AI, ML and Friends is a weekly seminar series within the School of Computing on Artificial Intelligence, Machine Learning, and related topics. We are open to attendees and presenters external to the school. Please sign up to the mailing list to receive weekly announcements including zoom details, and email the seminar organiser to schedule a talk.

Upcoming Seminars

01 October 2026, 11:00#

Artificial Intelligence-Assisted Chemical Gas Sensing: A Trans-disciplinary Exploration of AI-Augmented Sensors.#

Speaker: Allen Qian

Abstract: Chemical gas sensing using Metal Oxide (MOX) sensors is constrained by fundamental performance limits—sensitivity, selectivity, stability, and speed—and slow, trial-and-error development. This thesis introduces a framework that integrates Artificial Intelligence (AI) throughout the entire sensor lifecycle to accelerate discovery and enhance operational performance. First, addressing the manufacturing bottleneck, the research presents an image-to-performance screening framework. A deep learning model analyses Scanning Electron Microscope (SEM) images of Zinc Oxide sensors to predict performance with 92% accuracy, reducing hours of physical testing to seconds of inference. Furthermore, explainable AI extracts physically interpretable nanostructural design rules directly from these images Second, addressing operational limits, a machine learning workflow is applied to a WO3/ZIF-8 sensor array. By decoding multivariate transient responses, the system discriminates volatile organic compounds with 97.2% accuracy, cuts decision times from 30 minutes to 250 seconds, and drastically lowers effective detection limits. Ultimately, this thesis unifies these advancements into a closed-loop, AI-assisted lifecycle, demonstrating that optimal chemical sensors are no longer just superior materials, but co-designed systems of materials and machine intelligence.

Bio: Allen is a final-year PhD candidate at the Australian National University, Canberra. His research focuses on integrating AI into materials science discoveries. While pursuing his PhD, Allen also served as director of data science at the Australian Taxation Office, leading a team of 10 data scientists and delivering multiple high-impact data science solutions.

Where: Building 145, room 1.33