[ad_1]
One of the reasons the company focused its initial efforts on Canada is because the country has a large amount of geodetic data in the public domain, including descriptive field reports, outdated geological maps, geochemical data from well samples, aeromagnetic and electromagnetic data. … , lidar readings and satellite imagery from decades of research.
“We have a system where we can take all this data and store it in standard formats, control the quality of all the data, make it searchable and be able to programmatically access it,” says Goldman.
High tech
After collecting all the available information for the site, the KoBold team explores the data using machine learning. The company could, for example, build a model to predict which parts of the ore deposits have the highest cobalt concentrations, or create a new geological map of the region showing all the different rock types and fracture structures. It can add new data to these models as it is collected, allowing KoBold to adapt its intelligence strategy “in near real time,” Goldman says.
KoBold has already used insights from machine learning models to gain insight into its mining applications in Canada and develop its field programs. His partnership with the Stanford Center for Earth Resource Prediction, launched in February, adds an extra layer of analytics in the form of an AI “decision agent” that can plan an entire exploration plan.
Stanford geophysicist Jeff Kyers, who oversees the collaboration, explains that this digital decision maker estimates the uncertainty in the results of the KoBold model and then develops a data collection plan to consistently reduce that uncertainty. Like a chess player trying to win a game in as few moves as possible, the AI will seek to help KoBold make a decision about a potential client with the least amount of effort – whether it’s a decision to drill in a specific location or leave.
[ad_2]
Source link