The research team aims to rapidly pinpoint the best-performing 2D materials, design nanostructures that guide light more efficiently, and speed up the detection and analysis of single-photon sources – the tiny light engines that could drive tomorrow’s quantum technologies.
To make this happen, the team is combining the strengths of three fields:
- Quantum photonics, which uses light to process and transmit information
- 2D materials, which are sheets of atoms only one layer thick
- Machine learning, which helps the team find and design the best materials and structures faster than ever
Impact
Their goal is to create compact, efficient quantum light sources that can be built right onto microchips. This could solve one of the biggest challenges in the field today: finding a practical and scalable way to generate single photons – the building blocks of many quantum systems.
If successful, this technology could lead to:
- Hacker-proof communication, powered by quantum encryption
- Super-sensitive sensors for medicine, navigation, and environmental monitoring
- Faster, more efficient quantum computers that outperform classical machines in key tasks
These advances are essential for the next generation of quantum devices that are more accessible, energy-efficient, and suitable for real-world deployment.
2D
At the heart of the research are special 2D materials arranged in patterns called moiré superlattices. These patterns can create unique “quantum light spots”, and machine learning helps the scientists identify and fine-tune them with incredible speed and precision.
By blending machine learning with quantum materials, the project is exploring a new frontier – one where AI doesn’t just analyze data but helps design the very materials that power future technology.
It’s a bold new approach that not only deepens our understanding of how light and matter interact on the smallest scales, but also opens doors to programmable arrays of quantum emitters – a potential game-changer for scalable quantum systems.
Aim
The team aims to deliver machine learning models that can automatically identify materials, classify quantum emission patterns, and fine-tune photonic designs, whilst creating the foundational knowledge needed to integrate quantum components seamlessly on a single chip.
In short, this project is helping to shrink, speed up, and smarten quantum technologies, paving the way for devices that are powerful, practical, and ready for the future.
