Gübelin Gem Lab is celebrating its 100th anniversary with Gemtelligence, a new milestone in gemmology that uses machine learning to determine the origin and treatment of coloured gems.
Gemtelligence ensures consistency in the analysis of coloured gemstones and, for the first time, determines the origin of emeralds, rubies and sapphires using artificial intelligence and deep learning.
Developed in cooperation with the Swiss technology innovation centre CSEM, the platform revolutionises the way that gemmology interprets data by employing artificial intelligence (AI). This leads to greater analytical consistency and precision, thereby enhancing security and trust, according to Gübelin Gem Lab.
Gemtelligence uses an algorithm based entirely on AI to determine the country of origin of rubies, sapphires and emeralds. It also recognises heat treatments in rubies and sapphires.
The system draws on Gübelin Gem Lab’s reference stone collection that comprises over 28,000 gemstones from all commercially relevant mines. This is supplemented by analyses of thousands of high-grade customers’ stones that the lab has analysed since 1970.
The platform is being successfully implemented step by step in Gubelin laboratories in Lucerne, Hong Kong and New York. Each stone is currently still tested by human experts.
The algorithm offers greater precision, consistent assessments and increased efficiency, enabling gemmologists to delegate data interpretation to the programme and concentrate on research and development.
Daniel Nyfeler, managing director of the Gübelin Gem Lab and project manager for Gemtelligence, said, “The fascinating aspect of this project is not just the improved precision and consistency of the data evaluation but also the ability to simply dispense with time-consuming and expensive analyses. This is something the entire industry will profit from.”