Gübelin Gem Lab has teamed up with Swiss tech and research firm CSEM to develop a machine learning platform that improves on existing methods to determine the authenticity and origin of a gemstone.
Origin determination currently relies heavily on expert human judgment and analysis, but Gübelin Gem Lab and CSEM have partnered to automate these processes using machine learning, a key area of artificial intelligence (AI).
This new AI approach aims to increase the consistency and reliability of data interpretation, reduce potential human errors, and save time, according to the lab.
“The main benefit of deploying machine learning methods in gemmology is to increase the consistency of gem lab results and raise both the public’s and industry’s trust in their gemstones and jewellery, while also enabling the scalability of gem testing services,” said Dr. Daniel Nyfeler, managing director of Gübelin Gem Lab.
The joint proposal titled “Gemtelligence – Software development for the automated analysis of gemstones” was submitted to Innosuisse, a government institute that promotes scientific innovation. The proposal was recently approved.
With funding from the Swiss government, the project will encompass the assessment and evaluation of all types of analytical data typically collected in modern gem labs.
Gemtelligence is aimed at developing machine learning-based algorithms, which will be trained to evaluate standard gemstone characteristics. The base will be an existing catalogue of data from tens of thousands of clients’ gemstones that the Gübelin Gem Lab has tested since the 1970s, complemented through data from the unique Gübelin Reference Stone Collection that comprises of more than 27,000 gems.