Stock Photo: Getty Images
New research using artificial intelligence (AI) systems can help develop new gallium-based semiconductor materials much more quickly than traditional methods.
The international research, led by Flinders University and carried out in collaboration with Khalifa University in the United Arab Emirates, has built a machine learning platform that acts like a “smart materials discovery engine”. This can significantly reduce the time spent on complex computer and laboratory experiments to test and discover new materials for future semiconductors.
Semiconductors are used in high-tech applications ranging from wearable electronics, communication systems, and smartphones to medical applications, LED devices, and solar panels.
“The challenge is that there are millions of possible combinations of materials, and testing them one by one in the laboratory or in complex computer simulations is very time-consuming and expensive,” says Flinders University ARC Future Fellow Associate Professor Vi-Khanh Truong, lead author of the new paper in ACS Materials Letters, published by the American Chemical Society.
“Rather than randomly searching for materials, the AI we developed learns the hidden chemical laws that control how gallium-based materials behave and predicts entirely new material compositions with desirable electronic properties.”
Gallium is one of 31 important minerals found in Australia and has a wide range of uses. Although commonly used in the electronics field, it has recently gained attention for its efficiency in computer chip technology. Gallium arsenide, the main compound of gallium in electronics, is used in microwave circuits, high-speed switching circuits, and infrared circuits.
The AI system was trained using thousands of known semiconductor materials from the International Materials Database. They then used Bayesian optimization, a type of intelligent decision-making, to continually explore promising new gallium-containing materials while avoiding chemically impossible combinations.
“Importantly, the system does not simply generate random formulations; it checks whether the proposed materials are chemically realistic and physically stable before making recommendations. This greatly reduces wasted effort and accelerates the path to experimental validation,” said Associate Professor Truong, from Flinders School of Medicine’s Institute of Public Health Biomedical Nanoengineering.
“This research successfully generated multiple completely new gallium-based semiconductor candidates not present in existing databases.”
Associate Professor Truong said one of the key properties targeted in the research was the ‘band gap’, which determines how semiconductors interact with electricity and light.
“Different technologies require different bandgaps. Smaller bandgaps are useful for solar energy generation. Medium bandgaps are important for LEDs and optical devices. Larger bandgaps are important for high-power electronics and radiation-hardened systems.”
The paper “Discovery of gallium-containing semiconductors with targeted band gaps based on Bayesian optimization” (2026) by Tarek Khater, Aamna AlShehhi, Thong Nguyen-Minh Le, Vincent Chan, and Vi Khanh Truong was published in ACS Materials Letters DOI. 10.1021/acsmaterialslett.5c01482#15ed0a50-2a95-4059-8e27-2f12821fc5a7
Acknowledgments: Associate Professor Vi Khanh Truong acknowledges support from the Australian Research Council FT240100067 and the Channel 7 Children’s Research Foundation. High performance computing resources were provided by the Institute of Atomic and Molecular Science, Academia Sinica, Taiwan.
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
