Called Maxta, the tool will allow miners to go backwards and forwards in time to look at historical geological data versus actual plant output and zap forward through their mining plans to see how they will be affected.
The tool was developed for Australian-based miner PanAust's Ban Houayxai gold-silver operation in Laos.
In 2018 a machine learning algorithm from Petra Data Science was installed at the operation to predict future metallurgical characteristics based on previous plant performance.
The algorithm integrated two years of three-dimensional geological data with plant data to derive a formula that could be applied to block models. This allowed both "backward" reconciliation analysis and "forward" predictions.
Data from about 10 million tonnes of ore was integrated and analysed in 12-hour batches over a two-year period.
Unlike conventional mine to mill studies based on samples and test work, or tracking batches of ore with markers, machine learning-based value chain optimisation uses large amounts of historical data to predict future plant performance.
Proprietary data integration software creates a digital twin of the value chain allowing machine learning algorithms to continuously "learn" from the geology and plant data to automatically update the prediction model.
Petra Data Science managing director Dr Penny Stewart said the Maxta digital twin was inspired by NASA's Cyber-Physical Systems Modelling and Analysis program
"Like mining, both aviation and NASA are heavily reliant upon spatial data," she said.
"Weather and climate wreaks havoc on aviation. Similarly, geological uncertainty affects mining."
Maxta is the result of three years of intensive research and development into data integration across the mine value chain.
Over the past year Maxta R&D has been focused on machine learning algorithms for mine value chain optimisation and real-time deployment.