At La Trobe, Paul leads a team that uses AI and machine learning to analyze materials data in novel ways. His team applies these technologies to explore multi-dimensional datasets—going beyond surface-level insights. “AI allows us to dive deeper into the data, exploring it in one, two, three dimensions, and even across time,” he explained. This multi-dimensional analysis is key to understanding the complexities of materials, particularly in fields like surface science and characterization.

Pigram emphasized that his work is highly applied, focusing on solving real-world problems. “At La Trobe, we’re not just experimenting with AI for the sake of it. We’re looking at how AI and machine learning can be applied to real-world challenges in materials science,” he said. This practical approach has led his team to test various AI models, looking for the best methods to analyze their data. “There’s an enormous universe of AI approaches out there, and we’re constantly testing to see which one gives the best insights for our specific datasets,” he added.

While they modify existing machine learning models to fit their needs, Paul is clear that inventing new algorithms isn’t the primary focus. “Our main goal isn’t to develop new machine learning models from scratch. Instead, we’re focusing on adapting and refining existing ones to suit our applications,” he said.