It will be put to the test analysing geochemical data collected across the state to reveal patterns in big data that cannot be seen with standard methods as part of a research project with the Geological Survey of WA.

Lead researcher Dr Vladimir Puzyrev from Curtin University's Oil and Gas Innovation Centre and its School of Earth and Planetary Sciences said the researchers were using a machine learning technique called deep learning to help expand WA mineral exploration.

"Deep learning methods are completely transforming the landscape of data analysis because they achieve unprecedented performance levels across various tasks, significantly reducing the manual labour and subjectivity present in more conventional methods of exploration," Puzyrey said.

"The ultimate aim of this research project is to help identify new mineral deposits in WA by analysing big geochemical data using deep learning methods."

Researchers are analysing the Geological Survey of WA's Mineral Exploration database WAMEX, which has data and samples from the exploration projects in WA over many years.

Geological Survey of WA project lead and senior geologist Dr Paul Duuring said the WAMEX database contained more than 50 million samples.

"There are time and cost challenges in the manual quality control of such large data, so this project is an important step towards adding value to existing digital geochemical datasets," he said.

"An improved database opens new possibilities for WA's mineral exploration sector."

Puzyrev said the project also offered other potential applications, including identifying the most cost-effective and innovative geochemical data analysis method for the treatment of samples.

"More generally this research project also opens up potential new avenues for future research that will also benefit the state's mineral exploration sector," he said.