PGM, diamonds or other commodities, E&MJ takes the lead in projecting trends, following development and reporting on the most efficient operating pr

Issue link:

Contents of this Issue


Page 31 of 75

EXPLORATION 30 E&MJ • FEBRUARY 2019 release of energy is then registered by the detector in the XRF instrument, which in turn categorizes the energies by element. Handheld analyzers are convenient and adequate for a range of in-the-field identification requirements, but if great- er accuracy, flexibility and worker safety (protection from accidental X-ray expo- sure) are desired, a range of so-called benchtop analyzers are available as well. These can vary in size and configuration from units the size of a laser printer that can be used and stowed in the back of a vehicle or in a site office, to trailer or containerized setups that are touted as "laboratories in the field." Recent offerings in this area include Boart Longyear's TruScan, comprising a trailer-mounted module fitted with sam- ple handling and XRF scanning equip- ment. According to the company, TruScan is designed to provide same-day continu- ous analysis of the drill core and provide non-destructive, accurate, high-densi - ty elemental concentration data. Boart Longyear's Drilling Services utilizes TruS- can for elemental and photo scanning of core at the exploration site, providing geologists access to real-time geological data as the core is drilled. In addition, TruScan offers high-defini- tion wet, dry, and spot-scan photos of the retrieved rock core. Same-day TruScan data, according to the company, can be used by a geologist to log core more ac- curately the first time, identify alteration zones, and determine where to sample and where not to sample for lab analysis. In a similar vein, the Swedish-Austra- lian company Orexplore launched the Geo- Core X10, a digital drilling cores laboratory, which analyzes element concentrations and minerals contained in a drill core and provides a 3D representation of the rock's internal structure. Orexplore said the Geo- Core X10 is designed to work in remote lo- cations and has several flexible options for data storage and data transfer. Normally, the data generated by the GeoCore X10's high-resolution scanning engine is sent to a central server where it can be accessed by Orexplore's Insight analysis software. At sites that have access to a fast network connection, this is done automatically. In locations where there is either a very slow or no network available, the GeoCore X10 can store data locally on removable SSD (Solid State Drive) hard drives, which can then be transported and uploaded to a central server when a fast network is available. The drives also can be shipped directly to an Orexplore office for immediate uploading. Applying AI Recognizing the need for overall improve- ments in exploration data management and analysis capabilities, IT companies both large and small see it as an opportunity for application of Artificial Intelligence (AI) technology. Goldcorp and IBM, for exam- ple, have been collaborating since 2017 on a project aimed at teaching IBM's Watson AI platform to "think like a geologist" in or- der to make AI-based recommendations on where the company should focus its explo- ration efforts in the Red Lake gold district in Ontario, Canada. Other companies, such as Goldspot Discoveries, headquartered in Toronto, Ontario, and Earth AI, an Austra- lian company, are recent startups that ap- ply a branch of AI known as machine learn- ing to develop and refine mineral targeting systems that more effectively handle and analyze the growing volume of data associ- ated with exploration programs. Describing the Goldcorp/IBM AI col- laboration, Mark Fawcett, partner, Global Business Services at IBM, said, "One of the biggest challenges facing geologists is interpreting the vast amount of data that includes field mapping data, geochemical surveys, drill hole data, geophysical sur- veys, geological maps, Landsat imagery, aerial photographs, mine level plans, al- teration models, resource model data and reports in order to make the best decision on where to drill next. "Inputting that information into Watson and educating Watson on the pro- cess of exploration, gives the system the capacity to make more informed explora- tion decisions to improve the probability of discovery." The first phase of the IBM/Goldcorp program involved providing Watson with structured data from a wide range of sources, such as geophysical and geo- logical surveys, drillhole datasets, re- ports, academic papers and conference proceedings, providing insights into Red Lake's geology, current and historic min- ing and exploration activities and suc- cessful exploration techniques. "Phase two is where we start to edu- cate Watson to refine and build the ex- ploration model the system will use to make predictions and provide recommen- dations on where Goldcorp should direct its exploration activities," said Dariusz Piotrowski, global leader of cognitive and analytics development for Natural Re- sources at IBM. Exploring New Partnerships In addition to in-house corporate ini- tiatives aimed at improving exploration efficiency and chances for success, Boart Longyear says its TruScan systen can provide same-day continuous analysis of drill core and quickly return non-destructive, accurate, high-density elemental concentration data.

Articles in this issue

Links on this page

Archives of this issue

view archives of Engineering & Mining Journal - FEB 2019